Merge branch 'master' into GoogleDriveFolderFix

This may fix the failing ci

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -77,3 +77,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/2_site_support_request.yml

@@ -89,3 +89,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/3_site_feature_request.yml

@@ -85,3 +85,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/4_bug_report.yml

@@ -70,3 +70,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/5_feature_request.yml

@@ -64,3 +64,11 @@ body:
         [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc
         <more lines>
       render: shell
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/6_question.yml

@@ -70,3 +70,11 @@ body:
         [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc
         <more lines>
       render: shell
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/workflows/build.yml

@@ -266,7 +266,7 @@ jobs:
           # We need to ignore wheels otherwise we break universal2 builds
           python3 -m pip install -U --no-binary :all: -r requirements.txt
           # We need to fuse our own universal2 wheels for curl_cffi
-          python3 -m pip install -U delocate
+          python3 -m pip install -U 'delocate==0.11.0'
           mkdir curl_cffi_whls curl_cffi_universal2
           python3 devscripts/install_deps.py --print -o --include curl-cffi > requirements.txt
           for platform in "macosx_11_0_arm64" "macosx_11_0_x86_64"; do
@@ -409,7 +409,7 @@ jobs:
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.7.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.10.0-py3-none-any.whl"
 
       - name: Prepare
         run: |
@@ -469,7 +469,7 @@ jobs:
         run: |
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.7.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.10.0-py3-none-any.whl"
 
       - name: Prepare
         run: |

.github/workflows/core.yml

@@ -55,6 +55,7 @@ jobs:
     - name: Install test requirements
       run: python3 ./devscripts/install_deps.py --include test --include curl-cffi
     - name: Run tests
+      timeout-minutes: 15
       continue-on-error: False
       run: |
         python3 -m yt_dlp -v || true  # Print debug head

.github/workflows/issue-lockdown.yml

@@ -0,0 +1,21 @@
+name: Issue Lockdown
+on:
+  issues:
+    types: [opened]
+
+permissions:
+  issues: write
+
+jobs:
+  lockdown:
+    name: Issue Lockdown
+    if: vars.ISSUE_LOCKDOWN
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Lock new issue"
+        env:
+          GH_TOKEN: ${{ github.token }}
+          ISSUE_NUMBER: ${{ github.event.issue.number }}
+          REPOSITORY: ${{ github.repository }}
+        run: |
+          gh issue lock "${ISSUE_NUMBER}" -R "${REPOSITORY}"

.github/workflows/quick-test.yml

@@ -15,8 +15,9 @@ jobs:
       with:
         python-version: '3.8'
     - name: Install test requirements
-      run: python3 ./devscripts/install_deps.py --include test
+      run: python3 ./devscripts/install_deps.py -o --include test
     - name: Run tests
+      timeout-minutes: 15
       run: |
         python3 -m yt_dlp -v || true
         python3 ./devscripts/run_tests.py core

.github/workflows/release.yml

@@ -204,7 +204,7 @@ jobs:
           git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
           git add -u
           git commit -m "Release ${{ env.version }}" \
-            -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all :ci run dl"
+            -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all"
           git push origin --force ${{ github.event.ref }}:release
 
       - name: Get target commitish
@@ -325,7 +325,7 @@ jobs:
               "(https://github.com/yt-dlp/yt-dlp-master-builds/releases/latest \"Master builds\")"' || '' }} > ./RELEASE_NOTES
           printf '\n\n' >> ./RELEASE_NOTES
           cat >> ./RELEASE_NOTES << EOF
-          #### A description of the various files are in the [README](https://github.com/${{ github.repository }}#release-files)
+          #### A description of the various files is in the [README](https://github.com/${{ github.repository }}#release-files)
           ---
           $(python ./devscripts/make_changelog.py -vv --collapsible)
           EOF

.github/workflows/sanitize-comment.yml

@@ -0,0 +1,17 @@
+name: Sanitize comment
+
+on:
+  issue_comment:
+    types: [created, edited]
+
+permissions:
+  issues: write
+
+jobs:
+  sanitize-comment:
+    name: Sanitize comment
+    if: vars.SANITIZE_COMMENT && !github.event.issue.pull_request
+    runs-on: ubuntu-latest
+    steps:
+      - name: Sanitize comment
+        uses: yt-dlp/sanitize-comment@v1

CONTRIBUTORS

@@ -653,3 +653,23 @@ LeSuisse
 DunnesH
 iancmy
 mokrueger
+luvyana
+szantnerb
+hugepower
+scribblemaniac
+Codenade
+Demon000
+Deukhoofd
+grqz
+hibes
+Khaoklong51
+kieraneglin
+lengzuo
+naglis
+ndyanx
+otovalek
+quad
+rakslice
+sahilsinghss73
+tony-hn
+xingchensong

Changelog.md

@@ -4,6 +4,150 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2024.09.27
+
+#### Important changes
+- **The minimum *recommended* Python version has been raised to 3.9**
+Since Python 3.8 will reach end-of-life in October 2024, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086)
+
+#### Core changes
+- [Allow `none` arg to negate `--convert-subs` and `--convert-thumbnails`](https://github.com/yt-dlp/yt-dlp/commit/c08e0b20b5edd8957b8318716bc14e896d1b96f4) ([#11066](https://github.com/yt-dlp/yt-dlp/issues/11066)) by [kieraneglin](https://github.com/kieraneglin)
+- [Fix format sorting bug with vp9.2 vcodec](https://github.com/yt-dlp/yt-dlp/commit/8f4ea14680c7865d8ffac10a9174205d1d84ada7) ([#10884](https://github.com/yt-dlp/yt-dlp/issues/10884)) by [rakslice](https://github.com/rakslice)
+- [Raise minimum recommended Python version to 3.9](https://github.com/yt-dlp/yt-dlp/commit/cca534cd9e6850c70244f225a4a1895ef4bcdbec) ([#11098](https://github.com/yt-dlp/yt-dlp/issues/11098)) by [bashonly](https://github.com/bashonly)
+- **cookies**: [Improve error message for Windows `--cookies-from-browser chrome` issue](https://github.com/yt-dlp/yt-dlp/commit/b397a64691421ace5df09457c2a764821a2dc6f2) ([#11090](https://github.com/yt-dlp/yt-dlp/issues/11090)) by [seproDev](https://github.com/seproDev)
+- **utils**: `mimetype2ext`: [Recognize `aacp` as `aac`](https://github.com/yt-dlp/yt-dlp/commit/cc85596d5b59f0c14e9381b3675f619c1e12e597) ([#10860](https://github.com/yt-dlp/yt-dlp/issues/10860)) by [bashonly](https://github.com/bashonly)
+
+#### Extractor changes
+- [Fix JW Player format parsing](https://github.com/yt-dlp/yt-dlp/commit/409f8e9e3b4bde81ef76fc563256f876d2ff8099) ([#10956](https://github.com/yt-dlp/yt-dlp/issues/10956)) by [seproDev](https://github.com/seproDev)
+- [Handle decode errors when reading responses](https://github.com/yt-dlp/yt-dlp/commit/325001317d97f4545d66fac44c4ba772c6f45f22) ([#10868](https://github.com/yt-dlp/yt-dlp/issues/10868)) by [bashonly](https://github.com/bashonly)
+- **abc.net.au**: iview, showseries: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/7f909046f4dc0fba472b4963145aef6e0d42491b) ([#11101](https://github.com/yt-dlp/yt-dlp/issues/11101)) by [bashonly](https://github.com/bashonly)
+- **adn**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/cc88a54bb1ef285154775f8a6a413335ce4c71ce) ([#10749](https://github.com/yt-dlp/yt-dlp/issues/10749)) by [infanf](https://github.com/infanf)
+- **asobistage**: [Support redirected URLs](https://github.com/yt-dlp/yt-dlp/commit/a7d3235c84dac57a127cbe0ff38f7f7c2fdd8fa0) ([#10768](https://github.com/yt-dlp/yt-dlp/issues/10768)) by [pzhlkj6612](https://github.com/pzhlkj6612)
+- **bandcamp**: user: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/5d0176547f16a3642cd71627126e9dfc24981e20) ([#10328](https://github.com/yt-dlp/yt-dlp/issues/10328)) by [bashonly](https://github.com/bashonly), [quad](https://github.com/quad)
+- **beacon**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b4760c778d0c92c6e3f2bc8346cd72c8f08595ae) ([#9901](https://github.com/yt-dlp/yt-dlp/issues/9901)) by [Deukhoofd](https://github.com/Deukhoofd)
+- **bilibili**
+    - [Fix chapters and subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/a2000bc85730c950351d78bb818493dc39dca3cb) ([#11099](https://github.com/yt-dlp/yt-dlp/issues/11099)) by [bashonly](https://github.com/bashonly)
+    - [Fix festival URL support](https://github.com/yt-dlp/yt-dlp/commit/b43bd864851f2862e26caa85461c5d825d49d463) ([#10740](https://github.com/yt-dlp/yt-dlp/issues/10740)) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz)
+- **biliintl**: [Fix referer header](https://github.com/yt-dlp/yt-dlp/commit/a06bb586795ebab87a2356923acfc674d6f0e152) ([#11003](https://github.com/yt-dlp/yt-dlp/issues/11003)) by [Khaoklong51](https://github.com/Khaoklong51)
+- **dropbox**: [Fix password-protected video support](https://github.com/yt-dlp/yt-dlp/commit/63da31b3b29af90062d8a72a905ffe4b5e499042) ([#10735](https://github.com/yt-dlp/yt-dlp/issues/10735)) by [ndyanx](https://github.com/ndyanx)
+- **ertgr**: [Fix video extraction](https://github.com/yt-dlp/yt-dlp/commit/416686ed0cf792ec44ab059f3b229dd776077e14) ([#11091](https://github.com/yt-dlp/yt-dlp/issues/11091)) by [seproDev](https://github.com/seproDev)
+- **eurosport**: [Support local URL variants](https://github.com/yt-dlp/yt-dlp/commit/f0bb28504c8c2b75ee3e5796aed50de2a7f90a1b) ([#10785](https://github.com/yt-dlp/yt-dlp/issues/10785)) by [seproDev](https://github.com/seproDev)
+- **facebook**
+    - ads: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d62fef7e07d454c0d2ba2d69fb96d691dba1ded0) ([#10704](https://github.com/yt-dlp/yt-dlp/issues/10704)) by [kclauhk](https://github.com/kclauhk)
+    - reel: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/0e1b941c6b2caa688b0d3332e723d16dbafa4311) by [lengzuo](https://github.com/lengzuo)
+- **germanupa**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/124f058b546d652a359c67025bb479789bfbef0b) ([#10538](https://github.com/yt-dlp/yt-dlp/issues/10538)) by [grqz](https://github.com/grqz)
+- **hgtvde**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a555389c9bb32e589e00b4664974423fb7b04dcd) ([#10992](https://github.com/yt-dlp/yt-dlp/issues/10992)) by [bashonly](https://github.com/bashonly), [rdamas](https://github.com/rdamas)
+- **huya**: video: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/25c1cdaa2650563494d3bf00a38f72d0d9486bff) ([#10686](https://github.com/yt-dlp/yt-dlp/issues/10686)) by [hugepower](https://github.com/hugepower)
+- **iprima**: [Fix zoom URL support](https://github.com/yt-dlp/yt-dlp/commit/4a27b8f092f7f7c10b7a334d3535c97c2af02f0a) ([#10959](https://github.com/yt-dlp/yt-dlp/issues/10959)) by [otovalek](https://github.com/otovalek)
+- **khanacademy**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0fba08485b6445b72b5b63ae23ca2a73fa5d967f) ([#10913](https://github.com/yt-dlp/yt-dlp/issues/10913)) by [seproDev](https://github.com/seproDev)
+- **kick**
+    - clips: [Support new URL format](https://github.com/yt-dlp/yt-dlp/commit/0aa4426e9a35f7f8e184f1f2082b3b313c1448f7) ([#11107](https://github.com/yt-dlp/yt-dlp/issues/11107)) by [bashonly](https://github.com/bashonly)
+    - vod: [Support new URL format](https://github.com/yt-dlp/yt-dlp/commit/173d54c151b987409e3eb09552d8d89ed8fc50f7) ([#10988](https://github.com/yt-dlp/yt-dlp/issues/10988)) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz)
+- **kika**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e6f48ca80821939c1fd11ec2a0cdbf2fba9b258a) ([#5788](https://github.com/yt-dlp/yt-dlp/issues/5788)) by [1100101](https://github.com/1100101)
+- **lnkgo**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/fa83d0b36bc43d30fe9241c1e923f4614864b758) ([#10904](https://github.com/yt-dlp/yt-dlp/issues/10904)) by [naglis](https://github.com/naglis)
+- **loom**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/7509d692b37a7ec6230ea75bfe1e44a8de5eefce) ([#10760](https://github.com/yt-dlp/yt-dlp/issues/10760)) by [kclauhk](https://github.com/kclauhk)
+- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e2b3634e299be9c16a247ece3b1858d83889c324) ([#11083](https://github.com/yt-dlp/yt-dlp/issues/11083)) by [szantnerb](https://github.com/szantnerb)
+- **mojevideo**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/28b0ecba2af5b4919f198474b3d00a76ef322c31) ([#11019](https://github.com/yt-dlp/yt-dlp/issues/11019)) by [04-pasha-04](https://github.com/04-pasha-04), [pzhlkj6612](https://github.com/pzhlkj6612)
+- **niconico**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/eabb4680fdb09ba1f48d174a700a2e3b43f82add) ([#11103](https://github.com/yt-dlp/yt-dlp/issues/11103)) by [bashonly](https://github.com/bashonly)
+- **nzz**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4a9bc8c3630378bc29f0266126b503f6190c0430) ([#10461](https://github.com/yt-dlp/yt-dlp/issues/10461)) by [1-Byte](https://github.com/1-Byte)
+- **patreoncampaign**: [Support API URLs](https://github.com/yt-dlp/yt-dlp/commit/232e6db30c474d1b387e405342f34173ceeaf832) ([#10734](https://github.com/yt-dlp/yt-dlp/issues/10734)) by [bashonly](https://github.com/bashonly), [hibes](https://github.com/hibes)
+- **pinterest**: [Extend `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/c8c078fe28b0ffc15ef9646346c00c592fe71a78) ([#10867](https://github.com/yt-dlp/yt-dlp/issues/10867)) by [bashonly](https://github.com/bashonly), [sahilsinghss73](https://github.com/sahilsinghss73)
+- **radiko**: [Extract unique `id` values](https://github.com/yt-dlp/yt-dlp/commit/c8d096c5ce111411fbdbe2abb8fed54f317a6182) ([#10726](https://github.com/yt-dlp/yt-dlp/issues/10726)) by [garret1317](https://github.com/garret1317)
+- **rtp**: [Support more subpages](https://github.com/yt-dlp/yt-dlp/commit/d02df303d8e49390599db9f34482697e4d1cf5b2) ([#10787](https://github.com/yt-dlp/yt-dlp/issues/10787)) by [Demon000](https://github.com/Demon000)
+- **rumblechannel**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/ad0b857f459a6d390fbf124183916218c52f223a) ([#11049](https://github.com/yt-dlp/yt-dlp/issues/11049)) by [tony-hn](https://github.com/tony-hn)
+- **rutube**: [Support livestreams](https://github.com/yt-dlp/yt-dlp/commit/41be32e78c3845000dbac188ffb90ea3ea7c4dfa) ([#10844](https://github.com/yt-dlp/yt-dlp/issues/10844)) by [pzhlkj6612](https://github.com/pzhlkj6612)
+- **samplefocus**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/46f4c80bc363ee8116c33d37f65202e6c3470954) ([#10947](https://github.com/yt-dlp/yt-dlp/issues/10947)) by [seproDev](https://github.com/seproDev)
+- **screenrec**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/36f9e602ad55679764bc75a4f67f7562b1d6adcf) ([#10917](https://github.com/yt-dlp/yt-dlp/issues/10917)) by [naglis](https://github.com/naglis)
+- **sen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/41a241ca6ffb95b3d9aaf4f42106ca8cba9af1a6) ([#10952](https://github.com/yt-dlp/yt-dlp/issues/10952)) by [seproDev](https://github.com/seproDev)
+- **servus**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/300c91274f7ea5b1b0528fc5ee11cf1a61d4079e) ([#10944](https://github.com/yt-dlp/yt-dlp/issues/10944)) by [seproDev](https://github.com/seproDev)
+- **snapchatspotlight**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b37417e4f934fd8909788b493d017777155b0ae5) ([#11030](https://github.com/yt-dlp/yt-dlp/issues/11030)) by [seproDev](https://github.com/seproDev)
+- **svtpage**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/5a8a05aebb49693e78e1123015837ed5e961ff76) ([#11010](https://github.com/yt-dlp/yt-dlp/issues/11010)) by [diman8](https://github.com/diman8)
+- **tenplay**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d8d473002b654ab0e7b97ead869f58b4361eeae1) ([#10928](https://github.com/yt-dlp/yt-dlp/issues/10928)) by [aarubui](https://github.com/aarubui)
+- **tiktok**: [Fix web formats extraction](https://github.com/yt-dlp/yt-dlp/commit/3ad0b7f422d547204df687b6d0b2d9110fff3990) ([#11074](https://github.com/yt-dlp/yt-dlp/issues/11074)) by [bashonly](https://github.com/bashonly)
+- **twitter**: spaces: [Support video spaces](https://github.com/yt-dlp/yt-dlp/commit/bef1d4d6fc9493fda7f75e2289c07c507d10092f) ([#10789](https://github.com/yt-dlp/yt-dlp/issues/10789)) by [bashonly](https://github.com/bashonly)
+- **vidflex**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e978c312d6550a6ae4c9df18001afb1b420cb72f) ([#10002](https://github.com/yt-dlp/yt-dlp/issues/10002)) by [pzhlkj6612](https://github.com/pzhlkj6612)
+- **vimeo**
+    - [Always try to extract original format](https://github.com/yt-dlp/yt-dlp/commit/4115c24d157c5b5f63089d75c4e0f51d1f8b4489) ([#10721](https://github.com/yt-dlp/yt-dlp/issues/10721)) by [bashonly](https://github.com/bashonly) (With fixes in [e8e6a98](https://github.com/yt-dlp/yt-dlp/commit/e8e6a982a1b659eed434d225d7922f632bac6568) by [seproDev](https://github.com/seproDev))
+    - [Fix HLS audio format sorting](https://github.com/yt-dlp/yt-dlp/commit/a1b4ac2b8ed8e6eaa56044d439f1e0d00c2ba218) ([#11082](https://github.com/yt-dlp/yt-dlp/issues/11082)) by [fireattack](https://github.com/fireattack)
+- **watchespn**: [Improve auth support](https://github.com/yt-dlp/yt-dlp/commit/7adff8caf152dcf96d03aff69ed8545c0a63567c) ([#10910](https://github.com/yt-dlp/yt-dlp/issues/10910)) by [ischmidt20](https://github.com/ischmidt20)
+- **wistia**: [Support password-protected videos](https://github.com/yt-dlp/yt-dlp/commit/9f5c9a90898c5a1e672922d9cd799716c73cee34) ([#11100](https://github.com/yt-dlp/yt-dlp/issues/11100)) by [bashonly](https://github.com/bashonly)
+- **ximalaya**: [Add VIP support](https://github.com/yt-dlp/yt-dlp/commit/3dfd720d098b4d49d69cfc77e6376f22bcd90934) ([#10832](https://github.com/yt-dlp/yt-dlp/issues/10832)) by [seproDev](https://github.com/seproDev), [xingchensong](https://github.com/xingchensong)
+- **xinpianchang**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/3aa0156e05662923d130ddbc1c82596e38c01a00) ([#10950](https://github.com/yt-dlp/yt-dlp/issues/10950)) by [seproDev](https://github.com/seproDev)
+- **yleareena**: [Support podcasts](https://github.com/yt-dlp/yt-dlp/commit/48d629d461e05b1b19f5e53dc959bb9ebe95da42) ([#11104](https://github.com/yt-dlp/yt-dlp/issues/11104)) by [bashonly](https://github.com/bashonly)
+- **youtube**
+    - [Add `po_token`, `visitor_data`, `data_sync_id` extractor args](https://github.com/yt-dlp/yt-dlp/commit/3a3bd00037e9908e87da4fa9f2ad772aa34dc60e) ([#10648](https://github.com/yt-dlp/yt-dlp/issues/10648)) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz), [seproDev](https://github.com/seproDev) (With fixes in [fa2be9a](https://github.com/yt-dlp/yt-dlp/commit/fa2be9a7c63babede07480151363e54eee5702bd) by [bashonly](https://github.com/bashonly))
+    - [Support excluding `player_client`s in extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/49f3741a820ed142f6866317c2e7d247b130960e) ([#10710](https://github.com/yt-dlp/yt-dlp/issues/10710)) by [bashonly](https://github.com/bashonly)
+    - clip: [Prioritize `https` formats](https://github.com/yt-dlp/yt-dlp/commit/1d84b780cf33a1d84756825ac23f990a905703df) ([#11102](https://github.com/yt-dlp/yt-dlp/issues/11102)) by [bashonly](https://github.com/bashonly)
+    - tab: [Fix shorts tab extraction](https://github.com/yt-dlp/yt-dlp/commit/9431777b4c37129a6093080c77ca59960afbb9d7) ([#10938](https://github.com/yt-dlp/yt-dlp/issues/10938)) by [seproDev](https://github.com/seproDev)
+
+#### Networking changes
+- [Fix handler not being added to RequestError](https://github.com/yt-dlp/yt-dlp/commit/d1c4d88b2d912e8da5e76db455562ca63b1af690) ([#10955](https://github.com/yt-dlp/yt-dlp/issues/10955)) by [coletdjnz](https://github.com/coletdjnz)
+- [Pin `curl-cffi` version to < 0.7.2](https://github.com/yt-dlp/yt-dlp/commit/5bb1aa04dafce13ba9de707ea53169fab58b5207) ([#11092](https://github.com/yt-dlp/yt-dlp/issues/11092)) by [bashonly](https://github.com/bashonly)
+- **Request Handler**: websockets: [Upgrade websockets to 13.0](https://github.com/yt-dlp/yt-dlp/commit/6f9e6537434562d513d0c9b68ced8a61ade94a64) ([#10815](https://github.com/yt-dlp/yt-dlp/issues/10815)) by [coletdjnz](https://github.com/coletdjnz)
+
+#### Misc. changes
+- **build**
+    - [Bump PyInstaller version pin to `>=6.10.0`](https://github.com/yt-dlp/yt-dlp/commit/fb8b7f226d251e521a89b23c415e249e5b788e5c) ([#10709](https://github.com/yt-dlp/yt-dlp/issues/10709)) by [bashonly](https://github.com/bashonly)
+    - [Pin `delocate` version for `macos`](https://github.com/yt-dlp/yt-dlp/commit/7e41628ff523b3fe373b0981a5db441358980dab) ([#10901](https://github.com/yt-dlp/yt-dlp/issues/10901)) by [bashonly](https://github.com/bashonly)
+- **ci**
+    - [Add comment sanitization workflow](https://github.com/yt-dlp/yt-dlp/commit/b6200bdcf3a9415ae36859188f9a57e3e461c696) ([#10915](https://github.com/yt-dlp/yt-dlp/issues/10915)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+    - [Add issue tracker anti-spam protection](https://github.com/yt-dlp/yt-dlp/commit/ad9a8115aa29a1a95c961b16fcf129a228d98f50) ([#10861](https://github.com/yt-dlp/yt-dlp/issues/10861)) by [bashonly](https://github.com/bashonly)
+- **cleanup**: Miscellaneous: [c6387ab](https://github.com/yt-dlp/yt-dlp/commit/c6387abc1af9842bb0541288a5610abba9b1ab51) by [bashonly](https://github.com/bashonly), [Codenade](https://github.com/Codenade), [coletdjnz](https://github.com/coletdjnz), [grqz](https://github.com/grqz), [Grub4K](https://github.com/Grub4K), [pzhlkj6612](https://github.com/pzhlkj6612), [seproDev](https://github.com/seproDev)
+
+### 2024.08.06
+
+#### Core changes
+- **jsinterp**: [Improve `slice` implementation](https://github.com/yt-dlp/yt-dlp/commit/bb8bf1db993f59752d20b73b861bd55e40cf0e31) ([#10664](https://github.com/yt-dlp/yt-dlp/issues/10664)) by [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- **discoveryplusitaly**: [Support sport and olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c) ([#10655](https://github.com/yt-dlp/yt-dlp/issues/10655)) by [bashonly](https://github.com/bashonly)
+- **gem.cbc.ca**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/fc5eecfa31c9571b6031cc3968aaa0394be55d7a) ([#10565](https://github.com/yt-dlp/yt-dlp/issues/10565)) by [bashonly](https://github.com/bashonly), [scribblemaniac](https://github.com/scribblemaniac)
+- **niconico**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4d9231208332d4c32364b8cd814bff8b20232cae) ([#10677](https://github.com/yt-dlp/yt-dlp/issues/10677)) by [bashonly](https://github.com/bashonly)
+- **olympics**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/919540a9644e55deb78cdd6751757ec8fdaf76f4) ([#10625](https://github.com/yt-dlp/yt-dlp/issues/10625)) by [bashonly](https://github.com/bashonly)
+- **youku**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0088c6de23d832b117061a33e984dc452d992e9c) ([#10626](https://github.com/yt-dlp/yt-dlp/issues/10626)) by [hugepower](https://github.com/hugepower)
+- **youtube**
+    - [Change default player clients to `ios,web_creator`](https://github.com/yt-dlp/yt-dlp/commit/406f4c2e47502fffc1b0c210b4ee6487c89a44cb) ([#10674](https://github.com/yt-dlp/yt-dlp/issues/10674)) by [bashonly](https://github.com/bashonly)
+    - [Fix `n` function name extraction for player `b12cc44b`](https://github.com/yt-dlp/yt-dlp/commit/c86891eb9434b4d7eec426d38c0c625b5e13cb2f) ([#10668](https://github.com/yt-dlp/yt-dlp/issues/10668)) by [seproDev](https://github.com/seproDev)
+
+### 2024.08.01
+
+#### Core changes
+- **utils**: `unified_timestamp`: [Recognize Sunday](https://github.com/yt-dlp/yt-dlp/commit/6daf2c27c0464fba98337be30de0b66d520d0db1) ([#10589](https://github.com/yt-dlp/yt-dlp/issues/10589)) by [bashonly](https://github.com/bashonly)
+
+#### Extractor changes
+- **abematv**: [Fix availability extraction](https://github.com/yt-dlp/yt-dlp/commit/ef36d517f9b05785d61abca7691d9ab7d63cc75c) ([#10569](https://github.com/yt-dlp/yt-dlp/issues/10569)) by [middlingphys](https://github.com/middlingphys)
+- **cbc.ca**: player: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/94a1c5e642e468cebeb51f74c6c220434cb47d96) ([#10302](https://github.com/yt-dlp/yt-dlp/issues/10302)) by [bashonly](https://github.com/bashonly), [trainman261](https://github.com/trainman261)
+- **discoveryplus**: [Support olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/0b7728618417e1aa382722a4d29b916b594d4459) ([#10566](https://github.com/yt-dlp/yt-dlp/issues/10566)) by [bashonly](https://github.com/bashonly)
+- **kick**: clips: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb3936ae2b3ce96d0b53f9e17cad1082058f032b) ([#10572](https://github.com/yt-dlp/yt-dlp/issues/10572)) by [luvyana](https://github.com/luvyana)
+- **learningonscreen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/fe15d3178e242803ae7a934b90137f13598eba2e) ([#10590](https://github.com/yt-dlp/yt-dlp/issues/10590)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7e3e4779ad13e4511c9ba3869879e53f0267bd7a) ([#10605](https://github.com/yt-dlp/yt-dlp/issues/10605)) by [szantnerb](https://github.com/szantnerb)
+- **mlbtv**: [Fix makeup game extraction](https://github.com/yt-dlp/yt-dlp/commit/4b69e1b53ea21e631cd5dd68ff531e2f1671ec17) ([#10607](https://github.com/yt-dlp/yt-dlp/issues/10607)) by [bashonly](https://github.com/bashonly)
+- **olympics**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94) ([#10604](https://github.com/yt-dlp/yt-dlp/issues/10604)) by [bashonly](https://github.com/bashonly)
+- **tva**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/28d485714fef88937c82635438afba5db81f9089) ([#10567](https://github.com/yt-dlp/yt-dlp/issues/10567)) by [bashonly](https://github.com/bashonly)
+- **tver**: [Support olympic URLs](https://github.com/yt-dlp/yt-dlp/commit/5260696b1cba77161828941fdb38f09f14ac6c60) ([#10600](https://github.com/yt-dlp/yt-dlp/issues/10600)) by [vvto33](https://github.com/vvto33)
+- **vimeo**: review: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/2b6df93a243bdfb9d6bb5c1e18020625cd02d465) ([#10598](https://github.com/yt-dlp/yt-dlp/issues/10598)) by [bashonly](https://github.com/bashonly)
+- **youtube**
+    - [Change default player clients to `ios,tv`](https://github.com/yt-dlp/yt-dlp/commit/efb42763dec23ccf6a2e3bac3afbfefce8efd012) ([#10457](https://github.com/yt-dlp/yt-dlp/issues/10457)) by [seproDev](https://github.com/seproDev)
+    - [Fix `n` function name extraction for player `20dfca59`](https://github.com/yt-dlp/yt-dlp/commit/011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76) ([#10611](https://github.com/yt-dlp/yt-dlp/issues/10611)) by [bashonly](https://github.com/bashonly)
+    - [Fix age-verification workaround](https://github.com/yt-dlp/yt-dlp/commit/d19fcb934269465fd707e68a87f735ec6983e93d) ([#10610](https://github.com/yt-dlp/yt-dlp/issues/10610)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+    - [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/0e539617a41913c7da1edd74fb6543c10ad727b3) ([#10573](https://github.com/yt-dlp/yt-dlp/issues/10573)) by [bashonly](https://github.com/bashonly)
+
+#### Misc. changes
+- **cleanup**: Miscellaneous: [ffd7781](https://github.com/yt-dlp/yt-dlp/commit/ffd7781d6588926f820b44a34b9e6e3068fb9f97) by [bashonly](https://github.com/bashonly)
+
+### 2024.07.25
+
+#### Extractor changes
+- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly)
+- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly)
+- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly)
+- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly)
+- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly)
+- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly)
+
+#### Misc. changes
+- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly)
+
 ### 2024.07.16
 
 #### Core changes

README.md

@@ -200,7 +200,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
 
 The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting.
 
-* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE)
+* [**curl_cffi**](https://github.com/lexiforest/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lexiforest/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/lexiforest/curl_cffi/blob/main/LICENSE)
   * Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"`
   * Currently included in `yt-dlp.exe`, `yt-dlp_linux` and `yt-dlp_macos` builds
 
@@ -459,17 +459,17 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     conditions. Use a "\" to escape "&" or
                                     quotes if needed. If used multiple times,
                                     the filter matches if at least one of the
-                                    conditions is met. E.g. --match-filter
+                                    conditions is met. E.g. --match-filters
-                                    !is_live --match-filter "like_count>?100 &
+                                    !is_live --match-filters "like_count>?100 &
                                     description~='(?i)\bcats \& dogs\b'" matches
                                     only videos that are not live OR those that
                                     have a like count more than 100 (or the like
                                     field is not available) and also has a
                                     description that contains the phrase "cats &
-                                    dogs" (caseless). Use "--match-filter -" to
+                                    dogs" (caseless). Use "--match-filters -" to
                                     interactively ask whether to download each
                                     video
-    --no-match-filters              Do not use any --match-filter (default)
+    --no-match-filters              Do not use any --match-filters (default)
     --break-match-filters FILTER    Same as "--match-filters" but stops the
                                     download process when a video is rejected
     --no-break-match-filters        Do not use any --break-match-filters (default)
@@ -490,7 +490,7 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     encountering a file that is in the archive
                                     (default)
     --break-per-input               Alters --max-downloads, --break-on-existing,
-                                    --break-match-filter, and autonumber to
+                                    --break-match-filters, and autonumber to
                                     reset per input URL
     --no-break-per-input            --break-on-existing and similar options
                                     terminates the entire download queue
@@ -999,12 +999,16 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     be used multiple times
     --no-exec                       Remove any previously defined --exec
     --convert-subs FORMAT           Convert the subtitles to another format
-                                    (currently supported: ass, lrc, srt, vtt)
+                                    (currently supported: ass, lrc, srt, vtt).
-                                    (Alias: --convert-subtitles)
+                                    Use "--convert-subs none" to disable
+                                    conversion (default) (Alias: --convert-
+                                    subtitles)
     --convert-thumbnails FORMAT     Convert the thumbnails to another format
                                     (currently supported: jpg, png, webp). You
                                     can specify multiple rules using similar
-                                    syntax as --remux-video
+                                    syntax as "--remux-video". Use "--convert-
+                                    thumbnails none" to disable conversion
+                                    (default)
     --split-chapters                Split video into multiple files based on
                                     internal chapters. The "chapter:" prefix can
                                     be used with "--paths" and "--output" to set
@@ -1758,7 +1762,7 @@ $ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-"
 
 # EXTRACTOR ARGUMENTS
 
-Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
+Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
 
 Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"`
 
@@ -1767,7 +1771,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mediaconnect`, `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. The `android` clients will always be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
+* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
@@ -1775,8 +1779,11 @@ The following extractors use this feature:
     * E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
 * `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
 * `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
-* `innertube_key`: Innertube API key to use for all API requests
+* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used
 * `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
+* `data_sync_id`: Overrides the account Data Sync ID used in Innertube API requests. This may be needed if you are using an account with `youtube:player_skip=webpage,configs` or `youtubetab:skip=webpage`
+* `visitor_data`: Overrides the Visitor Data used in Innertube API requests. This should be used with `player_skip=webpage,configs` and without cookies. Note: this may have adverse effects if used improperly. If a session from a browser is wanted, you should pass cookies instead (which contain the Visitor ID)
+* `po_token`:  Proof of Origin (PO) Token(s) to use for requesting video playback. Comma seperated list of PO Tokens in the format `CLIENT+PO_TOKEN`, e.g. `youtube:po_token=web+XXX,android+YYY`
 
 #### youtubetab (YouTube playlists, channels, feeds, etc.)
 * `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details)
@@ -2177,9 +2184,9 @@ with yt_dlp.YoutubeDL(ydl_opts) as ydl:
 
 * **Output template improvements**: Output templates can now have date-time formatting, numeric offsets, object traversal etc. See [output template](#output-template) for details. Even more advanced operations can also be done with the help of `--parse-metadata` and `--replace-in-metadata`
 
-* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filter` etc
+* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filters` etc
 
-* **Improvements**: Regex and other operators in `--format`/`--match-filter`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
+* **Improvements**: Regex and other operators in `--format`/`--match-filters`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
 
 * **Plugins**: Extractors and PostProcessors can be loaded from an external file. See [plugins](#plugins) for details
 
@@ -2220,7 +2227,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * `certifi` will be used for SSL root certificates, if installed. If you want to use system certificates (e.g. self-signed), use `--compat-options no-certifi`
 * yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
 * ~~yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [aria2c](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is~~
-* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filter` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
+* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filters` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
 * yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
 * yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
 * The sub-modules `swfinterp`, `casefold` are removed.
@@ -2266,11 +2273,11 @@ While these options are redundant, they are still expected to be used due to the
     --get-thumbnail                  --print thumbnail
     -e, --get-title                  --print title
     -g, --get-url                    --print urls
-    --match-title REGEX              --match-filter "title ~= (?i)REGEX"
+    --match-title REGEX              --match-filters "title ~= (?i)REGEX"
-    --reject-title REGEX             --match-filter "title !~= (?i)REGEX"
+    --reject-title REGEX             --match-filters "title !~= (?i)REGEX"
-    --min-views COUNT                --match-filter "view_count >=? COUNT"
+    --min-views COUNT                --match-filters "view_count >=? COUNT"
-    --max-views COUNT                --match-filter "view_count <=? COUNT"
+    --max-views COUNT                --match-filters "view_count <=? COUNT"
-    --break-on-reject                Use --break-match-filter
+    --break-on-reject                Use --break-match-filters
     --user-agent UA                  --add-header "User-Agent:UA"
     --referer URL                    --add-header "Referer:URL"
     --playlist-start NUMBER          -I NUMBER:

devscripts/changelog_override.json

@@ -185,5 +185,10 @@
         "action": "add",
         "when": "6075a029dba70a89675ae1250e7cdfd91f0eba41",
         "short": "[priority] Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)\n    - A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors"
+    },
+    {
+        "action": "add",
+        "when": "fb8b7f226d251e521a89b23c415e249e5b788e5c",
+        "short": "[priority] **The minimum *recommended* Python version has been raised to 3.9**\nSince Python 3.8 will reach end-of-life in October 2024, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086)"
     }
 ]

devscripts/make_issue_template.py

@@ -46,6 +46,14 @@ VERBOSE_TMPL = '''
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.
 '''.strip()
 
 NO_SKIP = '''

pyproject.toml

@@ -49,14 +49,14 @@ dependencies = [
     "pycryptodomex",
     "requests>=2.32.2,<3",
     "urllib3>=1.26.17,<3",
-    "websockets>=12.0",
+    "websockets>=13.0",
 ]
 
 [project.optional-dependencies]
 default = []
 curl-cffi = [
     "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",
-    "curl-cffi>=0.5.10,!=0.6.*,<0.8; os_name!='nt' and implementation_name=='cpython'",
+    "curl-cffi>=0.5.10,!=0.6.*,<0.7.2; os_name!='nt' and implementation_name=='cpython'",
 ]
 secretstorage = [
     "cffi",
@@ -66,7 +66,7 @@ build = [
     "build",
     "hatchling",
     "pip",
-    "setuptools",
+    "setuptools>=71.0.2",  # 71.0.0 broke pyinstaller
     "wheel",
 ]
 dev = [
@@ -76,13 +76,13 @@ dev = [
 ]
 static-analysis = [
     "autopep8~=2.0",
-    "ruff~=0.5.0",
+    "ruff~=0.6.0",
 ]
 test = [
     "pytest~=8.1",
 ]
 pyinstaller = [
-    "pyinstaller>=6.7.0",  # for compat with setuptools>=70
+    "pyinstaller>=6.10.0",  # Windows temp cleanup fixed in 6.10.0
 ]
 py2exe = [
     "py2exe>=0.12",

supportedsites.md

@@ -143,6 +143,7 @@
  - **BBVTV**: [*bbvtv*](## "netrc machine")
  - **BBVTVLive**: [*bbvtv*](## "netrc machine")
  - **BBVTVRecordings**: [*bbvtv*](## "netrc machine")
+ - **BeaconTv**
  - **BeatBumpPlaylist**
  - **BeatBumpVideo**
  - **Beatport**
@@ -505,6 +506,7 @@
  - **gem.cbc.ca:playlist**
  - **Genius**
  - **GeniusLyrics**
+ - **Germanupa**: germanupa.de
  - **GetCourseRu**: [*getcourseru*](## "netrc machine")
  - **GetCourseRuPlayer**
  - **Gettr**
@@ -580,6 +582,7 @@
  - **HungamaAlbumPlaylist**
  - **HungamaSong**
  - **huya:live**: huya.com
+ - **huya:video**: 虎牙视频
  - **Hypem**
  - **Hytale**
  - **Icareus**
@@ -655,10 +658,12 @@
  - **Ketnet**
  - **khanacademy**
  - **khanacademy:unit**
- - **Kick**
+ - **kick:clips**
+ - **kick:live**
+ - **kick:vod**
  - **Kicker**
  - **KickStarter**
- - **KickVOD**
+ - **Kika**: KiKA.de
  - **kinja:embed**
  - **KinoPoisk**
  - **Kommunetv**
@@ -690,6 +695,7 @@
  - **Lcp**
  - **LcpPlay**
  - **Le**: 乐视网
+ - **LearningOnScreen**
  - **Lecture2Go**: (**Currently broken**)
  - **Lecturio**: [*lecturio*](## "netrc machine")
  - **LecturioCourse**: [*lecturio*](## "netrc machine")
@@ -720,7 +726,6 @@
  - **livestream:original**
  - **Livestreamfails**
  - **Lnk**
- - **LnkGo**
  - **loc**: Library of Congress
  - **loom**
  - **loom:folder**
@@ -754,7 +759,7 @@
  - **Masters**
  - **MatchTV**
  - **MBN**: mbn.co.kr (매일방송)
- - **MDR**: MDR.DE and KiKA
+ - **MDR**: MDR.DE
  - **MedalTV**
  - **media.ccc.de**
  - **media.ccc.de:lists**
@@ -809,6 +814,7 @@
  - **MNetTVLive**: [*mnettv*](## "netrc machine")
  - **MNetTVRecordings**: [*mnettv*](## "netrc machine")
  - **MochaVideo**
+ - **Mojevideo**: mojevideo.sk
  - **Mojvideo**
  - **Monstercat**
  - **MonsterSirenHypergryphMusic**
@@ -1140,7 +1146,6 @@
  - **QuantumTV**: [*quantumtv*](## "netrc machine")
  - **QuantumTVLive**: [*quantumtv*](## "netrc machine")
  - **QuantumTVRecordings**: [*quantumtv*](## "netrc machine")
- - **Qub**
  - **R7**: (**Currently broken**)
  - **R7Article**: (**Currently broken**)
  - **Radiko**
@@ -1284,12 +1289,14 @@
  - **Screencast**
  - **Screencastify**
  - **ScreencastOMatic**
+ - **ScreenRec**
  - **ScrippsNetworks**
  - **scrippsnetworks:watch**
  - **Scrolller**
  - **SCTE**: [*scte*](## "netrc machine") (**Currently broken**)
  - **SCTECourse**: [*scte*](## "netrc machine") (**Currently broken**)
  - **sejm**
+ - **Sen**
  - **SenalColombiaLive**: (**Currently broken**)
  - **SenateGov**
  - **SenateISVP**
@@ -1326,6 +1333,7 @@
  - **SlidesLive**
  - **Slutload**
  - **Smotrim**
+ - **SnapchatSpotlight**
  - **Snotr**
  - **Sohu**
  - **SohuV**
@@ -1517,9 +1525,9 @@
  - **tv5unis**
  - **tv5unis:video**
  - **tv8.it**
- - **TVA**
  - **TVANouvelles**
  - **TVANouvellesArticle**
+ - **tvaplus**: TVA+
  - **TVC**
  - **TVCArticle**
  - **TVer**
@@ -1607,6 +1615,7 @@
  - **videomore:season**
  - **videomore:video**
  - **VideoPress**
+ - **Vidflex**
  - **Vidio**: [*vidio*](## "netrc machine")
  - **VidioLive**: [*vidio*](## "netrc machine")
  - **VidioPremier**: [*vidio*](## "netrc machine")
@@ -1735,7 +1744,7 @@
  - **XiaoHongShu**: 小红书
  - **ximalaya**: 喜马拉雅FM
  - **ximalaya:album**: 喜马拉雅FM 专辑
- - **xinpianchang**: xinpianchang.com (**Currently broken**)
+ - **Xinpianchang**: 新片场
  - **XMinus**: (**Currently broken**)
  - **XNXX**
  - **Xstream**

test/test_YoutubeDL.py

@@ -236,6 +236,35 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
 
+    def test_format_selection_by_vcodec_sort(self):
+        formats = [
+            {'format_id': 'av1-format', 'ext': 'mp4', 'vcodec': 'av1', 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vp9-hdr-format', 'ext': 'mp4', 'vcodec': 'vp09.02.50.10.01.09.18.09.00', 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vp9-sdr-format', 'ext': 'mp4', 'vcodec': 'vp09.00.50.08', 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'h265-format', 'ext': 'mp4', 'vcodec': 'h265', 'acodec': 'none', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['vcodec:vp9.2']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-hdr-format')
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['vcodec:vp9']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-sdr-format')
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['+vcodec:vp9.2']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-hdr-format')
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['+vcodec:vp9']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-sdr-format')
+
     def test_format_selection_string_ops(self):
         formats = [
             {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},

test/test_jsinterp.py

@@ -403,6 +403,34 @@ class TestJSInterpreter(unittest.TestCase):
             self._test(jsi, [''], args=['', '-'])
             self._test(jsi, [], args=['', ''])
 
+    def test_slice(self):
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
+        self._test('function f(){return "012345678".slice()}', '012345678')
+        self._test('function f(){return "012345678".slice(0)}', '012345678')
+        self._test('function f(){return "012345678".slice(5)}', '5678')
+        self._test('function f(){return "012345678".slice(99)}', '')
+        self._test('function f(){return "012345678".slice(-2)}', '78')
+        self._test('function f(){return "012345678".slice(-99)}', '012345678')
+        self._test('function f(){return "012345678".slice(0, 0)}', '')
+        self._test('function f(){return "012345678".slice(1, 0)}', '')
+        self._test('function f(){return "012345678".slice(0, 1)}', '0')
+        self._test('function f(){return "012345678".slice(3, 6)}', '345')
+        self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
+        self._test('function f(){return "012345678".slice(-1, 1)}', '')
+        self._test('function f(){return "012345678".slice(-3, -1)}', '67')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_networking.py

@@ -822,6 +822,24 @@ class TestRequestHandlerMisc:
         rh.close()
         assert len(logging_handlers) == before_count
 
+    def test_wrap_request_errors(self):
+        class TestRequestHandler(RequestHandler):
+            def _validate(self, request):
+                if request.headers.get('x-fail'):
+                    raise UnsupportedRequest('test error')
+
+            def _send(self, request: Request):
+                raise RequestError('test error')
+
+        with TestRequestHandler(logger=FakeLogger()) as rh:
+            with pytest.raises(UnsupportedRequest, match='test error') as exc_info:
+                rh.validate(Request('http://example.com', headers={'x-fail': '1'}))
+            assert exc_info.value.handler is rh
+
+            with pytest.raises(RequestError, match='test error') as exc_info:
+                rh.send(Request('http://example.com'))
+            assert exc_info.value.handler is rh
+
 
 @pytest.mark.parametrize('handler', ['Urllib'], indirect=True)
 class TestUrllibRequestHandler(TestRequestHandlerBase):

test/test_utils.py

@@ -444,6 +444,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
         self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
         self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
+        self.assertEqual(unified_timestamp('Sunday, 26 Nov 2006, 19:00'), 1164567600)
+        self.assertEqual(unified_timestamp('wed, aug 16, 2008, 12:00pm'), 1218931200)
 
         self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
         self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
@@ -919,6 +921,11 @@ class TestUtil(unittest.TestCase):
             'acodec': 'none',
             'dynamic_range': 'HDR10',
         })
+        self.assertEqual(parse_codecs('vp09.02.50.10.01.09.18.09.00'), {
+            'vcodec': 'vp09.02.50.10.01.09.18.09.00',
+            'acodec': 'none',
+            'dynamic_range': 'HDR10',
+        })
         self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), {
             'vcodec': 'av01.0.12M.10.0.110.09.16.09.0',
             'acodec': 'none',

test/test_websockets.py

@@ -88,7 +88,7 @@ def create_wss_websocket_server():
     certfn = os.path.join(TEST_DIR, 'testcert.pem')
     sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
     sslctx.load_cert_chain(certfn, None)
-    return create_websocket_server(ssl_context=sslctx)
+    return create_websocket_server(ssl=sslctx)
 
 
 MTLS_CERT_DIR = os.path.join(TEST_DIR, 'testdata', 'certificate')
@@ -103,7 +103,7 @@ def create_mtls_wss_websocket_server():
     sslctx.load_verify_locations(cafile=cacertfn)
     sslctx.load_cert_chain(certfn, None)
 
-    return create_websocket_server(ssl_context=sslctx)
+    return create_websocket_server(ssl=sslctx)
 
 
 def create_legacy_wss_websocket_server():
@@ -112,7 +112,7 @@ def create_legacy_wss_websocket_server():
     sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
     sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
     sslctx.load_cert_chain(certfn, None)
-    return create_websocket_server(ssl_context=sslctx)
+    return create_websocket_server(ssl=sslctx)
 
 
 def ws_validate_and_send(rh, req):
@@ -139,7 +139,7 @@ class TestWebsSocketRequestHandlerConformance:
         cls.wss_thread, cls.wss_port = create_wss_websocket_server()
         cls.wss_base_url = f'wss://127.0.0.1:{cls.wss_port}'
 
-        cls.bad_wss_thread, cls.bad_wss_port = create_websocket_server(ssl_context=ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER))
+        cls.bad_wss_thread, cls.bad_wss_port = create_websocket_server(ssl=ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER))
         cls.bad_wss_host = f'wss://127.0.0.1:{cls.bad_wss_port}'
 
         cls.mtls_wss_thread, cls.mtls_wss_port = create_mtls_wss_websocket_server()

test/test_youtube_signature.py

@@ -171,6 +171,18 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
         'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
     ),
+    (
+        'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
+        'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
+    ),
+    (
+        'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
+        '-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
+    ),
+    (
+        'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
+        'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
+    ),
 ]
 
 

yt_dlp/__init__.py

@@ -235,6 +235,11 @@ def validate_options(opts):
         validate_regex('format sorting', f, FormatSorter.regex)
 
     # Postprocessor formats
+    if opts.convertsubtitles == 'none':
+        opts.convertsubtitles = None
+    if opts.convertthumbnails == 'none':
+        opts.convertthumbnails = None
+
     validate_regex('merge output format', opts.merge_output_format,
                    r'({0})(/({0}))*'.format('|'.join(map(re.escape, FFmpegMergerPP.SUPPORTED_EXTS))))
     validate_regex('audio format', opts.audioformat, FFmpegExtractAudioPP.FORMAT_RE)

yt_dlp/cookies.py

@@ -1053,8 +1053,9 @@ def _decrypt_windows_dpapi(ciphertext, logger):
         ctypes.byref(blob_out),  # pDataOut
     )
     if not ret:
-        logger.warning('failed to decrypt with DPAPI', only_once=True)
+        message = 'Failed to decrypt with DPAPI. See  https://github.com/yt-dlp/yt-dlp/issues/10927  for more info'
-        return None
+        logger.error(message)
+        raise DownloadError(message)  # force exit
 
     result = ctypes.string_at(blob_out.pbData, blob_out.cbData)
     ctypes.windll.kernel32.LocalFree(blob_out.pbData)

yt_dlp/downloader/external.py

@@ -508,7 +508,7 @@ class FFmpegFD(ExternalFD):
         env = None
         proxy = self.params.get('proxy')
         if proxy:
-            if not re.match(r'^[\da-zA-Z]+://', proxy):
+            if not re.match(r'[\da-zA-Z]+://', proxy):
                 proxy = f'http://{proxy}'
 
             if proxy.startswith('socks'):
@@ -559,7 +559,7 @@ class FFmpegFD(ExternalFD):
 
         selected_formats = info_dict.get('requested_formats') or [info_dict]
         for i, fmt in enumerate(selected_formats):
-            is_http = re.match(r'^https?://', fmt['url'])
+            is_http = re.match(r'https?://', fmt['url'])
             cookies = self.ydl.cookiejar.get_cookies_for_url(fmt['url']) if is_http else []
             if cookies:
                 args.extend(['-cookies', ''.join(

yt_dlp/extractor/_extractors.py

@@ -217,6 +217,7 @@ from .bbc import (
     BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
 )
+from .beacon import BeaconTvIE
 from .beatbump import (
     BeatBumpPlaylistIE,
     BeatBumpVideoIE,
@@ -729,6 +730,7 @@ from .genius import (
     GeniusIE,
     GeniusLyricsIE,
 )
+from .germanupa import GermanupaIE
 from .getcourseru import (
     GetCourseRuIE,
     GetCourseRuPlayerIE,
@@ -822,7 +824,10 @@ from .hungama import (
     HungamaIE,
     HungamaSongIE,
 )
-from .huya import HuyaLiveIE
+from .huya import (
+    HuyaLiveIE,
+    HuyaVideoIE,
+)
 from .hypem import HypemIE
 from .hypergryph import MonsterSirenHypergryphMusicIE
 from .hytale import HytaleIE
@@ -939,11 +944,13 @@ from .khanacademy import (
     KhanAcademyUnitIE,
 )
 from .kick import (
+    KickClipIE,
     KickIE,
     KickVODIE,
 )
 from .kicker import KickerIE
 from .kickstarter import KickStarterIE
+from .kika import KikaIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
 from .kommunetv import KommunetvIE
@@ -986,6 +993,7 @@ from .lcp import (
     LcpIE,
     LcpPlayIE,
 )
+from .learningonscreen import LearningOnScreenIE
 from .lecture2go import Lecture2GoIE
 from .lecturio import (
     LecturioCourseIE,
@@ -1034,10 +1042,7 @@ from .livestream import (
     LivestreamShortenerIE,
 )
 from .livestreamfails import LivestreamfailsIE
-from .lnkgo import (
+from .lnk import LnkIE
-    LnkGoIE,
-    LnkIE,
-)
 from .loom import (
     LoomFolderIE,
     LoomIE,
@@ -1162,6 +1167,7 @@ from .mlb import (
 )
 from .mlssoccer import MLSSoccerIE
 from .mocha import MochaVideoIE
+from .mojevideo import MojevideoIE
 from .mojvideo import MojvideoIE
 from .monstercat import MonstercatIE
 from .motherless import (
@@ -1808,6 +1814,7 @@ from .screen9 import Screen9IE
 from .screencast import ScreencastIE
 from .screencastify import ScreencastifyIE
 from .screencastomatic import ScreencastOMaticIE
+from .screenrec import ScreenRecIE
 from .scrippsnetworks import (
     ScrippsNetworksIE,
     ScrippsNetworksWatchIE,
@@ -1818,6 +1825,7 @@ from .scte import (
     SCTECourseIE,
 )
 from .sejmpl import SejmIE
+from .sen import SenIE
 from .senalcolombia import SenalColombiaLiveIE
 from .senategov import (
     SenateGovIE,
@@ -1873,6 +1881,7 @@ from .slideshare import SlideshareIE
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
 from .smotrim import SmotrimIE
+from .snapchat import SnapchatSpotlightIE
 from .snotr import SnotrIE
 from .sohu import (
     SohuIE,
@@ -2169,10 +2178,7 @@ from .tv5unis import (
     TV5UnisVideoIE,
 )
 from .tv24ua import TV24UAVideoIE
-from .tva import (
+from .tva import TVAIE
-    TVAIE,
-    QubIE,
-)
 from .tvanouvelles import (
     TVANouvellesArticleIE,
     TVANouvellesIE,
@@ -2312,6 +2318,7 @@ from .videomore import (
     VideomoreVideoIE,
 )
 from .videopress import VideoPressIE
+from .vidflex import VidflexIE
 from .vidio import (
     VidioIE,
     VidioLiveIE,

yt_dlp/extractor/abc.py

@@ -387,17 +387,27 @@ class ABCIViewShowSeriesIE(InfoExtractor):
             'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
         },
         'playlist_count': 15,
+        'skip': 'This program is not currently available in ABC iview',
+    }, {
+        'url': 'https://iview.abc.net.au/show/inbestigators',
+        'info_dict': {
+            'id': '175343-1',
+            'title': 'Series 1',
+            'description': 'md5:b9976935a6450e5b78ce2a940a755685',
+            'series': 'The Inbestigators',
+            'season': 'Series 1',
+            'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.+\.jpg',
+        },
+        'playlist_count': 17,
     }]
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
         webpage = self._download_webpage(url, show_id)
-        webpage_data = self._search_regex(
+        video_data = self._search_json(
-            r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
+            r'window\.__INITIAL_STATE__\s*=\s*[\'"]', webpage, 'initial state', show_id,
-            webpage, 'initial state')
+            transform_source=lambda x: x.encode().decode('unicode_escape'),
-        video_data = self._parse_json(
+            end_pattern=r'[\'"]\s*;')['route']['pageData']['_embedded']
-            unescapeHTML(webpage_data).encode().decode('unicode_escape'), show_id)
-        video_data = video_data['route']['pageData']['_embedded']
 
         highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])
         if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):

yt_dlp/extractor/abematv.py

@@ -9,12 +9,12 @@ import re
 import struct
 import time
 import urllib.parse
-import urllib.request
-import urllib.response
 import uuid
 
 from .common import InfoExtractor
 from ..aes import aes_ecb_decrypt
+from ..networking import RequestHandler, Response
+from ..networking.exceptions import TransportError
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
@@ -26,37 +26,36 @@ from ..utils import (
     traverse_obj,
     update_url_query,
 )
-from ..utils.networking import clean_proxies
 
 
-def add_opener(ydl, handler):  # FIXME: Create proper API in .networking
+class AbemaLicenseRH(RequestHandler):
-    """Add a handler for opening URLs, like _download_webpage"""
+    _SUPPORTED_URL_SCHEMES = ('abematv-license',)
-    # https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
+    _SUPPORTED_PROXY_SCHEMES = None
-    # https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
+    _SUPPORTED_FEATURES = None
-    rh = ydl._request_director.handlers['Urllib']
+    RH_NAME = 'abematv_license'
-    if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
-        return
-    headers = ydl.params['http_headers'].copy()
-    proxies = ydl.proxies.copy()
-    clean_proxies(proxies, headers)
-    opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies)
-    assert isinstance(opener, urllib.request.OpenerDirector)
-    opener.add_handler(handler)
-    rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
 
+    _STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
+    _HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
 
-class AbemaLicenseHandler(urllib.request.BaseHandler):
+    def __init__(self, *, ie: 'AbemaTVIE', **kwargs):
-    handler_order = 499
+        super().__init__(**kwargs)
-    STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
-    HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
-
-    def __init__(self, ie: 'AbemaTVIE'):
-        # the protocol that this should really handle is 'abematv-license://'
-        # abematv_license_open is just a placeholder for development purposes
-        # ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
-        setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
         self.ie = ie
 
+    def _send(self, request):
+        url = request.url
+        ticket = urllib.parse.urlparse(url).netloc
+
+        try:
+            response_data = self._get_videokey_from_ticket(ticket)
+        except ExtractorError as e:
+            raise TransportError(cause=e.cause) from e
+        except (IndexError, KeyError, TypeError) as e:
+            raise TransportError(cause=repr(e)) from e
+
+        return Response(
+            io.BytesIO(response_data), url,
+            headers={'Content-Length': str(len(response_data))})
+
     def _get_videokey_from_ticket(self, ticket):
         to_show = self.ie.get_param('verbose', False)
         media_token = self.ie._get_media_token(to_show=to_show)
@@ -72,25 +71,17 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
                 'Content-Type': 'application/json',
             })
 
-        res = decode_base_n(license_response['k'], table=self.STRTABLE)
+        res = decode_base_n(license_response['k'], table=self._STRTABLE)
         encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
 
         h = hmac.new(
-            binascii.unhexlify(self.HKEY),
+            binascii.unhexlify(self._HKEY),
             (license_response['cid'] + self.ie._DEVICE_ID).encode(),
             digestmod=hashlib.sha256)
         enckey = bytes_to_intlist(h.digest())
 
         return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
 
-    def abematv_license_open(self, url):
-        url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
-        ticket = urllib.parse.urlparse(url).netloc
-        response_data = self._get_videokey_from_ticket(ticket)
-        return urllib.response.addinfourl(io.BytesIO(response_data), headers={
-            'Content-Length': str(len(response_data)),
-        }, url=url, code=200)
-
 
 class AbemaTVBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'abematv'
@@ -139,7 +130,7 @@ class AbemaTVBaseIE(InfoExtractor):
         if self._USERTOKEN:
             return self._USERTOKEN
 
-        add_opener(self._downloader, AbemaLicenseHandler(self))
+        self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
 
         username, _ = self._get_login_info()
         auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')
@@ -386,8 +377,7 @@ class AbemaTVIE(AbemaTVBaseIE):
                 f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
                 note='Checking playability',
                 headers=headers)
-            ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
+            if not traverse_obj(api_response, ('label', 'free', {bool})):
-            if 3 not in ondemand_types:
                 # cannot acquire decryption key for these streams
                 self.report_warning('This is a premium-only stream')
                 availability = 'premium_only'

yt_dlp/extractor/academicearth.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class AcademicEarthCourseIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
+    _VALID_URL = r'https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
     IE_NAME = 'AcademicEarth:Course'
     _TEST = {
         'url': 'http://academicearth.org/playlists/laws-of-nature/',

yt_dlp/extractor/adn.py

@@ -49,9 +49,9 @@ class ADNBaseIE(InfoExtractor):
 
 
 class ADNIE(ADNBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://animationdigitalnetwork.com/video/fruits-basket/9841-episode-1-a-ce-soir',
+        'url': 'https://animationdigitalnetwork.com/video/558-fruits-basket/9841-episode-1-a-ce-soir',
         'md5': '1c9ef066ceb302c86f80c2b371615261',
         'info_dict': {
             'id': '9841',
@@ -71,10 +71,7 @@ class ADNIE(ADNBaseIE):
         },
         'skip': 'Only available in French and German speaking Europe',
     }, {
-        'url': 'http://animedigitalnetwork.com/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
+        'url': 'https://animationdigitalnetwork.com/de/video/973-the-eminence-in-shadow/23550-folge-1',
-        'only_matching': True,
-    }, {
-        'url': 'https://animationdigitalnetwork.com/de/video/the-eminence-in-shadow/23550-folge-1',
         'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
         'info_dict': {
             'id': '23550',
@@ -167,7 +164,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                     'username': username,
                 })) or {}).get('accessToken')
             if access_token:
-                self._HEADERS = {'authorization': 'Bearer ' + access_token}
+                self._HEADERS['Authorization'] = f'Bearer {access_token}'
         except ExtractorError as e:
             message = None
             if isinstance(e.cause, HTTPError) and e.cause.status == 401:
@@ -178,6 +175,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
 
     def _real_extract(self, url):
         lang, video_id = self._match_valid_url(url).group('lang', 'id')
+        self._HEADERS['X-Target-Distribution'] = lang or 'fr'
         video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
         player = self._download_json(
             video_base_url + 'configuration', video_id,
@@ -218,7 +216,6 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                 links_data = self._download_json(
                     links_url, video_id, 'Downloading links JSON metadata', headers={
                         'X-Player-Token': authorization,
-                        'X-Target-Distribution': lang or 'fr',
                         **self._HEADERS,
                     }, query={
                         'freeWithAds': 'true',
@@ -257,6 +254,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                 load_balancer_data = self._download_json(
                     load_balancer_url, video_id,
                     f'Downloading {format_id} {quality} JSON metadata',
+                    headers=self._HEADERS,
                     fatal=False) or {}
                 m3u8_url = load_balancer_data.get('location')
                 if not m3u8_url:
@@ -277,7 +275,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
 
         video = (self._download_json(
             self._API_BASE_URL + f'video/{video_id}', video_id,
-            'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
+            'Downloading additional video metadata', fatal=False, headers=self._HEADERS) or {}).get('video') or {}
         show = video.get('show') or {}
 
         return {
@@ -299,9 +297,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
 
 
 class ADNSeasonIE(ADNBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>[^/?#]+)/?(?:$|[#?])'
+    _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>\d+)[^/?#]*/?(?:$|[#?])'
     _TESTS = [{
-        'url': 'https://animationdigitalnetwork.com/video/tokyo-mew-mew-new',
+        'url': 'https://animationdigitalnetwork.com/video/911-tokyo-mew-mew-new',
         'playlist_count': 12,
         'info_dict': {
             'id': '911',
@@ -312,16 +310,14 @@ class ADNSeasonIE(ADNBaseIE):
 
     def _real_extract(self, url):
         lang, video_show_slug = self._match_valid_url(url).group('lang', 'id')
+        self._HEADERS['X-Target-Distribution'] = lang or 'fr'
         show = self._download_json(
             f'{self._API_BASE_URL}show/{video_show_slug}/', video_show_slug,
             'Downloading show JSON metadata', headers=self._HEADERS)['show']
         show_id = str(show['id'])
         episodes = self._download_json(
             f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
-            'Downloading episode list', headers={
+            'Downloading episode list', headers=self._HEADERS, query={
-                'X-Target-Distribution': lang or 'fr',
-                **self._HEADERS,
-            }, query={
                 'order': 'asc',
                 'limit': '-1',
             })

yt_dlp/extractor/applepodcasts.py

@@ -1,27 +1,42 @@
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     clean_podcast_url,
-    get_element_by_class,
     int_or_none,
     parse_iso8601,
-    try_get,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ApplePodcastsIE(InfoExtractor):
     _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
     _TESTS = [{
+        'url': 'https://podcasts.apple.com/us/podcast/ferreck-dawn-to-the-break-of-dawn-117/id1625658232?i=1000665010654',
+        'md5': '82cc219b8cc1dcf8bfc5a5e99b23b172',
+        'info_dict': {
+            'id': '1000665010654',
+            'ext': 'mp3',
+            'title': 'Ferreck Dawn - To The Break of Dawn 117',
+            'episode': 'Ferreck Dawn - To The Break of Dawn 117',
+            'description': 'md5:1fc571102f79dbd0a77bfd71ffda23bc',
+            'upload_date': '20240812',
+            'timestamp': 1723449600,
+            'duration': 3596,
+            'series': 'Ferreck Dawn - To The Break of Dawn',
+            'thumbnail': 're:.+[.](png|jpe?g|webp)',
+        },
+    }, {
         'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
-        'md5': '41dc31cd650143e530d9423b6b5a344f',
+        'md5': 'baf8a6b8b8aa6062dbb4639ed73d0052',
         'info_dict': {
             'id': '1000482637777',
             'ext': 'mp3',
             'title': '207 - Whitney Webb Returns',
+            'episode': '207 - Whitney Webb Returns',
+            'episode_number': 207,
             'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
             'upload_date': '20200705',
             'timestamp': 1593932400,
-            'duration': 6454,
+            'duration': 5369,
             'series': 'The Tim Dillon Show',
             'thumbnail': 're:.+[.](png|jpe?g|webp)',
         },
@@ -39,47 +54,24 @@ class ApplePodcastsIE(InfoExtractor):
     def _real_extract(self, url):
         episode_id = self._match_id(url)
         webpage = self._download_webpage(url, episode_id)
-        episode_data = {}
+        server_data = self._search_json(
-        ember_data = {}
+            r'<script [^>]*\bid=["\']serialized-server-data["\'][^>]*>', webpage,
-        # new page type 2021-11
+            'server data', episode_id, contains_pattern=r'\[{(?s:.+)}\]')[0]['data']
-        amp_data = self._parse_json(self._search_regex(
+        model_data = traverse_obj(server_data, (
-            r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
+            'headerButtonItems', lambda _, v: v['$kind'] == 'bookmark' and v['modelType'] == 'EpisodeOffer',
-            webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
+            'model', {dict}, any))
-        amp_data = try_get(amp_data,
-                           lambda a: self._parse_json(
-                               next(a[x] for x in iter(a) if episode_id in x),
-                               episode_id),
-                           dict) or {}
-        amp_data = amp_data.get('d') or []
-        episode_data = try_get(
-            amp_data,
-            lambda a: next(x for x in a
-                           if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
-            dict)
-        if not episode_data:
-            # try pre 2021-11 page type: TODO: consider deleting if no longer used
-            ember_data = self._parse_json(self._search_regex(
-                r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
-                webpage, 'ember data'), episode_id) or {}
-            ember_data = ember_data.get(episode_id) or ember_data
-            episode_data = try_get(ember_data, lambda x: x['data'], dict)
-        episode = episode_data['attributes']
-        description = episode.get('description') or {}
-
-        series = None
-        for inc in (amp_data or ember_data.get('included') or []):
-            if inc.get('type') == 'media/podcast':
-                series = try_get(inc, lambda x: x['attributes']['name'])
-        series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
 
         return {
             'id': episode_id,
-            'title': episode.get('name'),
+            **self._json_ld(
-            'url': clean_podcast_url(episode['assetUrl']),
+                traverse_obj(server_data, ('seoData', 'schemaContent', {dict}))
-            'description': description.get('standard') or description.get('short'),
+                or self._yield_json_ld(webpage, episode_id, fatal=False), episode_id, fatal=False),
-            'timestamp': parse_iso8601(episode.get('releaseDateTime')),
+            **traverse_obj(model_data, {
-            'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
+                'title': ('title', {str}),
-            'series': series,
+                'url': ('streamUrl', {clean_podcast_url}),
+                'timestamp': ('releaseDate', {parse_iso8601}),
+                'duration': ('duration', {int_or_none}),
+            }),
             'thumbnail': self._og_search_thumbnail(webpage),
             'vcodec': 'none',
         }

yt_dlp/extractor/ard.py

@@ -231,7 +231,7 @@ class ARDIE(InfoExtractor):
 
 class ARDBetaMediathekIE(InfoExtractor):
     IE_NAME = 'ARDMediathek'
-    _VALID_URL = r'''(?x)https://
+    _VALID_URL = r'''(?x)https?://
         (?:(?:beta|www)\.)?ardmediathek\.de/
         (?:[^/]+/)?
         (?:player|live|video)/
@@ -470,7 +470,7 @@ class ARDBetaMediathekIE(InfoExtractor):
 
 
 class ARDMediathekCollectionIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https://
+    _VALID_URL = r'''(?x)https?://
         (?:(?:beta|www)\.)?ardmediathek\.de/
         (?:[^/?#]+/)?
         (?P<playlist>sendung|serie|sammlung)/

yt_dlp/extractor/asobistage.py

@@ -101,9 +101,10 @@ class AsobiStageIE(InfoExtractor):
         self._HEADERS['Authorization'] = f'Bearer {token}'
 
     def _real_extract(self, url):
-        video_id, event, type_, slug = self._match_valid_url(url).group('id', 'event', 'type', 'slug')
+        webpage, urlh = self._download_webpage_handle(url, self._match_id(url))
+        video_id, event, type_, slug = self._match_valid_url(urlh.url).group('id', 'event', 'type', 'slug')
         video_type = {'archive': 'archives', 'player': 'broadcasts'}[type_]
-        webpage = self._download_webpage(url, video_id)
+
         event_data = traverse_obj(
             self._search_nextjs_data(webpage, video_id, default={}),
             ('props', 'pageProps', 'eventCMSData', {

yt_dlp/extractor/bandcamp.py

@@ -1,3 +1,5 @@
+import functools
+import json
 import random
 import re
 import time
@@ -6,7 +8,9 @@ from .common import InfoExtractor
 from ..utils import (
     KNOWN_EXTENSIONS,
     ExtractorError,
+    extract_attributes,
     float_or_none,
+    get_element_html_by_id,
     int_or_none,
     parse_filesize,
     str_or_none,
@@ -17,6 +21,7 @@ from ..utils import (
     url_or_none,
     urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class BandcampIE(InfoExtractor):
@@ -459,7 +464,7 @@ class BandcampUserIE(InfoExtractor):
         },
     }, {
         'url': 'https://coldworldofficial.bandcamp.com/music',
-        'playlist_mincount': 10,
+        'playlist_mincount': 7,
         'info_dict': {
             'id': 'coldworldofficial',
             'title': 'Discography of coldworldofficial',
@@ -473,12 +478,19 @@ class BandcampUserIE(InfoExtractor):
         },
     }]
 
+    def _yield_items(self, webpage):
+        yield from (
+            re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
+            or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
+
+        yield from traverse_obj(webpage, (
+            {functools.partial(get_element_html_by_id, 'music-grid')}, {extract_attributes},
+            'data-client-items', {json.loads}, ..., 'page_url', {str}))
+
     def _real_extract(self, url):
         uploader = self._match_id(url)
         webpage = self._download_webpage(url, uploader)
 
-        discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
-                            or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
-
         return self.playlist_from_matches(
-            discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))
+            self._yield_items(webpage), uploader, f'Discography of {uploader}',
+            getter=functools.partial(urljoin, url))

yt_dlp/extractor/beacon.py

@@ -0,0 +1,68 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_iso8601,
+    traverse_obj,
+)
+
+
+class BeaconTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?beacon\.tv/content/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://beacon.tv/content/welcome-to-beacon',
+        'md5': 'b3f5932d437f288e662f10f3bfc5bd04',
+        'info_dict': {
+            'id': 'welcome-to-beacon',
+            'ext': 'mp4',
+            'upload_date': '20240509',
+            'description': 'md5:ea2bd32e71acf3f9fca6937412cc3563',
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/I4CkkEvN/poster.jpg?width=720',
+            'title': 'Your home for Critical Role!',
+            'timestamp': 1715227200,
+            'duration': 105.494,
+        },
+    }, {
+        'url': 'https://beacon.tv/content/re-slayers-take-trailer',
+        'md5': 'd879b091485dbed2245094c8152afd89',
+        'info_dict': {
+            'id': 're-slayers-take-trailer',
+            'ext': 'mp4',
+            'title': 'The Re-Slayer’s Take | Official Trailer',
+            'timestamp': 1715189040,
+            'upload_date': '20240508',
+            'duration': 53.249,
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/PW5ApIw3/poster.jpg?width=720',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        content_data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
+            'props', 'pageProps', '__APOLLO_STATE__',
+            lambda k, v: k.startswith('Content:') and v['slug'] == video_id, any))
+        if not content_data:
+            raise ExtractorError('Failed to extract content data')
+
+        jwplayer_data = traverse_obj(content_data, (
+            (('contentVideo', 'video', 'videoData'),
+             ('contentPodcast', 'podcast', 'audioData')), {json.loads}, {dict}, any))
+        if not jwplayer_data:
+            if content_data.get('contentType') not in ('videoPodcast', 'video', 'podcast'):
+                raise ExtractorError('Content is not a video/podcast', expected=True)
+            if traverse_obj(content_data, ('contentTier', '__ref')) != 'MemberTier:65b258d178f89be87b4dc0a4':
+                self.raise_login_required('This video/podcast is for members only')
+            raise ExtractorError('Failed to extract content')
+
+        return {
+            **self._parse_jwplayer_data(jwplayer_data, video_id),
+            **traverse_obj(content_data, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'timestamp': ('publishedAt', {parse_iso8601}),
+            }),
+        }

yt_dlp/extractor/bilibili.py

@@ -46,6 +46,7 @@ from ..utils import (
 
 
 class BilibiliBaseIE(InfoExtractor):
+    _HEADERS = {'Referer': 'https://www.bilibili.com/'}
     _FORMAT_ID_RE = re.compile(r'-(\d+)\.m4s\?')
     _WBI_KEY_CACHE_TIMEOUT = 30  # exact expire timeout is unclear, use 30s for one session
     _wbi_key_cache = {}
@@ -192,7 +193,7 @@ class BilibiliBaseIE(InfoExtractor):
         video_info = self._download_json(
             'https://api.bilibili.com/x/player/v2', video_id,
             query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid},
-            note=f'Extracting subtitle info {cid}')
+            note=f'Extracting subtitle info {cid}', headers=self._HEADERS)
         if traverse_obj(video_info, ('data', 'need_login_subtitle')):
             self.report_warning(
                 f'Subtitles are only available when logged in. {self._login_hint()}', only_once=True)
@@ -207,7 +208,7 @@ class BilibiliBaseIE(InfoExtractor):
     def _get_chapters(self, aid, cid):
         chapters = aid and cid and self._download_json(
             'https://api.bilibili.com/x/player/v2', aid, query={'aid': aid, 'cid': cid},
-            note='Extracting chapters', fatal=False)
+            note='Extracting chapters', fatal=False, headers=self._HEADERS)
         return traverse_obj(chapters, ('data', 'view_points', ..., {
             'title': 'content',
             'start_time': 'from',
@@ -298,7 +299,7 @@ class BilibiliBaseIE(InfoExtractor):
 
 
 class BiliBiliIE(BilibiliBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'https://www.bilibili.com/video/BV13x41117TL',
@@ -622,6 +623,10 @@ class BiliBiliIE(BilibiliBaseIE):
             'ext': 'mp4',
         },
         'skip': 'geo-restricted',
+    }, {
+        'note': 'has - in the last path segment of the url',
+        'url': 'https://www.bilibili.com/festival/bh3-7th?bvid=BV1tr4y1f7p2&',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -1017,8 +1022,6 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
 
 
 class BilibiliCheeseBaseIE(BilibiliBaseIE):
-    _HEADERS = {'Referer': 'https://www.bilibili.com/'}
-
     def _extract_episode(self, season_info, ep_id):
         episode_info = traverse_obj(season_info, (
             'episodes', lambda _, v: v['id'] == int(ep_id)), get_all=False)
@@ -1848,7 +1851,7 @@ class BiliBiliPlayerIE(InfoExtractor):
 class BiliIntlBaseIE(InfoExtractor):
     _API_URL = 'https://api.bilibili.tv/intl/gateway'
     _NETRC_MACHINE = 'biliintl'
-    _HEADERS = {'Referer': 'https://www.bilibili.com/'}
+    _HEADERS = {'Referer': 'https://www.bilibili.tv/'}
 
     def _call_api(self, endpoint, *args, **kwargs):
         json = self._download_json(self._API_URL + endpoint, *args, **kwargs)

yt_dlp/extractor/callin.py

@@ -3,7 +3,7 @@ from ..utils import float_or_none, int_or_none, make_archive_id, traverse_obj
 
 
 class CallinIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?callin\.com/(episode)/(?P<id>[-a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?P<id>[-a-zA-Z]+)'
     _TESTS = [{
         'url': 'https://www.callin.com/episode/the-title-ix-regime-and-the-long-march-through-EBfXYSrsjc',
         'info_dict': {

yt_dlp/extractor/cbc.py

@@ -1,4 +1,5 @@
 import base64
+import functools
 import json
 import re
 import time
@@ -6,17 +7,24 @@ import urllib.parse
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
+from ..networking import HEADRequest
 from ..utils import (
     ExtractorError,
+    float_or_none,
     int_or_none,
     join_nonempty,
     js_to_json,
+    mimetype2ext,
     orderedSet,
     parse_iso8601,
+    replace_extension,
     smuggle_url,
     strip_or_none,
     traverse_obj,
     try_get,
+    update_url,
+    url_basename,
+    url_or_none,
 )
 
 
@@ -149,6 +157,7 @@ class CBCIE(InfoExtractor):
 class CBCPlayerIE(InfoExtractor):
     IE_NAME = 'cbc.ca:player'
     _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/(?:video/)?|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
+    _GEO_COUNTRIES = ['CA']
     _TESTS = [{
         'url': 'http://www.cbc.ca/player/play/2683190193',
         'md5': '64d25f841ddf4ddb28a235338af32e2c',
@@ -172,21 +181,20 @@ class CBCPlayerIE(InfoExtractor):
             'description': 'md5:dd3b692f0a139b0369943150bd1c46a9',
             'timestamp': 1425704400,
             'upload_date': '20150307',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
-            'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
             'chapters': [],
             'duration': 494.811,
-            'categories': ['AudioMobile/All in a Weekend Montreal'],
+            'categories': ['All in a Weekend Montreal'],
-            'tags': 'count:8',
+            'tags': 'count:11',
             'location': 'Quebec',
             'series': 'All in a Weekend Montreal',
             'season': 'Season 2015',
             'season_number': 2015,
             'media_type': 'Excerpt',
+            'genres': ['Other'],
         },
     }, {
         'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2164402062',
-        'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
         'info_dict': {
             'id': '2164402062',
             'ext': 'mp4',
@@ -194,107 +202,168 @@ class CBCPlayerIE(InfoExtractor):
             'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
             'timestamp': 1320410746,
             'upload_date': '20111104',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
             'chapters': [],
             'duration': 186.867,
             'series': 'CBC News: Windsor at 6:00',
-            'categories': ['News/Canada/Windsor'],
+            'categories': ['Windsor'],
             'location': 'Windsor',
-            'tags': ['cancer'],
+            'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
-            'creators': ['Allison Johnson'],
             'media_type': 'Excerpt',
+            'genres': ['News'],
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
         'url': 'https://www.cbc.ca/player/play/1.2985700',
         'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
         'info_dict': {
-            'id': '2657631896',
+            'id': '1.2985700',
             'ext': 'mp3',
             'title': 'CBC Montreal is organizing its first ever community hackathon!',
             'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
             'timestamp': 1425704400,
             'upload_date': '20150307',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
-            'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
             'chapters': [],
             'duration': 494.811,
-            'categories': ['AudioMobile/All in a Weekend Montreal'],
+            'categories': ['All in a Weekend Montreal'],
-            'tags': 'count:8',
+            'tags': 'count:11',
             'location': 'Quebec',
             'series': 'All in a Weekend Montreal',
             'season': 'Season 2015',
             'season_number': 2015,
             'media_type': 'Excerpt',
+            'genres': ['Other'],
         },
     }, {
         'url': 'https://www.cbc.ca/player/play/1.1711287',
-        'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
         'info_dict': {
-            'id': '2164402062',
+            'id': '1.1711287',
             'ext': 'mp4',
             'title': 'Cancer survivor four times over',
             'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
             'timestamp': 1320410746,
             'upload_date': '20111104',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
             'chapters': [],
             'duration': 186.867,
             'series': 'CBC News: Windsor at 6:00',
-            'categories': ['News/Canada/Windsor'],
+            'categories': ['Windsor'],
             'location': 'Windsor',
-            'tags': ['cancer'],
+            'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
-            'creators': ['Allison Johnson'],
             'media_type': 'Excerpt',
+            'genres': ['News'],
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Has subtitles
         # These broadcasts expire after ~1 month, can find new test URL here:
         # https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
-        'url': 'https://www.cbc.ca/player/play/1.7159484',
+        'url': 'https://www.cbc.ca/player/play/video/9.6424403',
-        'md5': '6ed6cd0fc2ef568d2297ba68a763d455',
+        'md5': '8025909eaffcf0adf59922904def9a5e',
         'info_dict': {
-            'id': '2324213316001',
+            'id': '9.6424403',
             'ext': 'mp4',
-            'title': 'The National | School boards sue social media giants',
+            'title': 'The National | N.W.T. wildfire emergency',
-            'description': 'md5:4b4db69322fa32186c3ce426da07402c',
+            'description': 'md5:ada33d36d1df69347ed575905bfd496c',
-            'timestamp': 1711681200,
+            'timestamp': 1718589600,
-            'duration': 2743.400,
+            'duration': 2692.833,
-            'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
+            'subtitles': {
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/607/559/thumbnail.jpeg',
+                'en-US': [{
-            'uploader': 'CBCC-NEW',
+                    'name': 'English Captions',
+                    'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt',
+                }],
+            },
+            'thumbnail': 'https://i.cbc.ca/ais/6272b5c6-5e78-4c05-915d-0e36672e33d1,1714756287822/full/max/0/default.jpg',
             'chapters': 'count:5',
-            'upload_date': '20240329',
+            'upload_date': '20240617',
-            'categories': 'count:4',
+            'categories': ['News', 'The National', 'The National Latest Broadcasts'],
             'series': 'The National - Full Show',
-            'tags': 'count:1',
+            'tags': ['The National'],
-            'creators': ['News'],
             'location': 'Canada',
             'media_type': 'Full Program',
+            'genres': ['News'],
         },
     }, {
         'url': 'https://www.cbc.ca/player/play/video/1.7194274',
         'md5': '188b96cf6bdcb2540e178a6caa957128',
         'info_dict': {
-            'id': '2334524995812',
+            'id': '1.7194274',
             'ext': 'mp4',
             'title': '#TheMoment a rare white spirit moose was spotted in Alberta',
             'description': 'md5:18ae269a2d0265c5b0bbe4b2e1ac61a3',
             'timestamp': 1714788791,
             'duration': 77.678,
             'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/201/543/THE_MOMENT.jpg',
+            'thumbnail': 'https://i.cbc.ca/ais/1.7194274,1717224990425/full/max/0/default.jpg',
-            'uploader': 'CBCC-NEW',
+            'chapters': [],
-            'chapters': 'count:0',
-            'upload_date': '20240504',
             'categories': 'count:3',
             'series': 'The National',
-            'tags': 'count:15',
+            'tags': 'count:17',
-            'creators': ['encoder'],
             'location': 'Canada',
             'media_type': 'Excerpt',
+            'upload_date': '20240504',
+            'genres': ['News'],
+        },
+    }, {
+        'url': 'https://www.cbc.ca/player/play/video/9.6427282',
+        'info_dict': {
+            'id': '9.6427282',
+            'ext': 'mp4',
+            'title': 'Men\'s Soccer - Argentina vs Morocco',
+            'description': 'Argentina faces Morocco on the football pitch at Saint Etienne Stadium.',
+            'series': 'CBC Sports',
+            'media_type': 'Event Coverage',
+            'thumbnail': 'https://i.cbc.ca/ais/a4c5c0c2-99fa-4bd3-8061-5a63879c1b33,1718828053500/full/max/0/default.jpg',
+            'timestamp': 1721825400.0,
+            'upload_date': '20240724',
+            'duration': 10568.0,
+            'chapters': [],
+            'genres': [],
+            'tags': ['2024 Paris Olympic Games'],
+            'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'],
+            'location': 'Canada',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.cbc.ca/player/play/video/9.6459530',
+        'md5': '6c1bb76693ab321a2e99c347a1d5ecbc',
+        'info_dict': {
+            'id': '9.6459530',
+            'ext': 'mp4',
+            'title': 'Parts of Jasper incinerated as wildfire rages',
+            'description': 'md5:6f1caa8d128ad3f629257ef5fecf0962',
+            'series': 'The National',
+            'media_type': 'Excerpt',
+            'thumbnail': 'https://i.cbc.ca/ais/507c0086-31a2-494d-96e4-bffb1048d045,1721953984375/full/max/0/default.jpg',
+            'timestamp': 1721964091.012,
+            'upload_date': '20240726',
+            'duration': 952.285,
+            'chapters': [],
+            'genres': [],
+            'tags': 'count:23',
+            'categories': ['News (FAST)', 'News', 'The National', 'TV News Shows', 'The National '],
+        },
+    }, {
+        'url': 'https://www.cbc.ca/player/play/video/9.6420651',
+        'md5': '71a850c2c6ee5e912de169f5311bb533',
+        'info_dict': {
+            'id': '9.6420651',
+            'ext': 'mp4',
+            'title': 'Is it a breath of fresh air? Measuring air quality in Edmonton',
+            'description': 'md5:3922b92cc8b69212d739bd9dd095b1c3',
+            'series': 'CBC News Edmonton',
+            'media_type': 'Excerpt',
+            'thumbnail': 'https://i.cbc.ca/ais/73c4ab9c-7ad4-46ee-bb9b-020fdc01c745,1718214547576/full/max/0/default.jpg',
+            'timestamp': 1718220065.768,
+            'upload_date': '20240612',
+            'duration': 286.086,
+            'chapters': [],
+            'genres': ['News'],
+            'categories': ['News', 'Edmonton'],
+            'tags': 'count:7',
+            'location': 'Edmonton',
         },
     }, {
         'url': 'cbcplayer:1.7159484',
@@ -307,23 +376,113 @@ class CBCPlayerIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _parse_param(self, asset_data, name):
+        return traverse_obj(asset_data, ('params', lambda _, v: v['name'] == name, 'value', {str}, any))
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        if '.' in video_id:
+        webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
-            webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
+        data = self._search_json(
-            video_id = self._search_json(
+            r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip']
-                r'window\.__INITIAL_STATE__\s*=', webpage,
+        assets = traverse_obj(
-                'initial state', video_id)['video']['currentClip']['mediaId']
+            data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type']))
+
+        if not assets and (media_id := traverse_obj(data, ('mediaId', {str}))):
+            # XXX: Deprecated; CBC is migrating off of ThePlatform
+            return {
+                '_type': 'url_transparent',
+                'ie_key': 'ThePlatform',
+                'url': smuggle_url(
+                    f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{media_id}?mbr=true&formats=MPEG4,FLV,MP3', {
+                        'force_smil_url': True,
+                    }),
+                'id': media_id,
+                '_format_sort_fields': ('res', 'proto'),  # Prioritize direct http formats over HLS
+            }
+
+        is_live = traverse_obj(data, ('media', 'streamType', {str})) == 'Live'
+        formats, subtitles = [], {}
+
+        for sub in traverse_obj(data, ('media', 'textTracks', lambda _, v: url_or_none(v['src']))):
+            subtitles.setdefault(sub.get('language') or 'und', []).append({
+                'url': sub['src'],
+                'name': sub.get('label'),
+            })
+
+        for asset in assets:
+            asset_key = asset['key']
+            asset_type = asset['type']
+            if asset_type != 'medianet':
+                self.report_warning(f'Skipping unsupported asset type "{asset_type}": {asset_key}')
+                continue
+            asset_data = self._download_json(asset_key, video_id, f'Downloading {asset_type} JSON')
+            ext = mimetype2ext(self._parse_param(asset_data, 'contentType'))
+            if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    asset_data['url'], video_id, 'mp4', m3u8_id='hls', live=is_live)
+                formats.extend(fmts)
+                # Avoid slow/error-prone webvtt-over-m3u8 if direct https vtt is available
+                if not subtitles:
+                    self._merge_subtitles(subs, target=subtitles)
+                if is_live or not fmts:
+                    continue
+                # Check for direct https mp4 format
+                best_video_fmt = traverse_obj(fmts, (
+                    lambda _, v: v.get('vcodec') != 'none' and v['tbr'], all,
+                    {functools.partial(sorted, key=lambda x: x['tbr'])}, -1, {dict})) or {}
+                base_url = self._search_regex(
+                    r'(https?://[^?#]+?/)hdntl=', best_video_fmt.get('url'), 'base url', default=None)
+                if not base_url or '/live/' in base_url:
+                    continue
+                mp4_url = base_url + replace_extension(url_basename(best_video_fmt['url']), 'mp4')
+                if self._request_webpage(
+                        HEADRequest(mp4_url), video_id, 'Checking for https format',
+                        errnote=False, fatal=False):
+                    formats.append({
+                        **best_video_fmt,
+                        'url': mp4_url,
+                        'format_id': 'https-mp4',
+                        'protocol': 'https',
+                        'manifest_url': None,
+                        'acodec': None,
+                    })
+            else:
+                formats.append({
+                    'url': asset_data['url'],
+                    'ext': ext,
+                    'vcodec': 'none' if self._parse_param(asset_data, 'mediaType') == 'audio' else None,
+                })
+
+        chapters = traverse_obj(data, (
+            'media', 'chapters', lambda _, v: float(v['startTime']) is not None, {
+                'start_time': ('startTime', {functools.partial(float_or_none, scale=1000)}),
+                'end_time': ('endTime', {functools.partial(float_or_none, scale=1000)}),
+                'title': ('name', {str}),
+            }))
+        # Filter out pointless single chapters with start_time==0 and no end_time
+        if len(chapters) == 1 and not (chapters[0].get('start_time') or chapters[0].get('end_time')):
+            chapters = []
 
         return {
-            '_type': 'url_transparent',
+            **traverse_obj(data, {
-            'ie_key': 'ThePlatform',
+                'title': ('title', {str}),
-            'url': smuggle_url(
+                'description': ('description', {str.strip}),
-                f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{video_id}?mbr=true&formats=MPEG4,FLV,MP3', {
+                'thumbnail': ('image', 'url', {url_or_none}, {functools.partial(update_url, query=None)}),
-                    'force_smil_url': True,
+                'timestamp': ('publishedAt', {functools.partial(float_or_none, scale=1000)}),
-                }),
+                'media_type': ('media', 'clipType', {str}),
+                'series': ('showName', {str}),
+                'season_number': ('media', 'season', {int_or_none}),
+                'duration': ('media', 'duration', {float_or_none}, {lambda x: None if is_live else x}),
+                'location': ('media', 'region', {str}),
+                'tags': ('tags', ..., 'name', {str}),
+                'genres': ('media', 'genre', all),
+                'categories': ('categories', ..., 'name', {str}),
+            }),
             'id': video_id,
-            '_format_sort_fields': ('res', 'proto'),  # Prioritize direct http formats over HLS
+            'formats': formats,
+            'subtitles': subtitles,
+            'chapters': chapters,
+            'is_live': is_live,
         }
 
 
@@ -647,11 +806,11 @@ class CBCGemLiveIE(InfoExtractor):
                 'title': 'Ottawa',
                 'description': 'The live TV channel and local programming from Ottawa',
                 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
-                'is_live': True,
+                'live_status': 'is_live',
                 'id': 'AyqZwxRqh8EH',
                 'ext': 'mp4',
-                'timestamp': 1492106160,
+                'release_timestamp': 1492106160,
-                'upload_date': '20170413',
+                'release_date': '20170413',
                 'uploader': 'CBCC-NEW',
             },
             'skip': 'Live might have ended',
@@ -680,49 +839,84 @@ class CBCGemLiveIE(InfoExtractor):
                 'description': 'March 24, 2023 | President Biden’s Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.',
                 'live_status': 'is_live',
                 'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*',
-                'timestamp': 1679706000,
+                'release_timestamp': 1679706000,
-                'upload_date': '20230325',
+                'release_date': '20230325',
             },
             'params': {'skip_download': True},
             'skip': 'Live might have ended',
         },
+        {   # event replay (medianetlive)
+            'url': 'https://gem.cbc.ca/live-event/42314',
+            'md5': '297a9600f554f2258aed01514226a697',
+            'info_dict': {
+                'id': '42314',
+                'ext': 'mp4',
+                'live_status': 'was_live',
+                'title': 'Women\'s Soccer - Canada vs New Zealand',
+                'description': 'md5:36200e5f1a70982277b5a6ecea86155d',
+                'thumbnail': r're:https://.+default\.jpg',
+                'release_timestamp': 1721917200,
+                'release_date': '20240725',
+            },
+            'params': {'skip_download': True},
+            'skip': 'Replay might no longer be available',
+        },
+        {   # event replay (medianetlive)
+            'url': 'https://gem.cbc.ca/live-event/43273',
+            'only_matching': True,
+        },
     ]
+    _GEO_COUNTRIES = ['CA']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']
 
-        # Two types of metadata JSON
+        # Three types of video_info JSON: info in root, freeTv stream/item, event replay
         if not video_info.get('formattedIdMedia'):
-            video_info = traverse_obj(
+            if traverse_obj(video_info, ('event', 'key')) == video_id:
-                video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}),
+                video_info = video_info['event']
-                get_all=False, default={})
+            else:
+                video_info = traverse_obj(video_info, (
+                    ('freeTv', ('streams', ...)), 'items',
+                    lambda _, v: v['key'].partition('-')[0] == video_id, any)) or {}
 
         video_stream_id = video_info.get('formattedIdMedia')
         if not video_stream_id:
-            raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
+            raise ExtractorError(
+                'Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
 
-        stream_data = self._download_json(
+        live_status = 'was_live' if video_info.get('isVodEnabled') else 'is_live'
-            'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
+        release_timestamp = traverse_obj(video_info, ('airDate', {parse_iso8601}))
-                'appCode': 'mpx',
+
-                'connectionType': 'hd',
+        if live_status == 'is_live' and release_timestamp and release_timestamp > time.time():
-                'deviceType': 'ipad',
+            formats = []
-                'idMedia': video_stream_id,
+            live_status = 'is_upcoming'
-                'multibitrate': 'true',
+            self.raise_no_formats('This livestream has not yet started', expected=True)
-                'output': 'json',
+        else:
-                'tech': 'hls',
+            stream_data = self._download_json(
-                'manifestType': 'desktop',
+                'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
-            })
+                    'appCode': 'medianetlive',
+                    'connectionType': 'hd',
+                    'deviceType': 'ipad',
+                    'idMedia': video_stream_id,
+                    'multibitrate': 'true',
+                    'output': 'json',
+                    'tech': 'hls',
+                    'manifestType': 'desktop',
+                })
+            formats = self._extract_m3u8_formats(
+                stream_data['url'], video_id, 'mp4', live=live_status == 'is_live')
 
         return {
             'id': video_id,
-            'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True),
+            'formats': formats,
-            'is_live': True,
+            'live_status': live_status,
+            'release_timestamp': release_timestamp,
             **traverse_obj(video_info, {
-                'title': 'title',
+                'title': ('title', {str}),
-                'description': 'description',
+                'description': ('description', {str}),
                 'thumbnail': ('images', 'card', 'url'),
-                'timestamp': ('airDate', {parse_iso8601}),
             }),
         }

yt_dlp/extractor/common.py

@@ -35,6 +35,7 @@ from ..networking import HEADRequest, Request
 from ..networking.exceptions import (
     HTTPError,
     IncompleteRead,
+    TransportError,
     network_exceptions,
 )
 from ..networking.impersonate import ImpersonateTarget
@@ -965,6 +966,9 @@ class InfoExtractor:
             return False
         content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal,
                                              encoding=encoding, data=data)
+        if content is False:
+            assert not fatal
+            return False
         return (content, urlh)
 
     @staticmethod
@@ -1039,7 +1043,15 @@ class InfoExtractor:
 
     def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True,
                               prefix=None, encoding=None, data=None):
-        webpage_bytes = urlh.read()
+        try:
+            webpage_bytes = urlh.read()
+        except TransportError as err:
+            errmsg = f'{video_id}: Error reading response: {err.msg}'
+            if fatal:
+                raise ExtractorError(errmsg, cause=err)
+            self.report_warning(errmsg)
+            return False
+
         if prefix is not None:
             webpage_bytes = prefix + webpage_bytes
         if self.get_param('dump_intermediate_pages', False):
@@ -1698,7 +1710,7 @@ class InfoExtractor:
                 rating = traverse_obj(e, ('aggregateRating', 'ratingValue'), expected_type=float_or_none)
                 if rating is not None:
                     info['average_rating'] = rating
-                if is_type(e, 'TVEpisode', 'Episode'):
+                if is_type(e, 'TVEpisode', 'Episode', 'PodcastEpisode'):
                     episode_name = unescapeHTML(e.get('name'))
                     info.update({
                         'episode': episode_name,
@@ -2065,7 +2077,7 @@ class InfoExtractor:
         has_drm = HlsFD._has_drm(m3u8_doc)
 
         def format_url(url):
-            return url if re.match(r'^https?://', url) else urllib.parse.urljoin(m3u8_url, url)
+            return url if re.match(r'https?://', url) else urllib.parse.urljoin(m3u8_url, url)
 
         if self.get_param('hls_split_discontinuity', False):
             def _extract_m3u8_playlist_indices(manifest_url=None, m3u8_doc=None):
@@ -2800,11 +2812,11 @@ class InfoExtractor:
                         base_url_e = element.find(_add_ns('BaseURL'))
                         if try_call(lambda: base_url_e.text) is not None:
                             base_url = base_url_e.text + base_url
-                            if re.match(r'^https?://', base_url):
+                            if re.match(r'https?://', base_url):
                                 break
                     if mpd_base_url and base_url.startswith('/'):
                         base_url = urllib.parse.urljoin(mpd_base_url, base_url)
-                    elif mpd_base_url and not re.match(r'^https?://', base_url):
+                    elif mpd_base_url and not re.match(r'https?://', base_url):
                         if not mpd_base_url.endswith('/'):
                             mpd_base_url += '/'
                         base_url = mpd_base_url + base_url
@@ -2894,7 +2906,7 @@ class InfoExtractor:
                         }
 
                     def location_key(location):
-                        return 'url' if re.match(r'^https?://', location) else 'path'
+                        return 'url' if re.match(r'https?://', location) else 'path'
 
                     if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
 
@@ -3150,7 +3162,7 @@ class InfoExtractor:
                     })
         return formats, subtitles
 
-    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None):
+    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None, _headers=None):
         def absolute_url(item_url):
             return urljoin(base_url, item_url)
 
@@ -3174,11 +3186,11 @@ class InfoExtractor:
                 formats = self._extract_m3u8_formats(
                     full_url, video_id, ext='mp4',
                     entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
-                    preference=preference, quality=quality, fatal=False)
+                    preference=preference, quality=quality, fatal=False, headers=_headers)
             elif ext == 'mpd':
                 is_plain_url = False
                 formats = self._extract_mpd_formats(
-                    full_url, video_id, mpd_id=mpd_id, fatal=False)
+                    full_url, video_id, mpd_id=mpd_id, fatal=False, headers=_headers)
             else:
                 is_plain_url = True
                 formats = [{
@@ -3272,6 +3284,8 @@ class InfoExtractor:
                         })
             for f in media_info['formats']:
                 f.setdefault('http_headers', {})['Referer'] = base_url
+                if _headers:
+                    f['http_headers'].update(_headers)
             if media_info['formats'] or media_info['subtitles']:
                 entries.append(media_info)
         return entries
@@ -3487,7 +3501,7 @@ class InfoExtractor:
                 continue
             urls.add(source_url)
             source_type = source.get('type') or ''
-            ext = mimetype2ext(source_type) or determine_ext(source_url)
+            ext = determine_ext(source_url, default_ext=mimetype2ext(source_type))
             if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
                 formats.extend(self._extract_m3u8_formats(
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',

yt_dlp/extractor/dplay.py

@@ -319,32 +319,6 @@ class DPlayIE(DPlayBaseIE):
             url, display_id, host, 'dplay' + country, country, domain)
 
 
-class HGTVDeIE(DPlayBaseIE):
-    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX
-    _TESTS = [{
-        'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
-        'info_dict': {
-            'id': '151205',
-            'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
-            'ext': 'mp4',
-            'title': 'Wer braucht schon eine Toilette',
-            'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
-            'duration': 1177.024,
-            'timestamp': 1595705400,
-            'upload_date': '20200725',
-            'creator': 'HGTV',
-            'series': 'Tiny House - klein, aber oho',
-            'season_number': 3,
-            'episode_number': 3,
-        },
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        return self._get_disco_api_info(
-            url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')
-
-
 class DiscoveryPlusBaseIE(DPlayBaseIE):
     """Subclasses must set _PRODUCT, _DISCO_API_PARAMS"""
 
@@ -373,6 +347,45 @@ class DiscoveryPlusBaseIE(DPlayBaseIE):
         return self._get_disco_api_info(url, self._match_id(url), **self._DISCO_API_PARAMS)
 
 
+class HGTVDeIE(DiscoveryPlusBaseIE):
+    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://de.hgtv.com/sendungen/mein-kleinstadt-traumhaus/vom-landleben-ins-loft',
+        'info_dict': {
+            'id': '7332936',
+            'ext': 'mp4',
+            'display_id': 'mein-kleinstadt-traumhaus/vom-landleben-ins-loft',
+            'title': 'Vom Landleben ins Loft',
+            'description': 'md5:e5f72c02c853970796dd3818f2e25745',
+            'episode': 'Episode 7',
+            'episode_number': 7,
+            'season': 'Season 7',
+            'season_number': 7,
+            'series': 'Mein Kleinstadt-Traumhaus',
+            'duration': 2645.0,
+            'timestamp': 1725998100,
+            'upload_date': '20240910',
+            'creators': ['HGTV'],
+            'tags': [],
+            'thumbnail': 'https://eu1-prod-images.disco-api.com/2024/08/09/82a386b9-c688-32c7-b9ff-0b13865f0bae.jpeg',
+        },
+    }]
+
+    _PRODUCT = 'hgtv'
+    _DISCO_API_PARAMS = {
+        'disco_host': 'eu1-prod.disco-api.com',
+        'realm': 'hgtv',
+        'country': 'de',
+    }
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers.update({
+            'x-disco-params': f'realm={realm}',
+            'x-disco-client': 'Alps:HyogaPlayer:0.0.0',
+            'Authorization': self._get_auth(disco_base, display_id, realm),
+        })
+
+
 class GoDiscoveryIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
@@ -934,7 +947,7 @@ class TLCIE(DiscoveryPlusBaseIE):
 
 
 class DiscoveryPlusIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport)?' + DPlayBaseIE._PATH_REGEX
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
         'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
         'info_dict': {
@@ -958,6 +971,9 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE):
     }, {
         'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review',
         'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/gb/video/olympics/dplus-sport-dplus-sport-sport/rugby-sevens-australia-samoa',
+        'only_matching': True,
     }]
 
     _PRODUCT = None
@@ -1144,13 +1160,19 @@ class DiscoveryPlusShowBaseIE(DPlayBaseIE):
 
 
 class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video' + DPlayBaseIE._PATH_REGEX
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
         'url': 'https://www.discoveryplus.com/it/video/i-signori-della-neve/stagione-2-episodio-1-i-preparativi',
         'only_matching': True,
     }, {
         'url': 'https://www.discoveryplus.com/it/video/super-benny/trailer',
         'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/it/video/olympics/dplus-sport-dplus-sport-sport/water-polo-greece-italy',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/it/video/sport/dplus-sport-dplus-sport-sport/lisa-vittozzi-allinferno-e-ritorno',
+        'only_matching': True,
     }]
 
     _PRODUCT = 'dplus_it'

yt_dlp/extractor/dropbox.py

@@ -6,8 +6,10 @@ import urllib.parse
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    update_url,
     update_url_query,
     url_basename,
+    urlencode_postdata,
 )
 
 
@@ -36,43 +38,58 @@ class DropboxIE(InfoExtractor):
         },
     ]
 
+    def _yield_decoded_parts(self, webpage):
+        for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)):
+            yield base64.b64decode(encoded).decode('utf-8', 'ignore')
+
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         fn = urllib.parse.unquote(url_basename(url))
         title = os.path.splitext(fn)[0]
-
         password = self.get_param('videopassword')
-        if (self._og_search_title(webpage) == 'Dropbox - Password Required'
-                or 'Enter the password for this link' in webpage):
 
+        for part in self._yield_decoded_parts(webpage):
+            if '/sm/password' in part:
+                webpage = self._download_webpage(
+                    update_url('https://www.dropbox.com/sm/password', query=part.partition('?')[2]), video_id)
+                break
+
+        if (self._og_search_title(webpage, default=None) == 'Dropbox - Password Required'
+                or 'Enter the password for this link' in webpage):
             if password:
-                content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id')
-                payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}'
                 response = self._download_json(
-                    'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode(),
+                    'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password',
-                    headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+                    headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'},
+                    data=urlencode_postdata({
+                        'is_xhr': 'true',
+                        't': self._get_cookies('https://www.dropbox.com')['t'].value,
+                        'content_id': self._search_regex(r'content_id=([\w.+=/-]+)["\']', webpage, 'content id'),
+                        'password': password,
+                        'url': url,
+                    }))
 
                 if response.get('status') != 'authed':
-                    raise ExtractorError('Authentication failed!', expected=True)
+                    raise ExtractorError('Invalid password', expected=True)
-                webpage = self._download_webpage(url, video_id)
+            elif not self._get_cookies('https://dropbox.com').get('sm_auth'):
-            elif self._get_cookies('https://dropbox.com').get('sm_auth'):
-                webpage = self._download_webpage(url, video_id)
-            else:
                 raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
+            webpage = self._download_webpage(url, video_id)
 
-        formats, subtitles, has_anonymous_download = [], {}, False
+        formats, subtitles = [], {}
-        for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)):
+        has_anonymous_download = False
-            decoded = base64.b64decode(encoded).decode('utf-8', 'ignore')
+        thumbnail = None
+        for part in self._yield_decoded_parts(webpage):
             if not has_anonymous_download:
                 has_anonymous_download = self._search_regex(
-                    r'(anonymous:\tanonymous)', decoded, 'anonymous', default=False)
+                    r'(anonymous:\tanonymous)', part, 'anonymous', default=False)
             transcode_url = self._search_regex(
-                r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', decoded, 'transcode url', default=None)
+                r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', part, 'transcode url', default=None)
             if not transcode_url:
                 continue
             formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id, 'mp4')
+            thumbnail = self._search_regex(
+                r'(https://www\.dropbox\.com/temp_thumb_from_token/[\w/?&=]+)', part, 'thumbnail', default=None)
             break
 
         # downloads enabled we can get the original file
@@ -89,4 +106,5 @@ class DropboxIE(InfoExtractor):
             'title': title,
             'formats': formats,
             'subtitles': subtitles,
+            'thumbnail': thumbnail,
         }

yt_dlp/extractor/ertgr.py

@@ -17,6 +17,7 @@ from ..utils import (
     url_or_none,
     variadic,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ERTFlixBaseIE(InfoExtractor):
@@ -74,29 +75,28 @@ class ERTFlixCodenameIE(ERTFlixBaseIE):
 
     def _extract_formats_and_subs(self, video_id):
         media_info = self._call_api(video_id, codename=video_id)
-        formats, subs = [], {}
+        formats, subtitles = [], {}
-        for media_file in try_get(media_info, lambda x: x['MediaFiles'], list) or []:
+        for media in traverse_obj(media_info, (
-            for media in try_get(media_file, lambda x: x['Formats'], list) or []:
+                'MediaFiles', lambda _, v: v['RoleCodename'] == 'main',
-                fmt_url = url_or_none(try_get(media, lambda x: x['Url']))
+                'Formats', lambda _, v: url_or_none(v['Url']))):
-                if not fmt_url:
+            fmt_url = media['Url']
-                    continue
+            ext = determine_ext(fmt_url)
-                ext = determine_ext(fmt_url)
+            if ext == 'm3u8':
-                if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                    formats_, subs_ = self._extract_m3u8_formats_and_subtitles(
+                    fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False)
-                        fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False)
+            elif ext == 'mpd':
-                elif ext == 'mpd':
+                fmts, subs = self._extract_mpd_formats_and_subtitles(
-                    formats_, subs_ = self._extract_mpd_formats_and_subtitles(
+                    fmt_url, video_id, mpd_id='dash', fatal=False)
-                        fmt_url, video_id, mpd_id='dash', fatal=False)
+            else:
-                else:
+                formats.append({
-                    formats.append({
+                    'url': fmt_url,
-                        'url': fmt_url,
+                    'format_id': str_or_none(media.get('Id')),
-                        'format_id': str_or_none(media.get('Id')),
+                })
-                    })
+                continue
-                    continue
+            formats.extend(fmts)
-                formats.extend(formats_)
+            self._merge_subtitles(subs, target=subtitles)
-                self._merge_subtitles(subs_, target=subs)
 
-        return formats, subs
+        return formats, subtitles
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

yt_dlp/extractor/espn.py

@@ -294,37 +294,37 @@ class ESPNCricInfoIE(InfoExtractor):
 class WatchESPNIE(AdobePassIE):
     _VALID_URL = r'https?://(?:www\.)?espn\.com/(?:watch|espnplus)/player/_/id/(?P<id>[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})'
     _TESTS = [{
-        'url': 'https://www.espn.com/watch/player/_/id/dbbc6b1d-c084-4b47-9878-5f13c56ce309',
+        'url': 'https://www.espn.com/watch/player/_/id/11ce417a-6ac9-42b6-8a15-46aeb9ad5710',
         'info_dict': {
-            'id': 'dbbc6b1d-c084-4b47-9878-5f13c56ce309',
+            'id': '11ce417a-6ac9-42b6-8a15-46aeb9ad5710',
             'ext': 'mp4',
-            'title': 'Huddersfield vs. Burnley',
+            'title': 'Abilene Chrstn vs. Texas Tech',
-            'duration': 7500,
+            'duration': 14166,
-            'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/dbbc6b1d-c084-4b47-9878-5f13c56ce309/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs',
+            'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/11ce417a-6ac9-42b6-8a15-46aeb9ad5710/16x9.jpg?timestamp=202407252343&showBadge=true&cb=12&package=ESPN_PLUS',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'https://www.espn.com/watch/player/_/id/a049a56e-a7ce-477e-aef3-c7e48ef8221c',
+        'url': 'https://www.espn.com/watch/player/_/id/90a2c85d-75e0-4b1e-a878-8e428a3cb2f3',
         'info_dict': {
-            'id': 'a049a56e-a7ce-477e-aef3-c7e48ef8221c',
+            'id': '90a2c85d-75e0-4b1e-a878-8e428a3cb2f3',
             'ext': 'mp4',
-            'title': 'Dynamo Dresden vs. VfB Stuttgart (Round #1) (German Cup)',
+            'title': 'UC Davis vs. California',
-            'duration': 8335,
+            'duration': 9547,
-            'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/bd1f3d12-0654-47d9-852e-71b85ea695c7/16x9.jpg?timestamp=202201112217&showBadge=true&cb=12&package=ESPN_PLUS',
+            'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/90a2c85d-75e0-4b1e-a878-8e428a3cb2f3/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'https://www.espn.com/espnplus/player/_/id/317f5fd1-c78a-4ebe-824a-129e0d348421',
+        'url': 'https://www.espn.com/watch/player/_/id/c4313bbe-95b5-4bb8-b251-ac143ea0fc54',
         'info_dict': {
-            'id': '317f5fd1-c78a-4ebe-824a-129e0d348421',
+            'id': 'c4313bbe-95b5-4bb8-b251-ac143ea0fc54',
             'ext': 'mp4',
-            'title': 'The Wheel - Episode 10',
+            'title': 'The College Football Show',
-            'duration': 3352,
+            'duration': 3639,
-            'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/317f5fd1-c78a-4ebe-824a-129e0d348421/16x9.jpg?timestamp=202205031523&showBadge=true&cb=12&package=ESPN_PLUS',
+            'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/c4313bbe-95b5-4bb8-b251-ac143ea0fc54/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs',
         },
         'params': {
             'skip_download': True,
@@ -353,6 +353,13 @@ class WatchESPNIE(AdobePassIE):
             if not cookie:
                 self.raise_login_required(method='cookies')
 
+            jwt = self._search_regex(r'=([^|]+)\|', cookie.value, 'cookie jwt')
+            id_token = self._download_json(
+                'https://registerdisney.go.com/jgc/v6/client/ESPN-ONESITE.WEB-PROD/guest/refresh-auth',
+                None, 'Refreshing token', headers={'Content-Type': 'application/json'}, data=json.dumps({
+                    'refreshToken': json.loads(base64.urlsafe_b64decode(f'{jwt}==='))['refresh_token'],
+                }).encode())['data']['token']['id_token']
+
             assertion = self._call_bamgrid_api(
                 'devices', video_id,
                 headers={'Content-Type': 'application/json; charset=UTF-8'},
@@ -371,7 +378,7 @@ class WatchESPNIE(AdobePassIE):
                 })['access_token']
 
             assertion = self._call_bamgrid_api(
-                'accounts/grant', video_id, payload={'id_token': cookie.value.split('|')[1]},
+                'accounts/grant', video_id, payload={'id_token': id_token},
                 headers={
                     'Authorization': token,
                     'Content-Type': 'application/json; charset=UTF-8',

yt_dlp/extractor/eurosport.py

@@ -3,7 +3,12 @@ from ..utils import traverse_obj
 
 
 class EurosportIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.eurosport\.com/\w+/(?:[\w-]+/[\d-]+/)?[\w-]+_(?P<id>vid\d+)'
+    _VALID_URL = r'''(?x)
+        https?://(?:
+            (?:(?:www|espanol)\.)?eurosport\.(?:com(?:\.tr)?|de|dk|es|fr|hu|it|nl|no|ro)|
+            eurosport\.tvn24\.pl
+        )/[\w-]+/(?:[\w-]+/[\d-]+/)?[\w.-]+_(?P<id>vid\d+)
+    '''
     _TESTS = [{
         'url': 'https://www.eurosport.com/tennis/roland-garros/2022/highlights-rafael-nadal-brushes-aside-caper-ruud-to-win-record-extending-14th-french-open-title_vid1694147/video.shtml',
         'info_dict': {
@@ -70,6 +75,42 @@ class EurosportIE(InfoExtractor):
             'duration': 105.0,
             'upload_date': '20230518',
         },
+    }, {
+        'url': 'https://www.eurosport.de/radsport/vuelta-a-espana/2024/vuelta-a-espana-2024-wout-van-aert-und-co.-verzweifeln-an-mcnulty-zeitfahr-krimi-in-lissabon_vid2219478/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.dk/speedway/mikkel-michelsen-misser-finalen-i-cardiff-se-danskeren-i-semifinalen-her_vid2219363/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.nl/mixed-martial-arts/ufc/2022/ufc-305-respect-tussen-adesanya-en-du-plessis_vid2219650/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.es/ciclismo/la-vuelta-2024-carlos-rodriguez-olvida-la-crono-y-ya-espera-que-llegue-la-montana-no-me-encontre-nada-comodo_vid2219682/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.fr/football/supercoupe-d-europe/2024-2025/kylian-mbappe-vinicius-junior-eduardo-camavinga-touche.-extraits-de-l-entrainement-du-real-madrid-en-video_vid2216993/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.it/calcio/serie-a/2024-2025/samardzic-a-bergamo-per-le-visite-mediche-con-l-atalanta_vid2219680/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.hu/kerekpar/vuelta-a-espana/2024/dramai-harc-a-masodpercekert-meglepetesgyoztes-a-vuelta-nyitoszakaszan_vid2219481/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.no/golf/fedex-st-jude-championship/2024/ligger-pa-andreplass-sa-skjer-dette-drama_vid30000618/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.no/golf/fedex-st-jude-championship/2024/ligger-pa-andreplass-sa-skjer-dette-drama_vid2219531/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.ro/tenis/western-southern-open-2/2024/rezumatul-partidei-dintre-zverev-si-shelton-de-la-cincinnati_vid2219657/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.com.tr/hentbol/olympic-games-paris-2024/2024/paris-2024-denmark-ile-germany-olimpiyatlarin-onemli-anlari_vid2215836/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://eurosport.tvn24.pl/kolarstwo/tour-de-france-kobiet/2024/kasia-niewiadoma-przed-ostatnim-8.-etapem-tour-de-france-kobiet_vid2219765/video.shtml',
+        'only_matching': True,
     }]
 
     _TOKEN = None
@@ -77,6 +118,7 @@ class EurosportIE(InfoExtractor):
     # actually defined in https://netsport.eurosport.io/?variables={"databaseId":<databaseId>,"playoutType":"VDP"}&extensions={"persistedQuery":{"version":1 ..
     # but this method require to get sha256 hash
     _GEO_COUNTRIES = ['DE', 'NL', 'EU', 'IT', 'FR']  # Not complete list but it should work
+    _GEO_BYPASS = False
 
     def _real_initialize(self):
         if EurosportIE._TOKEN is None:
@@ -98,13 +140,13 @@ class EurosportIE(InfoExtractor):
         for stream_type in json_data['attributes']['streaming']:
             if stream_type == 'hls':
                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4')
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4', fatal=False)
             elif stream_type == 'dash':
                 fmts, subs = self._extract_mpd_formats_and_subtitles(
-                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id)
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, fatal=False)
             elif stream_type == 'mss':
                 fmts, subs = self._extract_ism_formats_and_subtitles(
-                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id)
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, fatal=False)
 
             formats.extend(fmts)
             self._merge_subtitles(subs, target=subtitles)

yt_dlp/extractor/facebook.py

@@ -84,7 +84,7 @@ class FacebookIE(InfoExtractor):
             'timestamp': 1692346159,
             'thumbnail': r're:^https?://.*',
             'uploader_id': '100063551323670',
-            'duration': 3132.184,
+            'duration': 3133.583,
             'view_count': int,
             'concurrent_view_count': 0,
         },
@@ -112,9 +112,10 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20140506',
             'timestamp': 1399398998,
             'thumbnail': r're:^https?://.*',
-            'uploader_id': 'pfbid028wxorhX2ErLFJ578N6P3crHD3PHmXTCqCvfBpsnbSLmbokwSY75p5hWBjHGkG4zxl',
+            'uploader_id': 'pfbid05AzrFTXgY37tqwaSgbFTTEpCLBjjEJHkigogwGiRPtKEpAsJYJpzE94H1RxYXWEtl',
             'duration': 131.03,
             'concurrent_view_count': int,
+            'view_count': int,
         },
     }, {
         'note': 'Video with DASH manifest',
@@ -167,7 +168,7 @@ class FacebookIE(InfoExtractor):
         # have 1080P, but only up to 720p in swf params
         # data.video.story.attachments[].media
         'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
-        'md5': 'ca63897a90c9452efee5f8c40d080e25',
+        'md5': '1659aa21fb3dd1585874f668e81a72c8',
         'info_dict': {
             'id': '10155529876156509',
             'ext': 'mp4',
@@ -180,9 +181,10 @@ class FacebookIE(InfoExtractor):
             'view_count': int,
             'uploader_id': '100059479812265',
             'concurrent_view_count': int,
-            'duration': 44.478,
+            'duration': 44.181,
         },
     }, {
+        # FIXME: unable to extract uploader, no formats found
         # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
         # data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media
         'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
@@ -241,9 +243,9 @@ class FacebookIE(InfoExtractor):
             'timestamp': 1511548260,
             'upload_date': '20171124',
             'uploader': 'Vickie Gentry',
-            'uploader_id': 'pfbid0FuZhHCeWDAxWxEbr3yKPFaRstXvRxgsp9uCPG6GjD4J2AitB35NUAuJ4Q75KcjiDl',
+            'uploader_id': 'pfbid0FkkycT95ySNNyfCw4Cho6u5G7WbbZEcxT496Hq8rtx1K3LcTCATpR3wnyYhmyGC5l',
             'thumbnail': r're:^https?://.*',
-            'duration': 148.435,
+            'duration': 148.224,
         },
     }, {
         # data.node.comet_sections.content.story.attachments[].styles.attachment.media
@@ -271,7 +273,7 @@ class FacebookIE(InfoExtractor):
             'description': 'Today Makkovik\'s own Pilot Mandy Smith made her inaugural landing on the airstrip in her hometown. What a proud moment as we all cheered and...',
             'thumbnail': r're:^https?://.*',
             'uploader': 'Lela Evans',
-            'uploader_id': 'pfbid0shZJipuigyy5mqrUJn9ub5LJFWNHvan5prtyi3LrDuuuJ4NwrURgnQHYR9fywBepl',
+            'uploader_id': 'pfbid0swT2y7t6TAsZVBvcyeYPdhTMefGaS26mzUwML3vd1ma6ndGZKxsyS4Ssu3jitZLXl',
             'upload_date': '20231228',
             'timestamp': 1703804085,
             'duration': 394.347,
@@ -322,7 +324,7 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20180523',
             'uploader': 'ESL One Dota 2',
             'uploader_id': '100066514874195',
-            'duration': 4524.212,
+            'duration': 4524.001,
             'view_count': int,
             'thumbnail': r're:^https?://.*',
             'concurrent_view_count': int,
@@ -339,9 +341,9 @@ class FacebookIE(InfoExtractor):
             'title': 'Josef',
             'thumbnail': r're:^https?://.*',
             'concurrent_view_count': int,
-            'uploader_id': 'pfbid0cibUN6tV7DYgdbJdsUFN46wc4jKpVSPAvJQhFofGqBGmVn3V3JtAs2tfUwziw2hUl',
+            'uploader_id': 'pfbid02gpfwRM2XvdEJfsERupwQiNmBiDArc38RMRYZnap372q6Vs7MtFTVy72mmFWpJBTKl',
             'timestamp': 1549275572,
-            'duration': 3.413,
+            'duration': 3.283,
             'uploader': 'Josef Novak',
             'description': '',
             'upload_date': '20190204',
@@ -396,6 +398,7 @@ class FacebookIE(InfoExtractor):
         'playlist_count': 1,
         'skip': 'Requires logging in',
     }, {
+        # FIXME: Cannot parse data error
         # data.event.cover_media_renderer.cover_video
         'url': 'https://m.facebook.com/events/1509582499515440',
         'info_dict': {
@@ -498,7 +501,8 @@ class FacebookIE(InfoExtractor):
                 or get_first(post, ('video', 'creation_story', 'attachments', ..., 'media', lambda k, v: k == 'owner' and v['name']))
                 or get_first(post, (..., 'video', lambda k, v: k == 'owner' and v['name']))
                 or get_first(post, ('node', 'actors', ..., {dict}))
-                or get_first(post, ('event', 'event_creator', {dict})) or {})
+                or get_first(post, ('event', 'event_creator', {dict}))
+                or get_first(post, ('video', 'creation_story', 'short_form_video_context', 'video_owner', {dict})) or {})
             uploader = uploader_data.get('name') or (
                 clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
                 or self._search_regex(
@@ -524,6 +528,11 @@ class FacebookIE(InfoExtractor):
                     webpage, 'view count', default=None)),
                 'concurrent_view_count': get_first(post, (
                     ('video', (..., ..., 'attachments', ..., 'media')), 'liveViewerCount', {int_or_none})),
+                **traverse_obj(post, (lambda _, v: video_id in v['url'], 'feedback', {
+                    'like_count': ('likers', 'count', {int}),
+                    'comment_count': ('total_comment_count', {int}),
+                    'repost_count': ('share_count_reduced', {parse_count}),
+                }), get_all=False),
             }
 
             info_json_ld = self._search_json_ld(webpage, video_id, default={})
@@ -571,16 +580,21 @@ class FacebookIE(InfoExtractor):
                 # Formats larger than ~500MB will return error 403 unless chunk size is regulated
                 f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20
 
-        def extract_relay_data(_filter):
+        def yield_all_relay_data(_filter):
-            return self._parse_json(self._search_regex(
+            for relay_data in re.findall(rf'data-sjs>({{.*?{_filter}.*?}})</script>', webpage):
-                rf'data-sjs>({{.*?{_filter}.*?}})</script>',
+                yield self._parse_json(relay_data, video_id, fatal=False) or {}
-                webpage, 'replay data', default='{}'), video_id, fatal=False) or {}
 
-        def extract_relay_prefetched_data(_filter):
+        def extract_relay_data(_filter):
-            return traverse_obj(extract_relay_data(_filter), (
+            return next(filter(None, yield_all_relay_data(_filter)), {})
-                'require', (None, (..., ..., ..., '__bbox', 'require')),
+
+        def extract_relay_prefetched_data(_filter, target_keys=None):
+            path = 'data'
+            if target_keys is not None:
+                path = lambda k, v: k == 'data' and any(target in v for target in variadic(target_keys))
+            return traverse_obj(yield_all_relay_data(_filter), (
+                ..., 'require', (None, (..., ..., ..., '__bbox', 'require')),
                 lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v),
-                ..., ..., '__bbox', 'result', 'data', {dict}), get_all=False) or {}
+                ..., ..., '__bbox', 'result', path, {dict}), get_all=False) or {}
 
         if not video_data:
             server_js_data = self._parse_json(self._search_regex([
@@ -591,7 +605,8 @@ class FacebookIE(InfoExtractor):
 
         if not video_data:
             data = extract_relay_prefetched_data(
-                r'"(?:dash_manifest|playable_url(?:_quality_hd)?)')
+                r'"(?:dash_manifest|playable_url(?:_quality_hd)?)',
+                target_keys=('video', 'event', 'nodes', 'node', 'mediaset'))
             if data:
                 entries = []
 
@@ -926,18 +941,21 @@ class FacebookReelIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'https://www.facebook.com/reel/1195289147628387',
-        'md5': 'f13dd37f2633595982db5ed8765474d3',
+        'md5': 'a53256d10fc2105441fe0c4212ed8cea',
         'info_dict': {
             'id': '1195289147628387',
             'ext': 'mp4',
-            'title': 'md5:b05800b5b1ad56c0ca78bd3807b6a61e',
+            'title': r're:9\.6K views · 355 reactions .+ Let the “Slapathon” commence!! .+ LL COOL J · Mama Said Knock You Out$',
-            'description': 'md5:22f03309b216ac84720183961441d8db',
+            'description': r're:When your trying to help your partner .+ LL COOL J · Mama Said Knock You Out$',
-            'uploader': 'md5:723e6cb3091241160f20b3c5dc282af1',
+            'uploader': 'Beast Camp Training',
             'uploader_id': '100040874179269',
             'duration': 9.579,
             'timestamp': 1637502609,
             'upload_date': '20211121',
             'thumbnail': r're:^https?://.*',
+            'like_count': int,
+            'comment_count': int,
+            'repost_count': int,
         },
     }]
 
@@ -957,6 +975,7 @@ class FacebookAdsIE(InfoExtractor):
             'id': '899206155126718',
             'ext': 'mp4',
             'title': 'video by Kandao',
+            'description': 'md5:0822724069e3aca97cbed5dabbab282e',
             'uploader': 'Kandao',
             'uploader_id': '774114102743284',
             'uploader_url': r're:^https?://.*',
@@ -965,6 +984,22 @@ class FacebookAdsIE(InfoExtractor):
             'upload_date': '20231214',
             'like_count': int,
         },
+    }, {
+        # key 'watermarked_video_sd_url' missing
+        'url': 'https://www.facebook.com/ads/library/?id=501152689226254',
+        'info_dict': {
+            'id': '501152689226254',
+            'ext': 'mp4',
+            'title': 'video by mat.nawrocki',
+            'description': 'md5:02a446ace7ff8c3c37a2892922492490',
+            'uploader': 'mat.nawrocki',
+            'uploader_id': '148586968341456',
+            'uploader_url': r're:^https?://.*',
+            'timestamp': 1723452305,
+            'thumbnail': r're:^https?://.*',
+            'upload_date': '20240812',
+            'like_count': int,
+        },
     }, {
         'url': 'https://www.facebook.com/ads/library/?id=893637265423481',
         'info_dict': {
@@ -1011,34 +1046,42 @@ class FacebookAdsIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        post_data = [self._parse_json(j, video_id, fatal=False)
+        post_data = traverse_obj(
-                     for j in re.findall(r's\.handle\(({.*})\);requireLazy\(', webpage)]
+            re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))
-        data = traverse_obj(post_data, (
+        data = get_first(post_data, (
-            ..., 'require', ..., ..., ..., 'props', 'deeplinkAdCard', 'snapshot', {dict}), get_all=False)
+            'require', ..., ..., ..., '__bbox', 'require', ..., ..., ...,
+            'entryPointRoot', 'otherProps', 'deeplinkAdCard', 'snapshot', {dict}))
         if not data:
             raise ExtractorError('Unable to extract ad data')
 
         title = data.get('title')
         if not title or title == '{{product.name}}':
             title = join_nonempty('display_format', 'page_name', delim=' by ', from_dict=data)
+        markup_id = traverse_obj(data, ('body', '__m', {str}))
+        markup = traverse_obj(post_data, (
+            ..., 'require', ..., ..., ..., '__bbox', 'markup', lambda _, v: v[0].startswith(markup_id),
+            ..., '__html', {clean_html}, {lambda x: not x.startswith('{{product.') and x}, any))
 
-        info_dict = traverse_obj(data, {
+        info_dict = merge_dicts({
-            'description': ('link_description', {str}, {lambda x: x if x != '{{product.description}}' else None}),
+            'title': title,
+            'description': markup or None,
+        }, traverse_obj(data, {
+            'description': ('link_description', {lambda x: x if not x.startswith('{{product.') else None}),
             'uploader': ('page_name', {str}),
             'uploader_id': ('page_id', {str_or_none}),
             'uploader_url': ('page_profile_uri', {url_or_none}),
             'timestamp': ('creation_time', {int_or_none}),
             'like_count': ('page_like_count', {int_or_none}),
-        })
+        }))
 
         entries = []
         for idx, entry in enumerate(traverse_obj(
-            data, (('videos', 'cards'), lambda _, v: any(url_or_none(v[f]) for f in self._FORMATS_MAP))), 1,
+            data, (('videos', 'cards'), lambda _, v: any(url_or_none(v.get(f)) for f in self._FORMATS_MAP))), 1,
         ):
             entries.append({
                 'id': f'{video_id}_{idx}',
                 'title': entry.get('title') or title,
-                'description': entry.get('link_description') or info_dict.get('description'),
+                'description': traverse_obj(entry, 'body', 'link_description') or info_dict.get('description'),
                 'thumbnail': url_or_none(entry.get('video_preview_image_url')),
                 'formats': self._extract_formats(entry),
             })

yt_dlp/extractor/fc2.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class FC2IE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
+    _VALID_URL = r'(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
     IE_NAME = 'fc2'
     _NETRC_MACHINE = 'fc2'
     _TESTS = [{

yt_dlp/extractor/generic.py

@@ -2340,7 +2340,7 @@ class GenericIE(InfoExtractor):
                 default_search = 'fixup_error'
 
             if default_search in ('auto', 'auto_warning', 'fixup_error'):
-                if re.match(r'^[^\s/]+\.[^\s/]+/', url):
+                if re.match(r'[^\s/]+\.[^\s/]+/', url):
                     self.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
                 elif default_search != 'fixup_error':
@@ -2400,7 +2400,7 @@ class GenericIE(InfoExtractor):
 
         # Check for direct link to a video
         content_type = full_response.headers.get('Content-Type', '').lower()
-        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
+        m = re.match(r'(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
         if m:
             self.report_detected('direct video link')
             headers = filter_dict({'Referer': smuggled_data.get('referer')})

yt_dlp/extractor/germanupa.py

@@ -0,0 +1,91 @@
+from .common import InfoExtractor
+from .vimeo import VimeoIE
+from ..utils import (
+    parse_qs,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class GermanupaIE(InfoExtractor):
+    IE_DESC = 'germanupa.de'
+    _VALID_URL = r'https?://germanupa\.de/mediathek/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://germanupa.de/mediathek/4-figma-beratung-deine-sprechstunde-fuer-figma-fragen',
+        'info_dict': {
+            'id': '909179246',
+            'title': 'Tutorial: #4 Figma Beratung - Deine Sprechstunde für Figma-Fragen',
+            'ext': 'mp4',
+            'uploader': 'German UPA',
+            'uploader_id': 'germanupa',
+            'thumbnail': 'https://i.vimeocdn.com/video/1792564420-7415283ccef8bf8702dab8c6b7515555ceeb7a1c11371ffcc133b8e887dbf70e-d_1280',
+            'uploader_url': 'https://vimeo.com/germanupa',
+            'duration': 3987,
+        },
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'note': 'audio, uses GenericIE',
+        'url': 'https://germanupa.de/mediathek/live-vom-ux-festival-neuigkeiten-von-figma-jobmarkt-agenturszene-interview-zu-sustainable',
+        'info_dict': {
+            'id': '1867346676',
+            'title': 'Live vom UX Festival: Neuigkeiten von Figma, Jobmarkt, Agenturszene & Interview zu Sustainable UX',
+            'ext': 'opus',
+            'timestamp': 1720545088,
+            'upload_date': '20240709',
+            'duration': 3910.557,
+            'like_count': int,
+            'description': 'md5:db2aed5ff131e177a7b33901e9a8db05',
+            'uploader': 'German UPA',
+            'repost_count': int,
+            'genres': ['Science'],
+            'license': 'all-rights-reserved',
+            'uploader_url': 'https://soundcloud.com/user-80097677',
+            'uploader_id': '471579486',
+            'view_count': int,
+            'comment_count': int,
+            'thumbnail': 'https://i1.sndcdn.com/artworks-oCti2e9GhaZFWBqY-48ybGw-original.jpg',
+        },
+    }, {
+        'note': 'Nur für Mitglieder/Just for members',
+        'url': 'https://germanupa.de/mediathek/ux-festival-2024-usability-tests-und-ai',
+        'info_dict': {
+            'id': '986994430',
+            'title': 'UX Festival 2024 "Usability Tests und AI" von Lennart Weber',
+            'ext': 'mp4',
+            'release_date': '20240719',
+            'uploader_url': 'https://vimeo.com/germanupa',
+            'timestamp': 1721373980,
+            'license': 'by-sa',
+            'like_count': int,
+            'thumbnail': 'https://i.vimeocdn.com/video/1904187064-2a672630c30f9ad787bd390bff3f51d7506a3e8416763ba6dbf465732b165c5c-d_1280',
+            'duration': 2146,
+            'release_timestamp': 1721373980,
+            'uploader': 'German UPA',
+            'uploader_id': 'germanupa',
+            'upload_date': '20240719',
+            'comment_count': int,
+        },
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+        'skip': 'login required',
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        param_url = traverse_obj(
+            self._search_regex(
+                r'<iframe[^>]+data-src\s*?=\s*?([\'"])(?P<url>https://germanupa\.de/media/oembed\?url=(?:(?!\1).)+)\1',
+                webpage, 'embedded video', default=None, group='url'),
+            ({parse_qs}, 'url', 0, {url_or_none}))
+
+        if not param_url:
+            if self._search_regex(
+                    r'<div[^>]+class\s*?=\s*?([\'"])(?:(?!\1).)*login-wrapper(?:(?!\1).)*\1',
+                    webpage, 'login wrapper', default=None):
+                self.raise_login_required('This video is only available for members')
+            return self.url_result(url, 'Generic')  # Fall back to generic to extract audio
+
+        real_url = param_url.replace('https://vimeo.com/', 'https://player.vimeo.com/video/')
+        return self.url_result(VimeoIE._smuggle_referrer(real_url, url), VimeoIE, video_id)

yt_dlp/extractor/getcourseru.py

@@ -52,7 +52,7 @@ class GetCourseRuIE(InfoExtractor):
     _BASE_URL_RE = rf'https?://(?:(?!player02\.)[^.]+\.getcourse\.(?:ru|io)|{"|".join(map(re.escape, _DOMAINS))})'
     _VALID_URL = [
         rf'{_BASE_URL_RE}/(?!pl/|teach/)(?P<id>[^?#]+)',
-        rf'{_BASE_URL_RE}/(:?pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P<id>\d+)',
+        rf'{_BASE_URL_RE}/(?:pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P<id>\d+)',
     ]
     _TESTS = [{
         'url': 'http://academymel.online/3video_1',

yt_dlp/extractor/golem.py

@@ -7,7 +7,7 @@ from ..utils import (
 
 
 class GolemIE(InfoExtractor):
-    _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
+    _VALID_URL = r'https?://video\.golem\.de/.+?/(?P<id>.+?)/'
     _TEST = {
         'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
         'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',

yt_dlp/extractor/hrfensehen.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class HRFernsehenIE(InfoExtractor):
     IE_NAME = 'hrfernsehen'
-    _VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
+    _VALID_URL = r'https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
     _TESTS = [{
         'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
         'md5': '5c4e0ba94677c516a2f65a84110fc536',

yt_dlp/extractor/huya.py

@@ -8,15 +8,19 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    parse_duration,
     str_or_none,
     try_get,
     unescapeHTML,
+    unified_strdate,
     update_url_query,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class HuyaLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?P<id>[^/#?&]+)(?:\D|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P<id>[^/#?&]+)(?:\D|$)'
     IE_NAME = 'huya:live'
     IE_DESC = 'huya.com'
     TESTS = [{
@@ -24,6 +28,7 @@ class HuyaLiveIE(InfoExtractor):
         'info_dict': {
             'id': '572329',
             'title': str,
+            'ext': 'flv',
             'description': str,
             'is_live': True,
             'view_count': int,
@@ -131,3 +136,76 @@ class HuyaLiveIE(InfoExtractor):
         fm = base64.b64decode(params['fm']).decode().split('_', 1)[0]
         ss = hashlib.md5('|'.join([params['seqid'], params['ctype'], params['t']]))
         return fm, ss
+
+
+class HuyaVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?huya\.com/video/play/(?P<id>\d+)\.html'
+    IE_NAME = 'huya:video'
+    IE_DESC = '虎牙视频'
+
+    _TESTS = [{
+        'url': 'https://www.huya.com/video/play/1002412640.html',
+        'info_dict': {
+            'id': '1002412640',
+            'ext': 'mp4',
+            'title': '8月3日',
+            'thumbnail': r're:https?://.*\.jpg',
+            'duration': 14,
+            'uploader': '虎牙-ATS欧卡车队青木',
+            'uploader_id': '1564376151',
+            'upload_date': '20240803',
+            'view_count': int,
+            'comment_count': int,
+            'like_count': int,
+        },
+    },
+        {
+        'url': 'https://www.huya.com/video/play/556054543.html',
+        'info_dict': {
+            'id': '556054543',
+            'ext': 'mp4',
+            'title': '我不挑事 也不怕事',
+            'thumbnail': r're:https?://.*\.jpg',
+            'duration': 1864,
+            'uploader': '卡尔',
+            'uploader_id': '367138632',
+            'upload_date': '20210811',
+            'view_count': int,
+            'comment_count': int,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url: str):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'https://liveapi.huya.com/moment/getMomentContent', video_id,
+            query={'videoId': video_id})['data']['moment']['videoInfo']
+
+        formats = []
+        for definition in traverse_obj(video_data, ('definitions', lambda _, v: url_or_none(v['url']))):
+            formats.append({
+                'url': definition['url'],
+                **traverse_obj(definition, {
+                    'format_id': ('defName', {str}),
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                    'filesize': ('size', {int_or_none}),
+                }),
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            **traverse_obj(video_data, {
+                'title': ('videoTitle', {str}),
+                'thumbnail': ('videoCover', {url_or_none}),
+                'duration': ('videoDuration', {parse_duration}),
+                'uploader': ('nickName', {str}),
+                'uploader_id': ('uid', {str_or_none}),
+                'upload_date': ('videoUploadTime', {unified_strdate}),
+                'view_count': ('videoPlayNum', {int_or_none}),
+                'comment_count': ('videoCommentNum', {int_or_none}),
+                'like_count': ('favorCount', {int_or_none}),
+            }),
+        }

yt_dlp/extractor/iprima.py

@@ -25,9 +25,29 @@ class IPrimaIE(InfoExtractor):
             'id': 'p51388',
             'ext': 'mp4',
             'title': 'Partička (92)',
-            'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
+            'description': 'md5:57943f6a50d6188288c3a579d2fd5f01',
-            'upload_date': '20201103',
+            'episode': 'Partička (92)',
-            'timestamp': 1604437480,
+            'season': 'Partička',
+            'series': 'Prima Partička',
+            'episode_number': 92,
+            'thumbnail': 'https://d31b9s05ygj54s.cloudfront.net/prima-plus/image/video-ef6cf9de-c980-4443-92e4-17fe8bccd45c-16x9.jpeg',
+        },
+        'params': {
+            'skip_download': True,  # m3u8 download
+        },
+    }, {
+        'url': 'https://zoom.iprima.cz/porady/krasy-kanarskych-ostrovu/tenerife-v-risi-ohne',
+        'info_dict': {
+            'id': 'p1412199',
+            'ext': 'mp4',
+            'episode_number': 3,
+            'episode': 'Tenerife: V říši ohně',
+            'description': 'md5:4b4a05c574b5eaef130e68d4811c3f2c',
+            'duration': 3111.0,
+            'thumbnail': 'https://d31b9s05ygj54s.cloudfront.net/prima-plus/image/video-f66dd7fb-c1a0-47d1-b3bc-7db328d566c5-16x9-1711636518.jpg/t_16x9_medium_1366_768',
+            'title': 'Tenerife: V říši ohně',
+            'timestamp': 1711825800,
+            'upload_date': '20240330',
         },
         'params': {
             'skip_download': True,  # m3u8 download
@@ -131,6 +151,7 @@ class IPrimaIE(InfoExtractor):
         video_id = self._search_regex((
             r'productId\s*=\s*([\'"])(?P<id>p\d+)\1',
             r'pproduct_id\s*=\s*([\'"])(?P<id>p\d+)\1',
+            r'let\s+videos\s*=\s*([\'"])(?P<id>p\d+)\1',
         ), webpage, 'real id', group='id', default=None)
 
         if not video_id:
@@ -176,7 +197,7 @@ class IPrimaIE(InfoExtractor):
         final_result = self._search_json_ld(webpage, video_id, default={})
         final_result.update({
             'id': video_id,
-            'title': title,
+            'title': final_result.get('title') or title,
             'thumbnail': self._html_search_meta(
                 ['thumbnail', 'og:image', 'twitter:image'],
                 webpage, 'thumbnail', default=None),

yt_dlp/extractor/japandiet.py

@@ -194,11 +194,14 @@ class ShugiinItvVodIE(ShugiinItvBaseIE):
 
 
 class SangiinInstructionIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
+    _VALID_URL = r'https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
     IE_DESC = False  # this shouldn't be listed as a supported site
 
     def _real_extract(self, url):
-        raise ExtractorError('Copy the link from the botton below the video description or player, and use the link to download. If there are no button in the frame, get the URL of the frame showing the video.', expected=True)
+        raise ExtractorError(
+            'Copy the link from the button below the video description/player '
+            'and use that link to download. If there is no button in the frame, '
+            'get the URL of the frame showing the video.', expected=True)
 
 
 class SangiinIE(InfoExtractor):

yt_dlp/extractor/kaltura.py

@@ -22,7 +22,7 @@ class KalturaIE(InfoExtractor):
                 (?:
                     kaltura:(?P<partner_id>\w+):(?P<id>\w+)(?::(?P<player_type>\w+))?|
                     https?://
-                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
+                        (?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
                         (?:
                             (?:
                                 # flash player

yt_dlp/extractor/khanacademy.py

@@ -15,7 +15,7 @@ from ..utils import (
 class KhanAcademyBaseIE(InfoExtractor):
     _VALID_URL_TEMPL = r'https?://(?:www\.)?khanacademy\.org/(?P<id>(?:[^/]+/){%s}%s[^?#/&]+)'
 
-    _PUBLISHED_CONTENT_VERSION = '171419ab20465d931b356f22d20527f13969bb70'
+    _PUBLISHED_CONTENT_VERSION = 'dc34750f0572c80f5effe7134082fe351143c1e4'
 
     def _parse_video(self, video):
         return {
@@ -39,7 +39,7 @@ class KhanAcademyBaseIE(InfoExtractor):
             query={
                 'fastly_cacheable': 'persist_until_publish',
                 'pcv': self._PUBLISHED_CONTENT_VERSION,
-                'hash': '1242644265',
+                'hash': '3712657851',
                 'variables': json.dumps({
                     'path': display_id,
                     'countryCode': 'US',

yt_dlp/extractor/kick.py

@@ -1,9 +1,14 @@
+import functools
+
 from .common import InfoExtractor
 from ..networking import HEADRequest
 from ..utils import (
     UserNotLive,
+    determine_ext,
     float_or_none,
+    int_or_none,
     merge_dicts,
+    parse_iso8601,
     str_or_none,
     traverse_obj,
     unified_timestamp,
@@ -25,104 +30,212 @@ class KickBaseIE(InfoExtractor):
 
     def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
         return self._download_json(
-            f'https://kick.com/api/v1/{path}', display_id, note=note,
+            f'https://kick.com/api/{path}', display_id, note=note,
             headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
 
 
 class KickIE(KickBaseIE):
+    IE_NAME = 'kick:live'
     _VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w-]+)'
     _TESTS = [{
-        'url': 'https://kick.com/yuppy',
+        'url': 'https://kick.com/buddha',
         'info_dict': {
-            'id': '6cde1-kickrp-joe-flemmingskick-info-heremust-knowmust-see21',
+            'id': '92722911-nopixel-40',
             'ext': 'mp4',
             'title': str,
             'description': str,
-            'channel': 'yuppy',
-            'channel_id': '33538',
-            'uploader': 'Yuppy',
-            'uploader_id': '33793',
-            'upload_date': str,
-            'live_status': 'is_live',
             'timestamp': int,
-            'thumbnail': r're:^https?://.*\.jpg',
+            'thumbnail': r're:https?://.+\.jpg',
             'categories': list,
+            'upload_date': str,
+            'channel': 'buddha',
+            'channel_id': '32807',
+            'uploader': 'Buddha',
+            'uploader_id': '33057',
+            'live_status': 'is_live',
+            'concurrent_view_count': int,
+            'release_timestamp': int,
+            'age_limit': 18,
+            'release_date': str,
         },
-        'skip': 'livestream',
+        'params': {'skip_download': 'livestream'},
+        # 'skip': 'livestream',
     }, {
-        'url': 'https://kick.com/kmack710',
+        'url': 'https://kick.com/xqc',
         'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if (KickVODIE.suitable(url) or KickClipIE.suitable(url)) else super().suitable(url)
+
     def _real_extract(self, url):
         channel = self._match_id(url)
-        response = self._call_api(f'channels/{channel}', channel)
+        response = self._call_api(f'v2/channels/{channel}', channel)
         if not traverse_obj(response, 'livestream', expected_type=dict):
             raise UserNotLive(video_id=channel)
 
         return {
-            'id': str(traverse_obj(
-                response, ('livestream', ('slug', 'id')), get_all=False, default=channel)),
-            'formats': self._extract_m3u8_formats(
-                response['playback_url'], channel, 'mp4', live=True),
-            'title': traverse_obj(
-                response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
-            'description': traverse_obj(response, ('user', 'bio')),
             'channel': channel,
-            'channel_id': str_or_none(traverse_obj(response, 'id', ('livestream', 'channel_id'))),
-            'uploader': traverse_obj(response, 'name', ('user', 'username')),
-            'uploader_id': str_or_none(traverse_obj(response, 'user_id', ('user', 'id'))),
             'is_live': True,
-            'timestamp': unified_timestamp(traverse_obj(response, ('livestream', 'created_at'))),
+            'formats': self._extract_m3u8_formats(response['playback_url'], channel, 'mp4', live=True),
-            'thumbnail': traverse_obj(
+            **traverse_obj(response, {
-                response, ('livestream', 'thumbnail', 'url'), expected_type=url_or_none),
+                'id': ('livestream', 'slug', {str}),
-            'categories': traverse_obj(response, ('recent_categories', ..., 'name')),
+                'title': ('livestream', 'session_title', {str}),
+                'description': ('user', 'bio', {str}),
+                'channel_id': (('id', ('livestream', 'channel_id')), {int}, {str_or_none}, any),
+                'uploader': (('name', ('user', 'username')), {str}, any),
+                'uploader_id': (('user_id', ('user', 'id')), {int}, {str_or_none}, any),
+                'timestamp': ('livestream', 'created_at', {unified_timestamp}),
+                'release_timestamp': ('livestream', 'start_time', {unified_timestamp}),
+                'thumbnail': ('livestream', 'thumbnail', 'url', {url_or_none}),
+                'categories': ('recent_categories', ..., 'name', {str}),
+                'concurrent_view_count': ('livestream', 'viewer_count', {int_or_none}),
+                'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
+            }),
         }
 
 
 class KickVODIE(KickBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?kick\.com/video/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
+    IE_NAME = 'kick:vod'
+    _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/videos/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
     _TESTS = [{
-        'url': 'https://kick.com/video/58bac65b-e641-4476-a7ba-3707a35e60e3',
+        'url': 'https://kick.com/xqc/videos/8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
         'md5': '3870f94153e40e7121a6e46c068b70cb',
         'info_dict': {
-            'id': '58bac65b-e641-4476-a7ba-3707a35e60e3',
+            'id': '8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
             'ext': 'mp4',
-            'title': '🤠REBIRTH IS BACK!!!!🤠!stake CODE JAREDFPS 🤠',
+            'title': '18+ #ad 🛑LIVE🛑CLICK🛑DRAMA🛑NEWS🛑STUFF🛑REACT🛑GET IN HHERE🛑BOP BOP🛑WEEEE WOOOO🛑',
-            'description': 'md5:02b0c46f9b4197fb545ab09dddb85b1d',
+            'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.',
-            'channel': 'jaredfps',
+            'channel': 'xqc',
-            'channel_id': '26608',
+            'channel_id': '668',
-            'uploader': 'JaredFPS',
+            'uploader': 'xQc',
-            'uploader_id': '26799',
+            'uploader_id': '676',
-            'upload_date': '20240402',
+            'upload_date': '20240909',
-            'timestamp': 1712097108,
+            'timestamp': 1725919141,
-            'duration': 33859.0,
+            'duration': 10155.0,
             'thumbnail': r're:^https?://.*\.jpg',
-            'categories': ['Call of Duty: Warzone'],
+            'view_count': int,
+            'categories': ['Just Chatting'],
+            'age_limit': 0,
         },
-        'params': {
+        'params': {'skip_download': 'm3u8'},
-            'skip_download': 'm3u8',
-        },
-        'expected_warnings': [r'impersonation'],
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        response = self._call_api(f'video/{video_id}', video_id)
+        response = self._call_api(f'v1/video/{video_id}', video_id)
 
         return {
             'id': video_id,
             'formats': self._extract_m3u8_formats(response['source'], video_id, 'mp4'),
-            'title': traverse_obj(
+            **traverse_obj(response, {
-                response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
+                'title': ('livestream', ('session_title', 'slug'), {str}, any),
-            'description': traverse_obj(response, ('livestream', 'channel', 'user', 'bio')),
+                'description': ('livestream', 'channel', 'user', 'bio', {str}),
-            'channel': traverse_obj(response, ('livestream', 'channel', 'slug')),
+                'channel': ('livestream', 'channel', 'slug', {str}),
-            'channel_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'id'))),
+                'channel_id': ('livestream', 'channel', 'id', {int}, {str_or_none}),
-            'uploader': traverse_obj(response, ('livestream', 'channel', 'user', 'username')),
+                'uploader': ('livestream', 'channel', 'user', 'username', {str}),
-            'uploader_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'user_id'))),
+                'uploader_id': ('livestream', 'channel', 'user_id', {int}, {str_or_none}),
-            'timestamp': unified_timestamp(response.get('created_at')),
+                'timestamp': ('created_at', {parse_iso8601}),
-            'duration': float_or_none(traverse_obj(response, ('livestream', 'duration')), scale=1000),
+                'duration': ('livestream', 'duration', {functools.partial(float_or_none, scale=1000)}),
-            'thumbnail': traverse_obj(
+                'thumbnail': ('livestream', 'thumbnail', {url_or_none}),
-                response, ('livestream', 'thumbnail'), expected_type=url_or_none),
+                'categories': ('livestream', 'categories', ..., 'name', {str}),
-            'categories': traverse_obj(response, ('livestream', 'categories', ..., 'name')),
+                'view_count': ('views', {int_or_none}),
+                'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
+            }),
+        }
+
+
+class KickClipIE(KickBaseIE):
+    IE_NAME = 'kick:clips'
+    _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+(?:/clips/|/?\?(?:[^#]+&)?clip=)(?P<id>clip_[\w-]+)'
+    _TESTS = [{
+        'url': 'https://kick.com/mxddy?clip=clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
+        'info_dict': {
+            'id': 'clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
+            'ext': 'mp4',
+            'title': 'Maddy detains Abd D:',
+            'channel': 'mxddy',
+            'channel_id': '133789',
+            'uploader': 'AbdCreates',
+            'uploader_id': '3309077',
+            'thumbnail': r're:^https?://.*\.jpeg',
+            'duration': 35,
+            'timestamp': 1682481453,
+            'upload_date': '20230426',
+            'view_count': int,
+            'like_count': int,
+            'categories': ['VALORANT'],
+            'age_limit': 18,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://kick.com/destiny?clip=clip_01H9SKET879NE7N9RJRRDS98J3',
+        'info_dict': {
+            'id': 'clip_01H9SKET879NE7N9RJRRDS98J3',
+            'title': 'W jews',
+            'ext': 'mp4',
+            'channel': 'destiny',
+            'channel_id': '1772249',
+            'uploader': 'punished_furry',
+            'uploader_id': '2027722',
+            'duration': 49.0,
+            'upload_date': '20230908',
+            'timestamp': 1694150180,
+            'thumbnail': 'https://clips.kick.com/clips/j3/clip_01H9SKET879NE7N9RJRRDS98J3/thumbnail.png',
+            'view_count': int,
+            'like_count': int,
+            'categories': ['Just Chatting'],
+            'age_limit': 0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://kick.com/spreen/clips/clip_01J8RGZRKHXHXXKJEHGRM932A5',
+        'info_dict': {
+            'id': 'clip_01J8RGZRKHXHXXKJEHGRM932A5',
+            'ext': 'mp4',
+            'title': 'KLJASLDJKLJKASDLJKDAS',
+            'channel': 'spreen',
+            'channel_id': '5312671',
+            'uploader': 'AnormalBarraBaja',
+            'uploader_id': '26518262',
+            'duration': 43.0,
+            'upload_date': '20240927',
+            'timestamp': 1727399987,
+            'thumbnail': 'https://clips.kick.com/clips/f2/clip_01J8RGZRKHXHXXKJEHGRM932A5/thumbnail.webp',
+            'view_count': int,
+            'like_count': int,
+            'categories': ['Minecraft'],
+            'age_limit': 0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        clip_id = self._match_id(url)
+        clip = self._call_api(f'v2/clips/{clip_id}/play', clip_id)['clip']
+        clip_url = clip['clip_url']
+
+        if determine_ext(clip_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(clip_url, clip_id, 'mp4')
+        else:
+            formats = [{'url': clip_url}]
+
+        return {
+            'id': clip_id,
+            'formats': formats,
+            **traverse_obj(clip, {
+                'title': ('title', {str}),
+                'channel': ('channel', 'slug', {str}),
+                'channel_id': ('channel', 'id', {int}, {str_or_none}),
+                'uploader': ('creator', 'username', {str}),
+                'uploader_id': ('creator', 'id', {int}, {str_or_none}),
+                'thumbnail': ('thumbnail_url', {url_or_none}),
+                'duration': ('duration', {float_or_none}),
+                'categories': ('category', 'name', {str}, all),
+                'timestamp': ('created_at', {parse_iso8601}),
+                'view_count': ('views', {int_or_none}),
+                'like_count': ('likes', {int_or_none}),
+                'age_limit': ('is_mature', {bool}, {lambda x: 18 if x else 0}),
+            }),
         }

yt_dlp/extractor/kika.py

@@ -0,0 +1,126 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class KikaIE(InfoExtractor):
+    IE_DESC = 'KiKA.de'
+    _VALID_URL = r'https?://(?:www\.)?kika\.de/[\w/-]+/videos/(?P<id>[a-z-]+\d+)'
+    _GEO_COUNTRIES = ['DE']
+
+    _TESTS = [{
+        'url': 'https://www.kika.de/logo/videos/logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100',
+        'md5': 'fbfc8da483719ef06f396e5e5b938c69',
+        'info_dict': {
+            'id': 'logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100',
+            'ext': 'mp4',
+            'upload_date': '20240831',
+            'timestamp': 1725126600,
+            'season_number': 2024,
+            'modified_date': '20240831',
+            'episode': 'Episode 476',
+            'episode_number': 476,
+            'season': 'Season 2024',
+            'duration': 634,
+            'title': 'logo! vom Samstag, 31. August 2024',
+            'modified_timestamp': 1725129983,
+        },
+    }, {
+        'url': 'https://www.kika.de/kaltstart/videos/video92498',
+        'md5': '710ece827e5055094afeb474beacb7aa',
+        'info_dict': {
+            'id': 'video92498',
+            'ext': 'mp4',
+            'title': '7. Wo ist Leo?',
+            'description': 'md5:fb48396a5b75068bcac1df74f1524920',
+            'duration': 436,
+            'timestamp': 1702926876,
+            'upload_date': '20231218',
+            'episode_number': 7,
+            'modified_date': '20240319',
+            'modified_timestamp': 1710880610,
+            'episode': 'Episode 7',
+            'season_number': 1,
+            'season': 'Season 1',
+        },
+    }, {
+        'url': 'https://www.kika.de/bernd-das-brot/astrobrot/videos/video90088',
+        'md5': 'ffd1b700d7de0a6616a1d08544c77294',
+        'info_dict': {
+            'id': 'video90088',
+            'ext': 'mp4',
+            'upload_date': '20221102',
+            'timestamp': 1667390580,
+            'duration': 197,
+            'modified_timestamp': 1711093771,
+            'episode_number': 8,
+            'title': 'Es ist nicht leicht, ein Astrobrot zu sein',
+            'modified_date': '20240322',
+            'description': 'md5:d3641deaf1b5515a160788b2be4159a9',
+            'season_number': 1,
+            'episode': 'Episode 8',
+            'season': 'Season 1',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        doc = self._download_json(f'https://www.kika.de/_next-api/proxy/v1/videos/{video_id}', video_id)
+        video_assets = self._download_json(doc['assets']['url'], video_id)
+
+        subtitles = {}
+        if ttml_resource := url_or_none(video_assets.get('videoSubtitle')):
+            subtitles['de'] = [{
+                'url': ttml_resource,
+                'ext': 'ttml',
+            }]
+        if webvtt_resource := url_or_none(video_assets.get('webvttUrl')):
+            subtitles.setdefault('de', []).append({
+                'url': webvtt_resource,
+                'ext': 'vtt',
+            })
+
+        return {
+            'id': video_id,
+            'formats': list(self._extract_formats(video_assets, video_id)),
+            'subtitles': subtitles,
+            **traverse_obj(doc, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'timestamp': ('date', {parse_iso8601}),
+                'modified_timestamp': ('modificationDate', {parse_iso8601}),
+                'duration': ((
+                    ('durationInSeconds', {int_or_none}),
+                    ('duration', {parse_duration})), any),
+                'episode_number': ('episodeNumber', {int_or_none}),
+                'season_number': ('season', {int_or_none}),
+            }),
+        }
+
+    def _extract_formats(self, media_info, video_id):
+        for media in traverse_obj(media_info, ('assets', lambda _, v: url_or_none(v['url']))):
+            stream_url = media['url']
+            ext = determine_ext(stream_url)
+            if ext == 'm3u8':
+                yield from self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            else:
+                yield {
+                    'url': stream_url,
+                    'format_id': ext,
+                    **traverse_obj(media, {
+                        'width': ('frameWidth', {int_or_none}),
+                        'height': ('frameHeight', {int_or_none}),
+                        # NB: filesize is 0 if unknown, bitrate is -1 if unknown
+                        'filesize': ('fileSize', {int_or_none}, {lambda x: x or None}),
+                        'abr': ('bitrateAudio', {int_or_none}, {lambda x: None if x == -1 else x}),
+                        'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}),
+                    }),
+                }

yt_dlp/extractor/learningonscreen.py

@@ -0,0 +1,78 @@
+import functools
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_id,
+    join_nonempty,
+    parse_duration,
+    unified_timestamp,
+)
+from ..utils.traversal import traverse_obj
+
+
+class LearningOnScreenIE(InfoExtractor):
+    _VALID_URL = r'https?://learningonscreen\.ac\.uk/ondemand/index\.php/prog/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://learningonscreen.ac.uk/ondemand/index.php/prog/005D81B2?bcast=22757013',
+        'info_dict': {
+            'id': '005D81B2',
+            'ext': 'mp4',
+            'title': 'Planet Earth',
+            'duration': 3600.0,
+            'timestamp': 1164567600.0,
+            'upload_date': '20061126',
+            'thumbnail': 'https://stream.learningonscreen.ac.uk/trilt-cover-images/005D81B2-Planet-Earth-2006-11-26T190000Z-BBC4.jpg',
+        },
+    }]
+
+    def _real_initialize(self):
+        if not self._get_cookies('https://learningonscreen.ac.uk/').get('PHPSESSID-BOB-LIVE'):
+            self.raise_login_required(
+                'Use --cookies for authentication. See '
+                ' https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp  '
+                'for how to manually pass cookies', method=None)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        details = traverse_obj(webpage, (
+            {functools.partial(get_element_html_by_id, 'programme-details')}, {
+                'title': ({functools.partial(re.search, r'<h2>([^<]+)</h2>')}, 1, {clean_html}),
+                'timestamp': (
+                    {functools.partial(get_element_by_class, 'broadcast-date')},
+                    {functools.partial(re.match, r'([^<]+)')}, 1, {unified_timestamp}),
+                'duration': (
+                    {functools.partial(get_element_by_class, 'prog-running-time')},
+                    {clean_html}, {parse_duration}),
+            }))
+
+        title = details.pop('title', None) or traverse_obj(webpage, (
+            {functools.partial(get_element_html_by_id, 'add-to-existing-playlist')},
+            {extract_attributes}, 'data-record-title', {clean_html}))
+
+        entries = self._parse_html5_media_entries(
+            'https://stream.learningonscreen.ac.uk', webpage, video_id, m3u8_id='hls', mpd_id='dash',
+            _headers={'Origin': 'https://learningonscreen.ac.uk', 'Referer': 'https://learningonscreen.ac.uk/'})
+        if not entries:
+            raise ExtractorError('No video found')
+
+        if len(entries) > 1:
+            duration = details.pop('duration', None)
+            for idx, entry in enumerate(entries, start=1):
+                entry.update(details)
+                entry['id'] = join_nonempty(video_id, idx)
+                entry['title'] = join_nonempty(title, idx)
+            return self.playlist_result(entries, video_id, title, duration=duration)
+
+        return {
+            **entries[0],
+            **details,
+            'id': video_id,
+            'title': title,
+        }

yt_dlp/extractor/lnk.py

@@ -1,86 +1,11 @@
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     format_field,
     int_or_none,
-    parse_iso8601,
     unified_strdate,
 )
 
 
-class LnkGoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P<id>[A-Za-z0-9-]+)(?:/(?P<episode_id>\d+))?'
-    _TESTS = [{
-        'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai',
-        'info_dict': {
-            'id': '10809',
-            'ext': 'mp4',
-            'title': "Put'ka: Trys Klausimai",
-            'upload_date': '20161216',
-            'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.',
-            'age_limit': 18,
-            'duration': 117,
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1481904000,
-        },
-        'params': {
-            'skip_download': True,  # HLS download
-        },
-    }, {
-        'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
-        'info_dict': {
-            'id': '10467',
-            'ext': 'mp4',
-            'title': 'Nėrdas: Kompiuterio Valymas',
-            'upload_date': '20150113',
-            'description': 'md5:7352d113a242a808676ff17e69db6a69',
-            'age_limit': 18,
-            'duration': 346,
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1421164800,
-        },
-        'params': {
-            'skip_download': True,  # HLS download
-        },
-    }, {
-        'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413',
-        'only_matching': True,
-    }]
-    _AGE_LIMITS = {
-        'N-7': 7,
-        'N-14': 14,
-        'S': 18,
-    }
-    _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s'
-
-    def _real_extract(self, url):
-        display_id, video_id = self._match_valid_url(url).groups()
-
-        video_info = self._download_json(
-            'https://lnk.lt/api/main/video-page/{}/{}/false'.format(display_id, video_id or '0'),
-            display_id)['videoConfig']['videoInfo']
-
-        video_id = str(video_info['id'])
-        title = video_info['title']
-        prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4'
-        formats = self._extract_m3u8_formats(
-            self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''),
-            video_id, 'mp4', 'm3u8_native')
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'formats': formats,
-            'thumbnail': format_field(video_info, 'posterImage', 'https://lnk.lt/all-images/%s'),
-            'duration': int_or_none(video_info.get('duration')),
-            'description': clean_html(video_info.get('htmlDescription')),
-            'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0),
-            'timestamp': parse_iso8601(video_info.get('airDate')),
-            'view_count': int_or_none(video_info.get('viewsCount')),
-        }
-
-
 class LnkIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?lnk\.lt/[^/]+/(?P<id>\d+)'
 

yt_dlp/extractor/loom.py

@@ -92,9 +92,9 @@ class LoomIE(InfoExtractor):
         },
         'params': {'videopassword': 'seniorinfants2'},
     }, {
-        # embed, transcoded-url endpoint sends empty JSON response
+        # embed, transcoded-url endpoint sends empty JSON response, split video and audio HLS formats
         'url': 'https://www.loom.com/embed/ddcf1c1ad21f451ea7468b1e33917e4e',
-        'md5': '8488817242a0db1cb2ad0ea522553cf6',
+        'md5': 'b321d261656848c184a94e3b93eae28d',
         'info_dict': {
             'id': 'ddcf1c1ad21f451ea7468b1e33917e4e',
             'ext': 'mp4',
@@ -104,6 +104,7 @@ class LoomIE(InfoExtractor):
             'timestamp': 1657216459,
             'duration': 181,
         },
+        'params': {'format': 'bestvideo'},  # Test video-only fixup
         'expected_warnings': ['Failed to parse JSON'],
     }]
     _WEBPAGE_TESTS = [{
@@ -293,7 +294,11 @@ class LoomIE(InfoExtractor):
                 format_url = format_url.replace('-split.m3u8', '.m3u8')
                 m3u8_formats = self._extract_m3u8_formats(
                     format_url, video_id, 'mp4', m3u8_id=f'hls-{format_id}', fatal=False, quality=quality)
+                # Sometimes only split video/audio formats are available, need to fixup video-only formats
+                is_not_premerged = 'none' in traverse_obj(m3u8_formats, (..., 'vcodec'))
                 for fmt in m3u8_formats:
+                    if is_not_premerged and fmt.get('vcodec') != 'none':
+                        fmt['acodec'] = 'none'
                     yield {
                         **fmt,
                         'url': update_url(fmt['url'], query=query),

yt_dlp/extractor/mailru.py

@@ -126,7 +126,7 @@ class MailRuIE(InfoExtractor):
         video_data = None
 
         # fix meta_url if missing the host address
-        if re.match(r'^\/\+\/', meta_url):
+        if re.match(r'\/\+\/', meta_url):
             meta_url = urljoin('https://my.mail.ru', meta_url)
 
         if meta_url:

yt_dlp/extractor/mdr.py

@@ -13,8 +13,8 @@ from ..utils import (
 
 
 class MDRIE(InfoExtractor):
-    IE_DESC = 'MDR.DE and KiKA'
+    IE_DESC = 'MDR.DE'
-    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
+    _VALID_URL = r'https?://(?:www\.)?mdr\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
 
     _GEO_COUNTRIES = ['DE']
 
@@ -34,30 +34,6 @@ class MDRIE(InfoExtractor):
             'uploader': 'MITTELDEUTSCHER RUNDFUNK',
         },
         'skip': '404 not found',
-    }, {
-        'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
-        'md5': '4930515e36b06c111213e80d1e4aad0e',
-        'info_dict': {
-            'id': '19636',
-            'ext': 'mp4',
-            'title': 'Baumhaus vom 30. Oktober 2015',
-            'duration': 134,
-            'uploader': 'KIKA',
-        },
-        'skip': '404 not found',
-    }, {
-        'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
-        'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
-        'info_dict': {
-            'id': '8182',
-            'ext': 'mp4',
-            'title': 'Beutolomäus und der geheime Weihnachtswunsch',
-            'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
-            'timestamp': 1482541200,
-            'upload_date': '20161224',
-            'duration': 4628,
-            'uploader': 'KIKA',
-        },
     }, {
         # audio with alternative playerURL pattern
         'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html',
@@ -68,28 +44,7 @@ class MDRIE(InfoExtractor):
             'duration': 3239,
             'uploader': 'MITTELDEUTSCHER RUNDFUNK',
         },
-    }, {
+        'skip': '404 not found',
-        # empty bitrateVideo and bitrateAudio
-        'url': 'https://www.kika.de/filme/sendung128372_zc-572e3f45_zs-1d9fb70e.html',
-        'info_dict': {
-            'id': '128372',
-            'ext': 'mp4',
-            'title': 'Der kleine Wichtel kehrt zurück',
-            'description': 'md5:f77fafdff90f7aa1e9dca14f662c052a',
-            'duration': 4876,
-            'timestamp': 1607823300,
-            'upload_date': '20201213',
-            'uploader': 'ZDF',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
-        'only_matching': True,
     }, {
         'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html',
         'only_matching': True,

yt_dlp/extractor/mediaklikk.py

@@ -16,6 +16,15 @@ class MediaKlikkIE(InfoExtractor):
                         (?P<id>[^/#?_]+)'''
 
     _TESTS = [{
+        'url': 'https://mediaklikk.hu/filmajanlo/cikk/az-ajto/',
+        'info_dict': {
+            'id': '668177',
+            'title': 'Az ajtó',
+            'display_id': 'az-ajto',
+            'ext': 'mp4',
+            'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2016/01/vlcsnap-2023-07-31-14h18m52s111.jpg',
+        },
+    }, {
         # (old) mediaklikk. date in html.
         'url': 'https://mediaklikk.hu/video/hazajaro-delnyugat-bacska-a-duna-menten-palankatol-doroszloig/',
         'info_dict': {
@@ -37,6 +46,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230903',
             'thumbnail': 'https://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg',
         },
+        'skip': 'Webpage redirects to 404 page',
     }, {
         # (old) m4sport
         'url': 'https://m4sport.hu/video/2021/08/30/gyemant-liga-parizs/',
@@ -59,6 +69,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230908',
             'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-08-22h43m18s691.jpg',
         },
+        'skip': 'Webpage redirects to 404 page',
     }, {
         # m4sport with *video/ url and no date
         'url': 'https://m4sport.hu/bl-video/real-madrid-chelsea-1-1/',
@@ -69,6 +80,7 @@ class MediaKlikkIE(InfoExtractor):
             'ext': 'mp4',
             'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2021/04/Sequence-01.Still001-1024x576.png',
         },
+        'skip': 'Webpage redirects to 404 page',
     }, {
         # (old) hirado
         'url': 'https://hirado.hu/videok/felteteleket-szabott-a-fovaros/',
@@ -90,6 +102,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230911',
             'thumbnail': 'https://hirado.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-11-09h16m09s882.jpg',
         },
+        'skip': 'Webpage redirects to video list page',
     }, {
         # (old) petofilive
         'url': 'https://petofilive.hu/video/2021/06/07/tha-shudras-az-akusztikban/',
@@ -112,6 +125,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230909',
             'thumbnail': 'https://petofilive.hu/wp-content/uploads/sites/4/2023/09/Clipboard11-2.jpg',
         },
+        'skip': 'Webpage redirects to video list page',
     }]
 
     def _real_extract(self, url):
@@ -133,7 +147,9 @@ class MediaKlikkIE(InfoExtractor):
                 r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
 
         player_data['video'] = player_data.pop('token')
-        player_page = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, query=player_data)
+        player_page = self._download_webpage(
+            'https://player.mediaklikk.hu/playernew/player.php', video_id,
+            query=player_data, headers={'Referer': url})
         player_json = self._search_json(
             r'\bpl\.setup\s*\(', player_page, 'player json', video_id, end_pattern=r'\);')
         playlist_url = traverse_obj(
@@ -141,14 +157,14 @@ class MediaKlikkIE(InfoExtractor):
         if not playlist_url:
             raise ExtractorError('Unable to extract playlist url')
 
-        formats = self._extract_wowza_formats(
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(playlist_url, video_id)
-            playlist_url, video_id, skip_protocols=['f4m', 'smil', 'dash'])
 
         return {
             'id': video_id,
             'title': title,
             'display_id': display_id,
             'formats': formats,
+            'subtitles': subtitles,
             'upload_date': upload_date,
             'thumbnail': player_data.get('bgImage') or self._og_search_thumbnail(webpage),
         }

yt_dlp/extractor/mgtv.py

@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class MGTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/[bv]/(?:[^/]+/)*(?P<id>\d+)\.html'
     IE_DESC = '芒果TV'
     IE_NAME = 'MangoTV'
 

yt_dlp/extractor/mit.py

@@ -65,7 +65,7 @@ class TechTVMITIE(InfoExtractor):
 
 class OCWMITIE(InfoExtractor):
     IE_NAME = 'ocw.mit.edu'
-    _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
+    _VALID_URL = r'https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
     _BASE_URL = 'http://ocw.mit.edu/'
 
     _TESTS = [

yt_dlp/extractor/mlb.py

@@ -1,16 +1,21 @@
+import json
 import re
-import urllib.parse
+import time
 import uuid
 
 from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
 from ..utils import (
+    ExtractorError,
     determine_ext,
     int_or_none,
     join_nonempty,
+    jwt_decode_hs256,
     parse_duration,
     parse_iso8601,
     try_get,
     url_or_none,
+    urlencode_postdata,
 )
 from ..utils.traversal import traverse_obj
 
@@ -276,81 +281,225 @@ class MLBVideoIE(MLBBaseIE):
 class MLBTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P<id>\d{6})'
     _NETRC_MACHINE = 'mlb'
-
     _TESTS = [{
         'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638',
         'info_dict': {
             'id': '661581',
             'ext': 'mp4',
             'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies',
+            'release_date': '20220702',
+            'release_timestamp': 1656792300,
         },
-        'params': {
+        'params': {'skip_download': 'm3u8'},
-            'skip_download': True,
+    }, {
+        # makeup game: has multiple dates, need to avoid games with 'rescheduleDate'
+        'url': 'https://www.mlb.com/tv/g747039/vd22541c4-5a29-45f7-822b-635ec041cf5e',
+        'info_dict': {
+            'id': '747039',
+            'ext': 'mp4',
+            'title': '2024-07-29 - Toronto Blue Jays @ Baltimore Orioles',
+            'release_date': '20240729',
+            'release_timestamp': 1722280200,
         },
+        'params': {'skip_download': 'm3u8'},
     }]
+    _GRAPHQL_INIT_QUERY = '''\
+mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) {
+    initSession(device: $device, clientType: $clientType, experience: $experience) {
+        deviceId
+        sessionId
+        entitlements {
+            code
+        }
+        location {
+            countryCode
+            regionName
+            zipCode
+            latitude
+            longitude
+        }
+        clientExperience
+        features
+    }
+  }'''
+    _GRAPHQL_PLAYBACK_QUERY = '''\
+mutation initPlaybackSession(
+        $adCapabilities: [AdExperienceType]
+        $mediaId: String!
+        $deviceId: String!
+        $sessionId: String!
+        $quality: PlaybackQuality
+    ) {
+        initPlaybackSession(
+            adCapabilities: $adCapabilities
+            mediaId: $mediaId
+            deviceId: $deviceId
+            sessionId: $sessionId
+            quality: $quality
+        ) {
+            playbackSessionId
+            playback {
+                url
+                token
+                expiration
+                cdn
+            }
+        }
+    }'''
+    _APP_VERSION = '7.8.2'
+    _device_id = None
+    _session_id = None
     _access_token = None
+    _token_expiry = 0
+
+    @property
+    def _api_headers(self):
+        if (self._token_expiry - 120) <= time.time():
+            self.write_debug('Access token has expired; re-logging in')
+            self._perform_login(*self._get_login_info())
+        return {'Authorization': f'Bearer {self._access_token}'}
 
     def _real_initialize(self):
         if not self._access_token:
             self.raise_login_required(
                 'All videos are only available to registered users', method='password')
 
+    def _set_device_id(self, username):
+        if not self._device_id:
+            self._device_id = self.cache.load(
+                self._NETRC_MACHINE, 'device_ids', default={}).get(username)
+        if self._device_id:
+            return
+        self._device_id = str(uuid.uuid4())
+        self.cache.store(self._NETRC_MACHINE, 'device_ids', {username: self._device_id})
+
     def _perform_login(self, username, password):
-        data = f'grant_type=password&username={urllib.parse.quote(username)}&password={urllib.parse.quote(password)}&scope=openid offline_access&client_id=0oa3e1nutA1HLzAKG356'
+        try:
-        access_token = self._download_json(
+            self._access_token = self._download_json(
-            'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
+                'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
-            headers={
+                'Logging in', 'Unable to log in', headers={
-                'User-Agent': 'okhttp/3.12.1',
+                    'User-Agent': 'okhttp/3.12.1',
-                'Content-Type': 'application/x-www-form-urlencoded',
+                    'Content-Type': 'application/x-www-form-urlencoded',
-            }, data=data.encode())['access_token']
+                }, data=urlencode_postdata({
+                    'grant_type': 'password',
+                    'username': username,
+                    'password': password,
+                    'scope': 'openid offline_access',
+                    'client_id': '0oa3e1nutA1HLzAKG356',
+                }))['access_token']
+        except ExtractorError as error:
+            if isinstance(error.cause, HTTPError) and error.cause.status == 400:
+                raise ExtractorError('Invalid username or password', expected=True)
+            raise
 
-        entitlement = self._download_webpage(
+        self._token_expiry = traverse_obj(self._access_token, ({jwt_decode_hs256}, 'exp', {int})) or 0
-            f'https://media-entitlement.mlb.com/api/v3/jwt?os=Android&appname=AtBat&did={uuid.uuid4()}', None,
+        self._set_device_id(username)
-            headers={
-                'User-Agent': 'okhttp/3.12.1',
-                'Authorization': f'Bearer {access_token}',
-            })
 
-        data = f'grant_type=urn:ietf:params:oauth:grant-type:token-exchange&subject_token={entitlement}&subject_token_type=urn:ietf:params:oauth:token-type:jwt&platform=android-tv'
+        self._session_id = self._call_api({
-        self._access_token = self._download_json(
+            'operationName': 'initSession',
-            'https://us.edge.bamgrid.com/token', None,
+            'query': self._GRAPHQL_INIT_QUERY,
+            'variables': {
+                'device': {
+                    'appVersion': self._APP_VERSION,
+                    'deviceFamily': 'desktop',
+                    'knownDeviceId': self._device_id,
+                    'languagePreference': 'ENGLISH',
+                    'manufacturer': '',
+                    'model': '',
+                    'os': '',
+                    'osVersion': '',
+                },
+                'clientType': 'WEB',
+            },
+        }, None, 'session ID')['data']['initSession']['sessionId']
+
+    def _call_api(self, data, video_id, description='GraphQL JSON', fatal=True):
+        return self._download_json(
+            'https://media-gateway.mlb.com/graphql', video_id,
+            f'Downloading {description}', f'Unable to download {description}', fatal=fatal,
             headers={
+                **self._api_headers,
                 'Accept': 'application/json',
-                'Authorization': 'Bearer bWxidHYmYW5kcm9pZCYxLjAuMA.6LZMbH2r--rbXcgEabaDdIslpo4RyZrlVfWZhsAgXIk',
+                'Content-Type': 'application/json',
-                'Content-Type': 'application/x-www-form-urlencoded',
+                'x-client-name': 'WEB',
-            }, data=data.encode())['access_token']
+                'x-client-version': self._APP_VERSION,
+            }, data=json.dumps(data, separators=(',', ':')).encode())
+
+    def _extract_formats_and_subtitles(self, broadcast, video_id):
+        feed = traverse_obj(broadcast, ('homeAway', {str.title}))
+        medium = traverse_obj(broadcast, ('type', {str}))
+        language = traverse_obj(broadcast, ('language', {str.lower}))
+        format_id = join_nonempty(feed, medium, language)
+
+        response = self._call_api({
+            'operationName': 'initPlaybackSession',
+            'query': self._GRAPHQL_PLAYBACK_QUERY,
+            'variables': {
+                'adCapabilities': ['GOOGLE_STANDALONE_AD_PODS'],
+                'deviceId': self._device_id,
+                'mediaId': broadcast['mediaId'],
+                'quality': 'PLACEHOLDER',
+                'sessionId': self._session_id,
+            },
+        }, video_id, f'{format_id} broadcast JSON', fatal=False)
+
+        playback = traverse_obj(response, ('data', 'initPlaybackSession', 'playback', {dict}))
+        m3u8_url = traverse_obj(playback, ('url', {url_or_none}))
+        token = traverse_obj(playback, ('token', {str}))
+
+        if not (m3u8_url and token):
+            errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
+            if 'not entitled' in errors:
+                raise ExtractorError(errors, expected=True)
+            elif errors:  # Only warn when 'blacked out' since radio formats are available
+                self.report_warning(f'API returned errors for {format_id}: {errors}')
+            else:
+                self.report_warning(f'No formats available for {format_id} broadcast; skipping')
+            return [], {}
+
+        cdn_headers = {'x-cdn-token': token}
+        fmts, subs = self._extract_m3u8_formats_and_subtitles(
+            m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4',
+            m3u8_id=format_id, fatal=False, headers=cdn_headers)
+        for fmt in fmts:
+            fmt['http_headers'] = cdn_headers
+            fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' '))
+            fmt.setdefault('language', language)
+            if fmt.get('vcodec') == 'none' and fmt['language'] == 'en':
+                fmt['source_preference'] = 10
+
+        return fmts, subs
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        airings = self._download_json(
+        data = self._download_json(
-            f'https://search-api-mlbtv.mlb.com/svc/search/v2/graphql/persisted/query/core/Airings?variables=%7B%22partnerProgramIds%22%3A%5B%22{video_id}%22%5D%2C%22applyEsniMediaRightsLabels%22%3Atrue%7D',
+            'https://statsapi.mlb.com/api/v1/schedule', video_id, query={
-            video_id)['data']['Airings']
+                'gamePk': video_id,
+                'hydrate': 'broadcasts(all),statusFlags',
+            })
+        metadata = traverse_obj(data, (
+            'dates', ..., 'games',
+            lambda _, v: str(v['gamePk']) == video_id and not v.get('rescheduleDate'), any))
+
+        broadcasts = traverse_obj(metadata, (
+            'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF'))
 
         formats, subtitles = [], {}
-        for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']):
+        for broadcast in broadcasts:
-            format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing)
+            fmts, subs = self._extract_formats_and_subtitles(broadcast, video_id)
-            m3u8_url = traverse_obj(self._download_json(
+            formats.extend(fmts)
-                airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id,
+            self._merge_subtitles(subs, target=subtitles)
-                note=f'Downloading {format_id} stream info JSON',
-                errnote=f'Failed to download {format_id} stream info, skipping',
-                fatal=False, headers={
-                    'Authorization': self._access_token,
-                    'Accept': 'application/vnd.media-service+json; version=2',
-                }), ('stream', 'complete', {url_or_none}))
-            if not m3u8_url:
-                continue
-            f, s = self._extract_m3u8_formats_and_subtitles(
-                m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
-            formats.extend(f)
-            self._merge_subtitles(s, target=subtitles)
 
         return {
             'id': video_id,
-            'title': traverse_obj(airings, (..., 'titles', 0, 'episodeName'), get_all=False),
+            'title': join_nonempty(
-            'is_live': traverse_obj(airings, (..., 'mediaConfig', 'productType'), get_all=False) == 'LIVE',
+                traverse_obj(metadata, ('officialDate', {str})),
+                traverse_obj(metadata, ('teams', ('away', 'home'), 'team', 'name', {str}, all, {' @ '.join})),
+                delim=' - '),
+            'is_live': traverse_obj(broadcasts, (..., 'mediaState', 'mediaStateCode', {str}, any)) == 'MEDIA_ON',
+            'release_timestamp': traverse_obj(metadata, ('gameDate', {parse_iso8601})),
             'formats': formats,
             'subtitles': subtitles,
-            'http_headers': {'Authorization': f'Bearer {self._access_token}'},
         }
 
 

yt_dlp/extractor/mojevideo.py

@@ -0,0 +1,121 @@
+from .common import InfoExtractor
+from ..utils import js_to_json, remove_end, update_url_query
+
+
+class MojevideoIE(InfoExtractor):
+    IE_DESC = 'mojevideo.sk'
+    _VALID_URL = r'https?://(?:www\.)?mojevideo\.sk/video/(?P<id>\w+)/(?P<display_id>[\w()]+?)\.html'
+
+    _TESTS = [{
+        'url': 'https://www.mojevideo.sk/video/3d17c/chlapci_dobetonovali_sme_mame_hotovo.html',
+        'md5': '384a4628bd2bbd261c5206cf77c38c17',
+        'info_dict': {
+            'id': '3d17c',
+            'ext': 'mp4',
+            'title': 'Chlapci dobetónovali sme, máme hotovo!',
+            'display_id': 'chlapci_dobetonovali_sme_mame_hotovo',
+            'description': 'md5:a0822126044050d304a9ef58c92ddb34',
+            'thumbnail': 'https://fs5.mojevideo.sk/imgfb/250236.jpg',
+            'duration': 21.0,
+            'upload_date': '20230919',
+            'timestamp': 1695129706,
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # 720p
+        'url': 'https://www.mojevideo.sk/video/14677/den_blbec.html',
+        'md5': '517c3e111c53a67d10b429c1f344ba2f',
+        'info_dict': {
+            'id': '14677',
+            'ext': 'mp4',
+            'title': 'Deň blbec?',
+            'display_id': 'den_blbec',
+            'description': 'I maličkosť vám môže zmeniť celý deň. Nikdy nezahadzujte žuvačky na zem!',
+            'thumbnail': 'https://fs5.mojevideo.sk/imgfb/83575.jpg',
+            'duration': 100.0,
+            'upload_date': '20120515',
+            'timestamp': 1337076481,
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # 1080p
+        'url': 'https://www.mojevideo.sk/video/2feb2/band_maid_onset_(instrumental)_live_zepp_tokyo_(full_hd).html',
+        'md5': '64599a23d3ac31cf2fe069e4353d8162',
+        'info_dict': {
+            'id': '2feb2',
+            'ext': 'mp4',
+            'title': 'BAND-MAID - onset (Instrumental) Live - Zepp Tokyo (Full HD)',
+            'display_id': 'band_maid_onset_(instrumental)_live_zepp_tokyo_(full_hd)',
+            'description': 'Výborná inštrumentálna skladba od skupiny BAND-MAID.',
+            'thumbnail': 'https://fs5.mojevideo.sk/imgfb/196274.jpg',
+            'duration': 240.0,
+            'upload_date': '20190708',
+            'timestamp': 1562576592,
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # 720p
+        'url': 'https://www.mojevideo.sk/video/358c8/dva_nissany_skyline_strielaju_v_londyne.html',
+        'only_matching': True,
+    }, {
+        # 720p
+        'url': 'https://www.mojevideo.sk/video/2455d/gopro_hero4_session_nova_sportova_vodotesna_kamera.html',
+        'only_matching': True,
+    }, {
+        # 1080p
+        'url': 'https://www.mojevideo.sk/video/352ee/amd_rx_6800_xt_vs_nvidia_rtx_3080_(test_v_9_hrach).html',
+        'only_matching': True,
+    }, {
+        # 1080p
+        'url': 'https://www.mojevideo.sk/video/2cbeb/trailer_z_avengers_infinity_war.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id, display_id = self._match_valid_url(url).groups()
+        webpage = self._download_webpage(url, video_id)
+
+        video_id_dec = self._search_regex(
+            r'\bvId\s*=\s*(\d+)', webpage, 'video id', fatal=False) or str(int(video_id, 16))
+        video_exp = self._search_regex(r'\bvEx\s*=\s*["\'](\d+)', webpage, 'video expiry')
+        video_hashes = self._search_json(
+            r'\bvHash\s*=', webpage, 'video hashes', video_id,
+            contains_pattern=r'\[(?s:.+)\]', transform_source=js_to_json)
+
+        formats = []
+        for video_hash, (suffix, quality, format_note) in zip(video_hashes, [
+            ('', 1, 'normálna kvalita'),
+            ('_lq', 0, 'nízka kvalita'),
+            ('_hd', 2, 'HD-720p'),
+            ('_fhd', 3, 'FULL HD-1080p'),
+            ('_2k', 4, '2K-1440p'),
+        ]):
+            formats.append({
+                'format_id': f'mp4-{quality}',
+                'quality': quality,
+                'format_note': format_note,
+                'url': update_url_query(
+                    f'https://cache01.mojevideo.sk/securevideos69/{video_id_dec}{suffix}.mp4', {
+                        'md5': video_hash,
+                        'expires': video_exp,
+                    }),
+            })
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'title': (self._og_search_title(webpage, default=None)
+                      or remove_end(self._html_extract_title(webpage, 'title'), ' - Mojevideo')),
+            'description': self._og_search_description(webpage),
+            **self._search_json_ld(webpage, video_id, default={}),
+        }

yt_dlp/extractor/niconico.py

@@ -40,7 +40,6 @@ class NiconicoIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
-        'md5': 'd1a75c0823e2f629128c43e1212760f9',
         'info_dict': {
             'id': 'sm22312215',
             'ext': 'mp4',
@@ -56,8 +55,8 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['未設定'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # File downloaded with and without credentials are different, so omit
         # the md5 field
@@ -77,8 +76,8 @@ class NiconicoIE(InfoExtractor):
             'view_count': int,
             'genres': ['音楽・サウンド'],
             'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # 'video exists but is marked as "deleted"
         # md5 is unstable
@@ -112,7 +111,6 @@ class NiconicoIE(InfoExtractor):
     }, {
         # video not available via `getflv`; "old" HTML5 video
         'url': 'http://www.nicovideo.jp/watch/sm1151009',
-        'md5': 'f95a3d259172667b293530cc2e41ebda',
         'info_dict': {
             'id': 'sm1151009',
             'ext': 'mp4',
@@ -128,11 +126,10 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['ゲーム'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # "New" HTML5 video
-        # md5 is unstable
         'url': 'http://www.nicovideo.jp/watch/sm31464864',
         'info_dict': {
             'id': 'sm31464864',
@@ -149,12 +146,11 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['アニメ'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Video without owner
         'url': 'http://www.nicovideo.jp/watch/sm18238488',
-        'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
         'info_dict': {
             'id': 'sm18238488',
             'ext': 'mp4',
@@ -168,8 +164,8 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['エンターテイメント'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
         'only_matching': True,
@@ -424,7 +420,7 @@ class NiconicoIE(InfoExtractor):
                 'x-request-with': 'https://www.nicovideo.jp',
             })['data']['contentUrl']
         # Getting all audio formats results in duplicate video formats which we filter out later
-        dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id)
+        dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id, 'mp4')
 
         # m3u8 extraction does not provide audio bitrates, so extract from the API data and fix
         for audio_fmt in traverse_obj(dms_fmts, lambda _, v: v['vcodec'] == 'none'):
@@ -436,7 +432,6 @@ class NiconicoIE(InfoExtractor):
                     'asr': ('samplingRate', {int_or_none}),
                 }), get_all=False),
                 'acodec': 'aac',
-                'ext': 'm4a',
             }
 
         # Sort before removing dupes to keep the format dicts with the lowest tbr
@@ -458,9 +453,11 @@ class NiconicoIE(InfoExtractor):
             if video_id.startswith('so'):
                 video_id = self._match_id(handle.url)
 
-            api_data = self._parse_json(self._html_search_regex(
+            api_data = traverse_obj(
-                'data-api-data="([^"]+)"', webpage,
+                self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
-                'API data', default='{}'), video_id)
+                ('data', 'response', {dict}))
+            if not api_data:
+                raise ExtractorError('Server response data not found')
         except ExtractorError as e:
             try:
                 api_data = self._download_json(

yt_dlp/extractor/nzonscreen.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class NZOnScreenIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
         'info_dict': {

yt_dlp/extractor/nzz.py

@@ -1,9 +1,6 @@
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    extract_attributes,
-)
 
 
 class NZZIE(InfoExtractor):
@@ -22,19 +19,14 @@ class NZZIE(InfoExtractor):
         'playlist_count': 1,
     }]
 
+    def _entries(self, webpage, page_id):
+        for script in re.findall(r'(?s)<script[^>]* data-hid="jw-video-jw[^>]+>(.+?)</script>', webpage):
+            settings = self._search_json(r'var\s+settings\s*=[^{]*', script, 'settings', page_id, fatal=False)
+            if entry := self._parse_jwplayer_data(settings, page_id):
+                yield entry
+
     def _real_extract(self, url):
         page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
 
-        entries = []
+        return self.playlist_result(self._entries(webpage, page_id), page_id)
-        for player_element in re.findall(
-                r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage):
-            player_params = extract_attributes(player_element)
-            if player_params.get('data-type') not in ('kaltura_singleArticle',):
-                self.report_warning('Unsupported player type')
-                continue
-            entry_id = player_params['data-id']
-            entries.append(self.url_result(
-                'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
-
-        return self.playlist_result(entries, page_id)

yt_dlp/extractor/olympics.py

@@ -1,9 +1,19 @@
 from .common import InfoExtractor
-from ..utils import int_or_none, try_get
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    parse_qs,
+    try_get,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
 
 
 class OlympicsReplayIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?olympics\.com(?:/tokyo-2020)?/[a-z]{2}/(?:replay|video)/(?P<id>[^/#&?]+)'
+    _VALID_URL = r'https?://(?:www\.)?olympics\.com/[a-z]{2}/(?:paris-2024/)?(?:replay|videos?|original-series/episode)/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://olympics.com/fr/video/men-s-109kg-group-a-weightlifting-tokyo-2020-replays',
         'info_dict': {
@@ -11,26 +21,105 @@ class OlympicsReplayIE(InfoExtractor):
             'ext': 'mp4',
             'title': '+109kg (H) Groupe A - Haltérophilie | Replay de Tokyo 2020',
             'upload_date': '20210801',
-            'timestamp': 1627783200,
+            'timestamp': 1627797600,
             'description': 'md5:c66af4a5bc7429dbcc43d15845ff03b3',
-            'uploader': 'International Olympic Committee',
+            'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2',
-        },
+            'duration': 7017.0,
-        'params': {
-            'skip_download': True,
         },
     }, {
-        'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp',
+        'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024',
-        'only_matching': True,
+        'info_dict': {
+            'id': '32633650-c5ee-4280-8b94-fb6defb6a9b5',
+            'ext': 'mp4',
+            'title': 'B-girl Nicka - Breaking Life, Road to Paris 2024 | Episode 1',
+            'upload_date': '20240517',
+            'timestamp': 1715948200,
+            'description': 'md5:f63d728a41270ec628f6ac33ce471bb1',
+            'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/a3j96l7j6so3vyfijby1',
+            'duration': 1321.0,
+        },
+    }, {
+        'url': 'https://olympics.com/en/paris-2024/videos/men-s-preliminaries-gbr-esp-ned-rsa-hockey-olympic-games-paris-2024',
+        'info_dict': {
+            'id': '3d96db23-8eee-4b7c-8ef5-488a0361026c',
+            'ext': 'mp4',
+            'title': 'Men\'s Preliminaries GBR-ESP & NED-RSA | Hockey | Olympic Games Paris 2024',
+            'upload_date': '20240727',
+            'timestamp': 1722066600,
+        },
+        'skip': 'Geo-restricted to RU, BR, BT, NP, TM, BD, TL',
+    }, {
+        'url': 'https://olympics.com/en/paris-2024/videos/dnp-suni-lee-i-have-goals-and-i-have-expectations-for-myself-but-i-also-am-trying-to-give-myself-grace',
+        'info_dict': {
+            'id': 'a42f37ab-8a74-41d0-a7d9-af27b7b02a90',
+            'ext': 'mp4',
+            'title': 'md5:c7cfbc9918636a98e66400a812e4d407',
+            'upload_date': '20240729',
+            'timestamp': 1722288600,
+        },
     }]
+    _GEO_BYPASS = False
+
+    def _extract_from_nextjs_data(self, webpage, video_id):
+        data = traverse_obj(self._search_nextjs_data(webpage, video_id, default={}), (
+            'props', 'pageProps', 'page', 'items',
+            lambda _, v: v['name'] == 'videoPlaylist', 'data', 'currentVideo', {dict}, any))
+        if not data:
+            return None
+
+        geo_countries = traverse_obj(data, ('countries', ..., {str}))
+        if traverse_obj(data, ('geoRestrictedVideo', {bool})):
+            self.raise_geo_restricted(countries=geo_countries)
+
+        is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE'
+        m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl']
+        tokenized_url = self._tokenize_url(m3u8_url, data['jwtToken'], is_live, video_id)
+
+        try:
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                tokenized_url, video_id, 'mp4', m3u8_id='hls')
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and 'georestricted' in e.cause.msg:
+                self.raise_geo_restricted(countries=geo_countries)
+            raise
+
+        return {
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': is_live,
+            **traverse_obj(data, {
+                'id': ('videoID', {str}),
+                'title': ('title', {str}),
+                'timestamp': ('contentDate', {parse_iso8601}),
+            }),
+        }
+
+    def _tokenize_url(self, url, token, is_live, video_id):
+        return self._download_json(
+            'https://metering.olympics.com/tokengenerator', video_id,
+            'Downloading tokenized m3u8 url', query={
+                **parse_qs(url),
+                'url': update_url(url, query=None),
+                'service-id': 'live' if is_live else 'vod',
+                'user-auth': token,
+            })['data']['url']
+
+    def _legacy_tokenize_url(self, url, video_id):
+        return self._download_json(
+            'https://olympics.com/tokenGenerator', video_id,
+            'Downloading legacy tokenized m3u8 url', query={'url': url})
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
+
+        if info := self._extract_from_nextjs_data(webpage, video_id):
+            return info
+
         title = self._html_search_meta(('title', 'og:title', 'twitter:title'), webpage)
-        uuid = self._html_search_meta('episode_uid', webpage)
+        video_uuid = self._html_search_meta('episode_uid', webpage)
         m3u8_url = self._html_search_meta('video_url', webpage)
-        json_ld = self._search_json_ld(webpage, uuid)
+        json_ld = self._search_json_ld(webpage, video_uuid)
         thumbnails_list = json_ld.get('image')
         if not thumbnails_list:
             thumbnails_list = self._html_search_regex(
@@ -48,12 +137,12 @@ class OlympicsReplayIE(InfoExtractor):
                 'width': width,
                 'height': int_or_none(try_get(width, lambda x: x * height_a / width_a)),
             })
-        m3u8_url = self._download_json(
+
-            f'https://olympics.com/tokenGenerator?url={m3u8_url}', uuid, note='Downloading m3u8 url')
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-        formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, uuid, 'mp4', m3u8_id='hls')
+            self._legacy_tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls')
 
         return {
-            'id': uuid,
+            'id': video_uuid,
             'title': title,
             'thumbnails': thumbnails,
             'formats': formats,

yt_dlp/extractor/patreon.py

@@ -420,7 +420,7 @@ class PatreonIE(PatreonBaseIE):
 
 class PatreonCampaignIE(PatreonBaseIE):
 
-    _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m/(?P<campaign_id>\d+))|(?P<vanity>[-\w]+))'
+    _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m|api/campaigns)/(?P<campaign_id>\d+)|(?P<vanity>[-\w]+))'
     _TESTS = [{
         'url': 'https://www.patreon.com/dissonancepod/',
         'info_dict': {
@@ -442,25 +442,44 @@ class PatreonCampaignIE(PatreonBaseIE):
         'url': 'https://www.patreon.com/m/4767637/posts',
         'info_dict': {
             'title': 'Not Just Bikes',
-            'channel_follower_count': int,
             'id': '4767637',
             'channel_id': '4767637',
             'channel_url': 'https://www.patreon.com/notjustbikes',
-            'description': 'md5:595c6e7dca76ae615b1d38c298a287a1',
+            'description': 'md5:9f4b70051216c4d5c58afe580ffc8d0f',
             'age_limit': 0,
             'channel': 'Not Just Bikes',
             'uploader_url': 'https://www.patreon.com/notjustbikes',
-            'uploader': 'Not Just Bikes',
+            'uploader': 'Jason',
             'uploader_id': '37306634',
             'thumbnail': r're:^https?://.*$',
         },
         'playlist_mincount': 71,
+    }, {
+        'url': 'https://www.patreon.com/api/campaigns/4243769/posts',
+        'info_dict': {
+            'title': 'Second Thought',
+            'channel_follower_count': int,
+            'id': '4243769',
+            'channel_id': '4243769',
+            'channel_url': 'https://www.patreon.com/secondthought',
+            'description': 'md5:69c89a3aba43efdb76e85eb023e8de8b',
+            'age_limit': 0,
+            'channel': 'Second Thought',
+            'uploader_url': 'https://www.patreon.com/secondthought',
+            'uploader': 'JT Chapman',
+            'uploader_id': '32718287',
+            'thumbnail': r're:^https?://.*$',
+        },
+        'playlist_mincount': 201,
     }, {
         'url': 'https://www.patreon.com/dissonancepod/posts',
         'only_matching': True,
     }, {
         'url': 'https://www.patreon.com/m/5932659',
         'only_matching': True,
+    }, {
+        'url': 'https://www.patreon.com/api/campaigns/4243769',
+        'only_matching': True,
     }]
 
     @classmethod

yt_dlp/extractor/pinterest.py

@@ -109,7 +109,7 @@ class PinterestBaseIE(InfoExtractor):
 
 
 class PinterestIE(PinterestBaseIE):
-    _VALID_URL = rf'{PinterestBaseIE._VALID_URL_BASE}/pin/(?P<id>\d+)'
+    _VALID_URL = rf'{PinterestBaseIE._VALID_URL_BASE}/pin/(?:[\w-]+--)?(?P<id>\d+)'
     _TESTS = [{
         # formats found in data['videos']
         'url': 'https://www.pinterest.com/pin/664281013778109217/',
@@ -174,6 +174,25 @@ class PinterestIE(PinterestBaseIE):
     }, {
         'url': 'https://co.pinterest.com/pin/824721750502199491/',
         'only_matching': True,
+    },
+        {
+        'url': 'https://pinterest.com/pin/dive-into-serenity-blue-lagoon-pedi-nails-for-a-tranquil-and-refreshing-spa-experience-video-in-2024--2885187256207927',
+        'info_dict': {
+            'id': '2885187256207927',
+            'ext': 'mp4',
+            'title': 'Dive into Serenity: Blue Lagoon Pedi Nails for a Tranquil and Refreshing Spa Experience! 💙💅',
+            'description': 'md5:5da41c767d2317e42e49b663b0b2150f',
+            'uploader': 'Glamour Artistry |Everyday Outfits, Luxury Fashion & Nail Designs',
+            'uploader_id': '1142999717836434688',
+            'upload_date': '20240702',
+            'timestamp': 1719939156,
+            'duration': 7.967,
+            'comment_count': int,
+            'repost_count': int,
+            'categories': 'count:9',
+            'tags': ['#BlueLagoonPediNails', '#SpaExperience'],
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
+        },
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/pornhub.py

@@ -628,8 +628,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
             page_entries = self._extract_entries(webpage, host)
             if not page_entries:
                 break
-            for e in page_entries:
+            yield from page_entries
-                yield e
             if not self._has_more(webpage):
                 break
 

yt_dlp/extractor/radiko.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     clean_html,
+    join_nonempty,
     time_seconds,
     try_call,
     unified_timestamp,
@@ -167,7 +168,7 @@ class RadikoBaseIE(InfoExtractor):
 
 
 class RadikoIE(RadikoBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P<station>[A-Z0-9-]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P<station>[A-Z0-9-]+)/(?P<timestring>\d+)'
 
     _TESTS = [{
         # QRR (文化放送) station provides <desc>
@@ -183,8 +184,9 @@ class RadikoIE(RadikoBaseIE):
     }]
 
     def _real_extract(self, url):
-        station, video_id = self._match_valid_url(url).groups()
+        station, timestring = self._match_valid_url(url).group('station', 'timestring')
-        vid_int = unified_timestamp(video_id, False)
+        video_id = join_nonempty(station, timestring)
+        vid_int = unified_timestamp(timestring, False)
         prog, station_program, ft, radio_begin, radio_end = self._find_program(video_id, station, vid_int)
 
         auth_token, area_id = self._auth_client()
@@ -207,7 +209,7 @@ class RadikoIE(RadikoBaseIE):
                     'ft': radio_begin,
                     'end_at': radio_end,
                     'to': radio_end,
-                    'seek': video_id,
+                    'seek': timestring,
                 },
             ),
         }

yt_dlp/extractor/radiofrance.py

@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class RadioFranceIE(InfoExtractor):
-    _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
     IE_NAME = 'radiofrance'
 
     _TEST = {

yt_dlp/extractor/reverbnation.py

@@ -6,7 +6,7 @@ from ..utils import (
 
 
 class ReverbNationIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
+    _VALID_URL = r'https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
     _TESTS = [{
         'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
         'md5': 'c0aaf339bcee189495fdf5a8c8ba8645',

yt_dlp/extractor/rtp.py

@@ -8,7 +8,7 @@ from ..utils import js_to_json
 
 
 class RTPIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
+    _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/(?:(?:estudoemcasa|palco|zigzag)/)?p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
         'md5': 'e736ce0c665e459ddb818546220b4ef8',
@@ -19,9 +19,25 @@ class RTPIE(InfoExtractor):
             'description': 'As paixões musicais de António Cartaxo e António Macedo',
             'thumbnail': r're:^https?://.*\.jpg',
         },
+    }, {
+        'url': 'https://www.rtp.pt/play/zigzag/p13166/e757904/25-curiosidades-25-de-abril',
+        'md5': '9a81ed53f2b2197cfa7ed455b12f8ade',
+        'info_dict': {
+            'id': 'e757904',
+            'ext': 'mp4',
+            'title': '25 Curiosidades, 25 de Abril',
+            'description': 'Estudar ou não estudar - Em cada um dos episódios descobrimos uma curiosidade acerca de como era viver em Portugal antes da revolução do 25 de abr',
+            'thumbnail': r're:^https?://.*\.jpg',
+        },
     }, {
         'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
         'only_matching': True,
+    }, {
+        'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/portugues-1-ano',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rtp.pt/play/palco/p13785/l7nnon',
+        'only_matching': True,
     }]
 
     _RX_OBFUSCATION = re.compile(r'''(?xs)
@@ -49,17 +65,17 @@ class RTPIE(InfoExtractor):
 
         f, config = self._search_regex(
             r'''(?sx)
-                var\s+f\s*=\s*(?P<f>".*?"|{[^;]+?});\s*
+                (?:var\s+f\s*=\s*(?P<f>".*?"|{[^;]+?});\s*)?
                 var\s+player1\s+=\s+new\s+RTPPlayer\s*\((?P<config>{(?:(?!\*/).)+?})\);(?!\s*\*/)
             ''', webpage,
             'player config', group=('f', 'config'))
 
-        f = self._parse_json(
-            f, video_id,
-            lambda data: self.__unobfuscate(data, video_id=video_id))
         config = self._parse_json(
             config, video_id,
             lambda data: self.__unobfuscate(data, video_id=video_id))
+        f = config['file'] if not f else self._parse_json(
+            f, video_id,
+            lambda data: self.__unobfuscate(data, video_id=video_id))
 
         formats = []
         if isinstance(f, dict):

yt_dlp/extractor/rumble.py

@@ -8,14 +8,17 @@ from ..utils import (
     UnsupportedError,
     clean_html,
     determine_ext,
+    extract_attributes,
     format_field,
     get_element_by_class,
+    get_elements_html_by_class,
     int_or_none,
     join_nonempty,
     parse_count,
     parse_iso8601,
     traverse_obj,
     unescapeHTML,
+    urljoin,
 )
 
 
@@ -382,8 +385,10 @@ class RumbleChannelIE(InfoExtractor):
                 if isinstance(e.cause, HTTPError) and e.cause.status == 404:
                     break
                 raise
-            for video_url in re.findall(r'class="[^>"]*videostream__link[^>]+href="([^"]+\.html)"', webpage):
+            for video_url in traverse_obj(
-                yield self.url_result('https://rumble.com' + video_url)
+                get_elements_html_by_class('videostream__link', webpage), (..., {extract_attributes}, 'href'),
+            ):
+                yield self.url_result(urljoin('https://rumble.com', video_url))
 
     def _real_extract(self, url):
         url, playlist_id = self._match_valid_url(url).groups()

yt_dlp/extractor/rutube.py

@@ -6,6 +6,7 @@ from ..utils import (
     determine_ext,
     int_or_none,
     parse_qs,
+    traverse_obj,
     try_get,
     unified_timestamp,
     url_or_none,
@@ -80,6 +81,8 @@ class RutubeBaseIE(InfoExtractor):
                     'url': format_url,
                     'format_id': format_id,
                 })
+        for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
+            formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False))
         return formats
 
     def _download_and_extract_formats(self, video_id, query=None):
@@ -90,7 +93,7 @@ class RutubeBaseIE(InfoExtractor):
 class RutubeIE(RutubeBaseIE):
     IE_NAME = 'rutube'
     IE_DESC = 'Rutube videos'
-    _VALID_URL = r'https?://rutube\.ru/(?:video(?:/private)?|(?:play/)?embed)/(?P<id>[\da-z]{32})'
+    _VALID_URL = r'https?://rutube\.ru/(?:(?:live/)?video(?:/private)?|(?:play/)?embed)/(?P<id>[\da-z]{32})'
     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
 
     _TESTS = [{
@@ -164,6 +167,29 @@ class RutubeIE(RutubeBaseIE):
             'uploader': 'Стас Быков',
         },
         'expected_warnings': ['Unable to download f4m'],
+    }, {
+        'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
+        'info_dict': {
+            'id': 'c58f502c7bb34a8fcdd976b221fca292',
+            'ext': 'mp4',
+            'categories': ['Телепередачи'],
+            'description': '',
+            'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
+            'live_status': 'is_live',
+            'age_limit': 0,
+            'uploader_id': '23460655',
+            'timestamp': 1652972968,
+            'view_count': int,
+            'upload_date': '20220519',
+            'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'uploader': 'Первый канал',
+        },
+    }, {
+        'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
+        'only_matching': True,
+    }, {
+        'url': 'https://rutube.ru/live/video/private/c58f502c7bb34a8fcdd976b221fca292/',
+        'only_matching': True,
     }]
 
     @classmethod

yt_dlp/extractor/samplefocus.py

@@ -36,7 +36,7 @@ class SampleFocusIE(InfoExtractor):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_webpage(url, display_id, impersonate=True)
 
         sample_id = self._search_regex(
             r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
@@ -82,7 +82,15 @@ class SampleFocusIE(InfoExtractor):
         return {
             'id': sample_id,
             'title': title,
-            'url': mp3_url,
+            'formats': [{
+                'url': mp3_url,
+                'ext': 'mp3',
+                'vcodec': 'none',
+                'acodec': 'mp3',
+                'http_headers': {
+                    'Referer': url,
+                },
+            }],
             'display_id': display_id,
             'thumbnail': thumbnail,
             'uploader': uploader,

yt_dlp/extractor/screenrec.py

@@ -0,0 +1,33 @@
+from .common import InfoExtractor
+
+
+class ScreenRecIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?screenrec\.com/share/(?P<id>\w{10})'
+    _TESTS = [{
+        'url': 'https://screenrec.com/share/DasLtbknYo',
+        'info_dict': {
+            'id': 'DasLtbknYo',
+            'ext': 'mp4',
+            'title': '02.05.2024_03.01.25_REC',
+            'description': 'Recorded with ScreenRec',
+            'thumbnail': r're:^https?://.*\.gif$',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        m3u8_url = self._search_regex(
+            r'customUrl\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 URL', group='url')
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage, default=None) or self._html_extract_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4'),
+        }

yt_dlp/extractor/sen.py

@@ -0,0 +1,36 @@
+from .common import InfoExtractor
+from ..utils import url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class SenIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sen\.com/video/(?P<id>[0-9a-f-]+)'
+    _TEST = {
+        'url': 'https://www.sen.com/video/eef46eb1-4d79-4e28-be9d-bd937767f8c4',
+        'md5': 'ff615aca9691053c94f8f10d96cd7884',
+        'info_dict': {
+            'id': 'eef46eb1-4d79-4e28-be9d-bd937767f8c4',
+            'ext': 'mp4',
+            'description': 'Florida, 28 Sep 2022',
+            'title': 'Hurricane Ian',
+            'tags': ['North America', 'Storm', 'Weather'],
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        api_data = self._download_json(f'https://api.sen.com/content/public/video/{video_id}', video_id)
+        m3u8_url = (traverse_obj(api_data, (
+            'data', 'nodes', lambda _, v: v['id'] == 'player', 'video', 'url', {url_or_none}, any))
+            or f'https://vod.sen.com/videos/{video_id}/manifest.m3u8')
+
+        return {
+            'id': video_id,
+            'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'),
+            **traverse_obj(api_data, ('data', 'nodes', lambda _, v: v['id'] == 'details', any, 'content', {
+                'title': ('title', 'text', {str}),
+                'description': ('descriptions', 0, 'text', {str}),
+                'tags': ('badges', ..., 'text', {str}),
+            })),
+        }

yt_dlp/extractor/servus.py

@@ -27,7 +27,7 @@ class ServusIE(InfoExtractor):
         'info_dict': {
             'id': 'AA-28BYCQNH92111',
             'ext': 'mp4',
-            'title': 'Klettersteige in den Alpen',
+            'title': 'Vie Ferrate - Klettersteige in den Alpen',
             'description': 'md5:25e47ddd83a009a0f9789ba18f2850ce',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 2823,
@@ -38,6 +38,7 @@ class ServusIE(InfoExtractor):
             'season_number': 11,
             'episode': 'Episode 8 - Vie Ferrate – Klettersteige in den Alpen',
             'episode_number': 8,
+            'categories': ['Bergwelten'],
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -71,8 +72,11 @@ class ServusIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url).upper()
 
+        webpage = self._download_webpage(url, video_id)
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False)
+
         video = self._download_json(
-            'https://api-player.redbull.com/stv/servus-tv?timeZone=Europe/Berlin',
+            'https://api-player.redbull.com/stv/servus-tv-playnet',
             video_id, 'Downloading video JSON', query={'videoId': video_id})
         if not video.get('videoUrl'):
             self._report_errors(video)
@@ -89,7 +93,7 @@ class ServusIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video.get('title'),
-            'description': self._get_description(video_id) or video.get('description'),
+            'description': self._get_description(next_data) or video.get('description'),
             'thumbnail': video.get('poster'),
             'duration': float_or_none(video.get('duration')),
             'timestamp': unified_timestamp(video.get('currentSunrise')),
@@ -100,16 +104,19 @@ class ServusIE(InfoExtractor):
             'episode_number': episode_number,
             'formats': formats,
             'subtitles': subtitles,
+            **traverse_obj(next_data, ('props', 'pageProps', 'data', {
+                'title': ('title', 'rendered', {str}),
+                'timestamp': ('stv_date', 'raw', {int}),
+                'duration': ('stv_duration', {float_or_none}),
+                'categories': ('category_names', ..., {str}),
+            })),
         }
 
-    def _get_description(self, video_id):
+    def _get_description(self, next_data):
-        info = self._download_json(
+        return join_nonempty(*traverse_obj(next_data, (
-            f'https://backend.servustv.com/wp-json/rbmh/v2/media_asset/aa_id/{video_id}?fieldset=page',
+            'props', 'pageProps', 'data',
-            video_id, fatal=False)
+            ('stv_short_description', 'stv_long_description'), {str},
-
+            {lambda x: x.replace('\n\n', '\n')}, {unescapeHTML})), delim='\n\n')
-        return join_nonempty(*traverse_obj(info, (
-            ('stv_short_description', 'stv_long_description'),
-            {lambda x: unescapeHTML(x.replace('\n\n', '\n'))})), delim='\n\n')
 
     def _report_errors(self, video):
         playability_errors = traverse_obj(video, ('playabilityErrors', ...))

yt_dlp/extractor/snapchat.py

@@ -0,0 +1,76 @@
+from .common import InfoExtractor
+from ..utils import float_or_none, int_or_none, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class SnapchatSpotlightIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?snapchat\.com/spotlight/(?P<id>\w+)'
+
+    _TESTS = [{
+        'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA',
+        'md5': '46c580f63592d0cbb76e974d2f9f0fcc',
+        'info_dict': {
+            'id': 'W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA',
+            'ext': 'mp4',
+            'title': 'Views 💕',
+            'description': '',
+            'thumbnail': r're:https://cf-st\.sc-cdn\.net/d/kKJHIR1QAznRKK9jgYYDq\.256\.IRZXSOY',
+            'duration': 4.665,
+            'timestamp': 1637777831.369,
+            'upload_date': '20211124',
+            'repost_count': int,
+            'uploader': 'shreypatel57',
+            'uploader_url': 'https://www.snapchat.com/add/shreypatel57',
+        },
+    }, {
+        'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ',
+        'md5': '4cd9626458c1a0e3e6dbe72c544a9ec2',
+        'info_dict': {
+            'id': 'W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ',
+            'ext': 'mp4',
+            'title': 'Spotlight Snap',
+            'description': 'How he flirt her teacher🤭🤭🤩😍 #kdrama#cdrama #dramaclips #dramaspotlight',
+            'thumbnail': r're:https://cf-st\.sc-cdn\.net/i/ztfr6xFs0FOcFhwVczWfj\.256\.IRZXSOY',
+            'duration': 10.91,
+            'timestamp': 1722720291.307,
+            'upload_date': '20240803',
+            'view_count': int,
+            'repost_count': int,
+            'uploader': 'ganda0535',
+            'uploader_url': 'https://www.snapchat.com/add/ganda0535',
+            'tags': ['#dramaspotlight', '#dramaclips', '#cdrama', '#kdrama'],
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
+        video_data = traverse_obj(page_props, (
+            'spotlightFeed', 'spotlightStories',
+            lambda _, v: v['story']['storyId']['value'] == video_id, 'metadata', any), None)
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            **traverse_obj(video_data, ('videoMetadata', {
+                'title': ('name', {str}),
+                'description': ('description', {str}),
+                'timestamp': ('uploadDateMs', {lambda x: float_or_none(x, 1000)}),
+                'view_count': ('viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
+                'repost_count': ('shareCount', {int_or_none}),
+                'url': ('contentUrl', {url_or_none}),
+                'width': ('width', {int_or_none}),
+                'height': ('height', {int_or_none}),
+                'duration': ('durationMs', {lambda x: float_or_none(x, 1000)}),
+                'thumbnail': ('thumbnailUrl', {url_or_none}),
+                'uploader': ('creator', 'personCreator', 'username', {str}),
+                'uploader_url': ('creator', 'personCreator', 'url', {url_or_none}),
+            })),
+            **traverse_obj(video_data, {
+                'description': ('description', {str}),
+                'tags': ('hashtags', ..., {str}),
+                'view_count': ('engagementStats', 'viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
+                'repost_count': ('engagementStats', 'shareCount', {int_or_none}),
+            }),
+        }

yt_dlp/extractor/svt.py

@@ -472,7 +472,7 @@ class SVTPageIE(SVTBaseIE):
         title = self._og_search_title(webpage)
 
         urql_state = self._search_json(
-            r'window\.svt\.nyh\.urqlState\s*=', webpage, 'json data', display_id)
+            r'window\.svt\.(?:nyh\.)?urqlState\s*=', webpage, 'json data', display_id)
 
         data = traverse_obj(urql_state, (..., 'data', {str}, {json.loads}), get_all=False) or {}
 

yt_dlp/extractor/tele13.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class Tele13IE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
     _TESTS = [
         {
             'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',

yt_dlp/extractor/tenplay.py

@@ -1,33 +1,31 @@
-import base64
-import datetime as dt
 import functools
 import itertools
 
 from .common import InfoExtractor
 from ..networking import HEADRequest
-from ..utils import int_or_none, traverse_obj, urlencode_postdata, urljoin
+from ..utils import int_or_none, traverse_obj, url_or_none, urljoin
 
 
 class TenPlayIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?P<id>tpv\d{6}[a-z]{5})'
     _NETRC_MACHINE = '10play'
     _TESTS = [{
-        'url': 'https://10play.com.au/neighbours/web-extras/season-39/nathan-borg-is-the-first-aussie-actor-with-a-cochlear-implant-to-join-neighbours/tpv210128qupwd',
+        'url': 'https://10play.com.au/neighbours/web-extras/season-41/heres-a-first-look-at-mischa-bartons-neighbours-debut/tpv230911hyxnz',
         'info_dict': {
-            'id': '6226844312001',
+            'id': '6336940246112',
             'ext': 'mp4',
-            'title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours',
+            'title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut',
-            'alt_title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours',
+            'alt_title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut',
-            'description': 'md5:a02d0199c901c2dd4c796f1e7dd0de43',
+            'description': 'Neighbours Premieres Monday, September 18 At 4:30pm On 10 And 10 Play And 6:30pm On 10 Peach',
-            'duration': 186,
+            'duration': 74,
-            'season': 'Season 39',
+            'season': 'Season 41',
-            'season_number': 39,
+            'season_number': 41,
             'series': 'Neighbours',
             'thumbnail': r're:https://.*\.jpg',
             'uploader': 'Channel 10',
             'age_limit': 15,
-            'timestamp': 1611810000,
+            'timestamp': 1694386800,
-            'upload_date': '20210128',
+            'upload_date': '20230910',
             'uploader_id': '2199827728001',
         },
         'params': {
@@ -35,21 +33,30 @@ class TenPlayIE(InfoExtractor):
         },
         'skip': 'Only available in Australia',
     }, {
-        'url': 'https://10play.com.au/todd-sampsons-body-hack/episodes/season-4/episode-7/tpv200921kvngh',
+        'url': 'https://10play.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
         'info_dict': {
-            'id': '6192880312001',
+            'id': '9000000000091177',
             'ext': 'mp4',
-            'title': "Todd Sampson's Body Hack - S4 Ep. 2",
+            'title': 'Neighbours - S42 Ep. 9107',
-            'description': 'md5:fa278820ad90f08ea187f9458316ac74',
+            'alt_title': 'Thu 05 Sep',
+            'description': 'md5:37a1f4271be34b9ee2b533426a5fbaef',
+            'duration': 1388,
+            'episode': 'Episode 9107',
+            'episode_number': 9107,
+            'season': 'Season 42',
+            'season_number': 42,
+            'series': 'Neighbours',
+            'thumbnail': r're:https://.*\.jpg',
             'age_limit': 15,
-            'timestamp': 1600770600,
+            'timestamp': 1725517860,
-            'upload_date': '20200922',
+            'upload_date': '20240905',
             'uploader': 'Channel 10',
             'uploader_id': '2199827728001',
         },
         'params': {
             'skip_download': True,
         },
+        'skip': 'Only available in Australia',
     }, {
         'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
         'only_matching': True,
@@ -66,55 +73,42 @@ class TenPlayIE(InfoExtractor):
         'X': 18,
     }
 
-    def _get_bearer_token(self, video_id):
-        username, password = self._get_login_info()
-        if username is None or password is None:
-            self.raise_login_required('Your 10play account\'s details must be provided with --username and --password.')
-        _timestamp = dt.datetime.now().strftime('%Y%m%d000000')
-        _auth_header = base64.b64encode(_timestamp.encode('ascii')).decode('ascii')
-        data = self._download_json('https://10play.com.au/api/user/auth', video_id, 'Getting bearer token', headers={
-            'X-Network-Ten-Auth': _auth_header,
-        }, data=urlencode_postdata({
-            'email': username,
-            'password': password,
-        }))
-        return 'Bearer ' + data['jwt']['accessToken']
-
     def _real_extract(self, url):
         content_id = self._match_id(url)
         data = self._download_json(
             'https://10play.com.au/api/v1/videos/' + content_id, content_id)
-        headers = {}
 
-        if data.get('memberGated') is True:
+        video_data = self._download_json(
-            _token = self._get_bearer_token(content_id)
+            f'https://vod.ten.com.au/api/videos/bcquery?command=find_videos_by_id&video_id={data["altId"]}',
-            headers = {'Authorization': _token}
+            content_id, 'Downloading video JSON')
-
+        m3u8_url = self._request_webpage(
-        _video_url = self._download_json(
+            HEADRequest(video_data['items'][0]['HLSURL']),
-            data.get('playbackApiEndpoint'), content_id, 'Downloading video JSON',
+            content_id, 'Checking stream URL').url
-            headers=headers).get('source')
-        m3u8_url = self._request_webpage(HEADRequest(
-            _video_url), content_id).url
         if '10play-not-in-oz' in m3u8_url:
             self.raise_geo_restricted(countries=['AU'])
+        # Attempt to get a higher quality stream
+        m3u8_url = m3u8_url.replace(',150,75,55,0000', ',300,150,75,55,0000')
         formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4')
 
         return {
+            'id': content_id,
             'formats': formats,
-            'subtitles': {'en': [{'url': data.get('captionUrl')}]} if data.get('captionUrl') else None,
+            'subtitles': {'en': [{'url': data['captionUrl']}]} if url_or_none(data.get('captionUrl')) else None,
-            'id': data.get('altId') or content_id,
-            'duration': data.get('duration'),
-            'title': data.get('subtitle'),
-            'alt_title': data.get('title'),
-            'description': data.get('description'),
-            'age_limit': self._AUS_AGES.get(data.get('classification')),
-            'series': data.get('tvShow'),
-            'season_number': int_or_none(data.get('season')),
-            'episode_number': int_or_none(data.get('episode')),
-            'timestamp': data.get('published'),
-            'thumbnail': data.get('imageUrl'),
             'uploader': 'Channel 10',
             'uploader_id': '2199827728001',
+            **traverse_obj(data, {
+                'id': ('altId', {str}),
+                'duration': ('duration', {int_or_none}),
+                'title': ('subtitle', {str}),
+                'alt_title': ('title', {str}),
+                'description': ('description', {str}),
+                'age_limit': ('classification', {self._AUS_AGES.get}),
+                'series': ('tvShow', {str}),
+                'season_number': ('season', {int_or_none}),
+                'episode_number': ('episode', {int_or_none}),
+                'timestamp': ('published', {int_or_none}),
+                'thumbnail': ('imageUrl', {url_or_none}),
+            }),
         }
 
 

yt_dlp/extractor/tiktok.py

@@ -23,7 +23,6 @@ from ..utils import (
     mimetype2ext,
     parse_qs,
     qualities,
-    remove_start,
     srt_subtitles_timecode,
     str_or_none,
     traverse_obj,
@@ -254,7 +253,16 @@ class TikTokBaseIE(InfoExtractor):
 
     def _get_subtitles(self, aweme_detail, aweme_id, user_name):
         # TODO: Extract text positioning info
+
+        EXT_MAP = {  # From lowest to highest preference
+            'creator_caption': 'json',
+            'srt': 'srt',
+            'webvtt': 'vtt',
+        }
+        preference = qualities(tuple(EXT_MAP.values()))
+
         subtitles = {}
+
         # aweme/detail endpoint subs
         captions_info = traverse_obj(
             aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict)
@@ -278,8 +286,8 @@ class TikTokBaseIE(InfoExtractor):
                 if not caption.get('url'):
                     continue
                 subtitles.setdefault(caption.get('lang') or 'en', []).append({
-                    'ext': remove_start(caption.get('caption_format'), 'web'),
                     'url': caption['url'],
+                    'ext': EXT_MAP.get(caption.get('Format')),
                 })
         # webpage subs
         if not subtitles:
@@ -288,9 +296,14 @@ class TikTokBaseIE(InfoExtractor):
                     self._create_url(user_name, aweme_id), aweme_id, fatal=False)
             for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', lambda _, v: v['Url'])):
                 subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({
-                    'ext': remove_start(caption.get('Format'), 'web'),
                     'url': caption['Url'],
+                    'ext': EXT_MAP.get(caption.get('Format')),
                 })
+
+        # Deprioritize creator_caption json since it can't be embedded or used by media players
+        for lang, subs_list in subtitles.items():
+            subtitles[lang] = sorted(subs_list, key=lambda x: preference(x['ext']))
+
         return subtitles
 
     def _parse_url_key(self, url_key):
@@ -529,16 +542,12 @@ class TikTokBaseIE(InfoExtractor):
                 **COMMON_FORMAT_INFO,
                 'format_id': 'download',
                 'url': self._proto_relative_url(download_url),
+                'format_note': 'watermarked',
+                'preference': -2,
             })
 
         self._remove_duplicate_formats(formats)
 
-        for f in traverse_obj(formats, lambda _, v: 'unwatermarked' not in v['url']):
-            f.update({
-                'format_note': join_nonempty(f.get('format_note'), 'watermarked', delim=', '),
-                'preference': f.get('preference') or -2,
-            })
-
         # Is it a slideshow with only audio for download?
         if not formats and traverse_obj(aweme_detail, ('music', 'playUrl', {url_or_none})):
             audio_url = aweme_detail['music']['playUrl']
@@ -552,7 +561,8 @@ class TikTokBaseIE(InfoExtractor):
                 'vcodec': 'none',
             })
 
-        return formats
+        # Filter out broken formats, see https://github.com/yt-dlp/yt-dlp/issues/11034
+        return [f for f in formats if urllib.parse.urlparse(f['url']).hostname != 'www.tiktok.com']
 
     def _parse_aweme_video_web(self, aweme_detail, webpage_url, video_id, extract_flat=False):
         author_info = traverse_obj(aweme_detail, (('authorInfo', 'author', None), {

yt_dlp/extractor/tva.py

@@ -1,60 +1,29 @@
 import functools
 import re
 
+from .brightcove import BrightcoveNewIE
 from .common import InfoExtractor
 from ..utils import float_or_none, int_or_none, smuggle_url, strip_or_none
 from ..utils.traversal import traverse_obj
 
 
 class TVAIE(InfoExtractor):
-    _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)'
+    IE_NAME = 'tvaplus'
+    IE_DESC = 'TVA+'
+    _VALID_URL = r'https?://(?:www\.)?tvaplus\.ca/(?:[^/?#]+/)*[\w-]+-(?P<id>\d+)(?:$|[#?])'
     _TESTS = [{
-        'url': 'https://videos.tva.ca/details/_5596811470001',
+        'url': 'https://www.tvaplus.ca/tva/alerte-amber/saison-1/episode-01-1000036619',
-        'info_dict': {
-            'id': '5596811470001',
-            'ext': 'mp4',
-            'title': 'Un extrait de l\'épisode du dimanche 8 octobre 2017 !',
-            'uploader_id': '5481942443001',
-            'upload_date': '20171003',
-            'timestamp': 1507064617,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'skip': 'HTTP Error 404: Not Found',
-    }, {
-        'url': 'https://video.tva.ca/details/_5596811470001',
-        'only_matching': True,
-    }]
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['CA']}),
-            'ie_key': 'BrightcoveNew',
-        }
-
-
-class QubIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?qub\.ca/(?:[^/]+/)*[0-9a-z-]+-(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.qub.ca/tvaplus/tva/alerte-amber/saison-1/episode-01-1000036619',
         'md5': '949490fd0e7aee11d0543777611fbd53',
         'info_dict': {
             'id': '6084352463001',
             'ext': 'mp4',
-            'title': 'Ép 01. Mon dernier jour',
+            'title': 'Mon dernier jour',
             'uploader_id': '5481942443001',
             'upload_date': '20190907',
             'timestamp': 1567899756,
             'description': 'md5:9c0d7fbb90939420c651fd977df90145',
             'thumbnail': r're:https://.+\.jpg',
-            'episode': 'Ép 01. Mon dernier jour',
+            'episode': 'Mon dernier jour',
             'episode_number': 1,
             'tags': ['alerte amber', 'alerte amber saison 1', 'surdemande'],
             'duration': 2625.963,
@@ -64,23 +33,36 @@ class QubIE(InfoExtractor):
             'channel': 'TVA',
         },
     }, {
-        'url': 'https://www.qub.ca/tele/video/lcn-ca-vous-regarde-rev-30s-ap369664-1009357943',
+        'url': 'https://www.tvaplus.ca/tva/le-baiser-du-barbu/le-baiser-du-barbu-886644190',
-        'only_matching': True,
+        'info_dict': {
+            'id': '6354448043112',
+            'ext': 'mp4',
+            'title': 'Le Baiser du barbu',
+            'uploader_id': '5481942443001',
+            'upload_date': '20240606',
+            'timestamp': 1717694023,
+            'description': 'md5:025b1219086c1cbf4bc27e4e034e8b57',
+            'thumbnail': r're:https://.+\.jpg',
+            'episode': 'Le Baiser du barbu',
+            'tags': ['fullepisode', 'films'],
+            'duration': 6053.504,
+            'series': 'Le Baiser du barbu',
+            'channel': 'TVA',
+        },
     }]
-    # reference_id also works with old account_id(5481942443001)
+    _BC_URL_TMPL = 'https://players.brightcove.net/5481942443001/default_default/index.html?videoId={}'
-    # BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5813221784001/default_default/index.html?videoId=ref:%s'
 
     def _real_extract(self, url):
         entity_id = self._match_id(url)
         webpage = self._download_webpage(url, entity_id)
-        entity = self._search_nextjs_data(webpage, entity_id)['props']['initialProps']['pageProps']['fallbackData']
+        entity = self._search_nextjs_data(webpage, entity_id)['props']['pageProps']['staticEntity']
         video_id = entity['videoId']
         episode = strip_or_none(entity.get('name'))
 
         return {
             '_type': 'url_transparent',
-            'url': f'https://videos.tva.ca/details/_{video_id}',
+            'url': smuggle_url(self._BC_URL_TMPL.format(video_id), {'geo_countries': ['CA']}),
-            'ie_key': TVAIE.ie_key(),
+            'ie_key': BrightcoveNewIE.ie_key(),
             'id': video_id,
             'title': episode,
             'episode': episode,

yt_dlp/extractor/tver.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class TVerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video)/)+(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video|olympic/paris2024/video)/)+(?P<id>[a-zA-Z0-9]+)'
     _TESTS = [{
         'skip': 'videos are only available for 7 days',
         'url': 'https://tver.jp/episodes/ep83nf3w4p',
@@ -23,6 +23,20 @@ class TVerIE(InfoExtractor):
             'channel': 'テレビ朝日',
         },
         'add_ie': ['BrightcoveNew'],
+    }, {
+        'url': 'https://tver.jp/olympic/paris2024/video/6359578055112/',
+        'info_dict': {
+            'id': '6359578055112',
+            'ext': 'mp4',
+            'title': '堀米雄斗 金メダルで五輪連覇！「みんなの応援が最後に乗れたカギ」',
+            'timestamp': 1722279928,
+            'upload_date': '20240729',
+            'tags': ['20240729', 'japanese', 'japanmedal', 'paris'],
+            'uploader_id': '4774017240001',
+            'thumbnail': r're:https?://[^/?#]+boltdns\.net/[^?#]+/1920x1080/match/image\.jpg',
+            'duration': 670.571,
+        },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://tver.jp/corner/f0103888',
         'only_matching': True,
@@ -47,7 +61,15 @@ class TVerIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, video_type = self._match_valid_url(url).group('id', 'type')
-        if video_type not in {'series', 'episodes'}:
+
+        if video_type == 'olympic/paris2024/video':
+            # Player ID is taken from .content.brightcove.E200.pro.pc.account_id:
+            # https://tver.jp/olympic/paris2024/req/api/hook?q=https%3A%2F%2Folympic-assets.tver.jp%2Fweb-static%2Fjson%2Fconfig.json&d=
+            return self.url_result(smuggle_url(
+                self.BRIGHTCOVE_URL_TEMPLATE % ('4774017240001', video_id),
+                {'geo_countries': ['JP']}), 'BrightcoveNew')
+
+        elif video_type not in {'series', 'episodes'}:
             webpage = self._download_webpage(url, video_id, note='Resolving to new URL')
             video_id = self._match_id(self._search_regex(
                 (r'canonical"\s*href="(https?://tver\.jp/[^"]+)"', r'&link=(https?://tver\.jp/[^?&]+)[?&]'),

yt_dlp/extractor/tvn24.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 class TVN24IE(InfoExtractor):
     _WORKING = False
-    _VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:(?!eurosport)[^/]+\.)?tvn24(?:bis)?\.pl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html',
         'md5': 'fbdec753d7bc29d96036808275f2130c',

yt_dlp/extractor/twitcasting.py

@@ -270,7 +270,7 @@ class TwitCastingLiveIE(InfoExtractor):
 
 
 class TwitCastingUserIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/?#]+\.)?twitcasting\.tv/(?P<id>[^/?#]+)/(:?show|archive)/?(?:[#?]|$)'
+    _VALID_URL = r'https?://(?:[^/?#]+\.)?twitcasting\.tv/(?P<id>[^/?#]+)/(?:show|archive)/?(?:[#?]|$)'
     _TESTS = [{
         'url': 'https://twitcasting.tv/natsuiromatsuri/archive/',
         'info_dict': {

yt_dlp/extractor/twitter.py

@@ -1764,7 +1764,7 @@ class TwitterSpacesIE(TwitterBaseIE):
             'release_timestamp': 1659904215,
             'release_date': '20220807',
         },
-        'params': {'skip_download': 'm3u8'},
+        'skip': 'No longer available',
     }, {
         # post_live/TimedOut but downloadable
         'url': 'https://twitter.com/i/spaces/1vAxRAVQWONJl',
@@ -1780,6 +1780,8 @@ class TwitterSpacesIE(TwitterBaseIE):
             'upload_date': '20230413',
             'release_timestamp': 1681839000,
             'release_date': '20230418',
+            'protocol': 'm3u8',  # ffmpeg is forced
+            'container': 'm4a_dash',  # audio-only format fixup is applied
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -1790,11 +1792,31 @@ class TwitterSpacesIE(TwitterBaseIE):
             'ext': 'm4a',
             'title': 'あ',
             'description': 'Twitter Space participated by nobody yet',
-            'uploader': '息根とめる🔪Twitchで復活',
+            'uploader': '息根とめる',
             'uploader_id': 'tomeru_ikinone',
             'live_status': 'was_live',
             'timestamp': 1685617198,
             'upload_date': '20230601',
+            'protocol': 'm3u8',  # ffmpeg is forced
+            'container': 'm4a_dash',  # audio-only format fixup is applied
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        # Video Space
+        'url': 'https://x.com/i/spaces/1DXGydznBYWKM',
+        'info_dict': {
+            'id': '1DXGydznBYWKM',
+            'ext': 'mp4',
+            'title': 'America and Israel’s “special relationship”',
+            'description': 'Twitter Space participated by nobody yet',
+            'uploader': 'Candace Owens',
+            'uploader_id': 'RealCandaceO',
+            'live_status': 'was_live',
+            'timestamp': 1723931351,
+            'upload_date': '20240817',
+            'release_timestamp': 1723932000,
+            'release_date': '20240817',
+            'protocol': 'm3u8_native',  # not ffmpeg, detected as video space
         },
         'params': {'skip_download': 'm3u8'},
     }]
@@ -1854,13 +1876,17 @@ class TwitterSpacesIE(TwitterBaseIE):
             source = traverse_obj(
                 self._call_api(f'live_video_stream/status/{metadata["media_key"]}', metadata['media_key']),
                 ('source', ('noRedirectPlaybackUrl', 'location'), {url_or_none}), get_all=False)
-            formats = self._extract_m3u8_formats(  # XXX: Some Spaces need ffmpeg as downloader
+            is_audio_space = source and 'audio-space' in source
-                source, metadata['media_key'], 'm4a', entry_protocol='m3u8', live=is_live,
+            formats = self._extract_m3u8_formats(
-                headers=headers, fatal=False) if source else []
+                source, metadata['media_key'], 'm4a' if is_audio_space else 'mp4',
-            for fmt in formats:
+                # XXX: Some audio-only Spaces need ffmpeg as downloader
-                fmt.update({'vcodec': 'none', 'acodec': 'aac'})
+                entry_protocol='m3u8' if is_audio_space else 'm3u8_native',
-                if not is_live:
+                live=is_live, headers=headers, fatal=False) if source else []
-                    fmt['container'] = 'm4a_dash'
+            if is_audio_space:
+                for fmt in formats:
+                    fmt.update({'vcodec': 'none', 'acodec': 'aac'})
+                    if not is_live:
+                        fmt['container'] = 'm4a_dash'
 
         participants = ', '.join(traverse_obj(
             space_data, ('participants', 'speakers', ..., 'display_name'))) or 'nobody yet'

yt_dlp/extractor/unsupported.py

@@ -49,6 +49,7 @@ class KnownDRMIE(UnsupportedInfoExtractor):
         r'amazon\.(?:\w{2}\.)?\w+/gp/video',
         r'music\.amazon\.(?:\w{2}\.)?\w+',
         r'(?:watch|front)\.njpwworld\.com',
+        r'qub\.ca/vrai',
     )
 
     _TESTS = [{
@@ -149,6 +150,9 @@ class KnownDRMIE(UnsupportedInfoExtractor):
     }, {
         'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
         'only_matching': True,
+    }, {
+        'url': 'https://www.qub.ca/vrai/l-effet-bocuse-d-or/saison-1/l-effet-bocuse-d-or-saison-1-bande-annonce-1098225063',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/vidflex.py

@@ -0,0 +1,148 @@
+import base64
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    join_nonempty,
+    mimetype2ext,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class VidflexIE(InfoExtractor):
+    _DOMAINS_RE = [
+        r'[^.]+\.vidflex\.tv',
+        r'(?:www\.)?acactv\.ca',
+        r'(?:www\.)?albertalacrossetv\.com',
+        r'(?:www\.)?cjfltv\.com',
+        r'(?:www\.)?figureitoutbaseball\.com',
+        r'(?:www\.)?ocaalive\.com',
+        r'(?:www\.)?pegasussports\.tv',
+        r'(?:www\.)?praxisseries\.ca',
+        r'(?:www\.)?silenticetv\.com',
+        r'(?:www\.)?tuffhedemantv\.com',
+        r'(?:www\.)?watchfuntv\.com',
+        r'live\.ofsaa\.on\.ca',
+        r'tv\.procoro\.ca',
+        r'tv\.realcastmedia\.net',
+        r'tv\.fringetheatre\.ca',
+        r'video\.haisla\.ca',
+        r'video\.hockeycanada\.ca',
+        r'video\.huuayaht\.org',
+        r'video\.turningpointensemble\.ca',
+        r'videos\.livingworks\.net',
+        r'videos\.telusworldofscienceedmonton\.ca',
+        r'watch\.binghamtonbulldogs\.com',
+        r'watch\.rekindle\.tv',
+        r'watch\.wpca\.com',
+    ]
+    _VALID_URL = rf'https?://(?:{"|".join(_DOMAINS_RE)})/[a-z]{{2}}(?:-[a-z]{{2}})?/c/[\w-]+\.(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://video.hockeycanada.ca/en/c/nwt-micd-up-with-jamie-lee-rattray.107486',
+        'only_matching': True,
+    }, {
+        # m3u8 + https
+        'url': 'https://video.hockeycanada.ca/en-us/c/nwt-micd-up-with-jamie-lee-rattray.107486',
+        'info_dict': {
+            'id': '107486',
+            'title': 'NWT: Mic’d up with Jamie Lee Rattray',
+            'ext': 'mp4',
+            'duration': 115,
+            'timestamp': 1634310409,
+            'upload_date': '20211015',
+            'tags': ['English', '2021', "National Women's Team"],
+            'description': 'md5:efb1cf6165b48cc3f5555c4262dd5b23',
+            'thumbnail': r're:^https?://wpmedia01-a\.akamaihd\.net/en/asset/public/image/.+',
+        },
+        'params': {'skip_download': True},
+    }, {
+        'url': 'https://video.hockeycanada.ca/en/c/mwc-remembering-the-wild-ride-in-riga.112307',
+        'info_dict': {
+            'id': '112307',
+            'title': 'MWC: Remembering the wild ride in Riga',
+            'ext': 'mp4',
+            'duration': 322,
+            'timestamp': 1716235607,
+            'upload_date': '20240520',
+            'tags': ['English', '2024', "National Men's Team", 'IIHF World Championship', 'Fan'],
+            'description': r're:.+Canada’s National Men’s Team.+',
+            'thumbnail': r're:^https?://wpmedia01-a\.akamaihd\.net/en/asset/public/image/.+',
+        },
+        'params': {'skip_download': True},
+    }, {
+        # the same video in French
+        'url': 'https://video.hockeycanada.ca/fr/c/cmm-retour-sur-un-parcours-endiable-a-riga.112304',
+        'info_dict': {
+            'id': '112304',
+            'title': 'CMM : Retour sur un parcours endiablé à Riga',
+            'ext': 'mp4',
+            'duration': 322,
+            'timestamp': 1716235545,
+            'upload_date': '20240520',
+            'tags': ['French', '2024', "National Men's Team", 'IIHF World Championship', 'Fan'],
+            'description': 'md5:cf825222882a3dab1cd62cffcf3b4d1f',
+            'thumbnail': r're:^https?://wpmedia01-a\.akamaihd\.net/en/asset/public/image/.+',
+        },
+        'params': {'skip_download': True},
+    }, {
+        'url': 'https://myfbcgreenville.vidflex.tv/en/c/may-12th-2024.658',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.figureitoutbaseball.com/en/c/fiob-podcast-14-dan-bertolini-ncaa-d1-head-coach-recorded-11-29-2018.1367',
+        'only_matching': True,
+    }, {
+        'url': 'https://videos.telusworldofscienceedmonton.ca/en/c/the-aurora-project-timelapse-4.577',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tuffhedemantv.com/en/c/2022-tuff-hedeman-tour-hobbs-nm-january-22.227',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.albertalacrossetv.com/en/c/up-floor-ground-balls-one-more.3449',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.silenticetv.com/en/c/jp-unlocked-day-in-the-life-of-langley-ha-15u.5197',
+        'only_matching': True,
+    }, {
+        'url': 'https://jphl.vidflex.tv/en/c/jp-unlocked-day-in-the-life-of-langley-ha-15u.5197',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        data_url = self._html_search_regex(
+            r'content_api:\s*(["\'])(?P<url>https?://(?:(?!\1).)+)\1', webpage, 'content api url', group='url')
+        media_config = traverse_obj(
+            self._download_json(data_url, video_id),
+            ('config', {base64.b64decode}, {bytes.decode}, {json.loads}, {dict}))
+
+        return {
+            'id': video_id,
+            'formats': list(self._yield_formats(media_config, video_id)),
+            **self._search_json_ld(
+                webpage.replace('/*<![CDATA[*/', '').replace('/*]]>*/', ''), video_id),
+        }
+
+    def _yield_formats(self, media_config, video_id):
+        for media_source in traverse_obj(media_config, ('media', 'source', lambda _, v: url_or_none(v['src']))):
+            media_url = media_source['src']
+            media_type = mimetype2ext(media_source.get('type'))
+
+            if media_type == 'm3u8':
+                yield from self._extract_m3u8_formats(media_url, video_id, fatal=False, m3u8_id='hls')
+            elif media_type == 'mp4':
+                bitrate = self._search_regex(r'_(\d+)k\.mp4', media_url, 'bitrate', default=None)
+                yield {
+                    'format_id': join_nonempty('http', bitrate),
+                    'url': media_url,
+                    'ext': 'mp4',
+                    'tbr': int_or_none(bitrate),
+                }
+            else:
+                yield {
+                    'url': media_url,
+                    'ext': media_type,
+                }