mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-19 14:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into pr/6498

Browse source
This commit is contained in:
bashonly 2023-07-22 13:23:54 -05:00
parent 1416cee726 11de6fec9c
commit 194bc49c55
No known key found for this signature in database
GPG key ID: 783F096F253D15B0
226 changed files with 6016 additions and 2405 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
.github/ISSUE_TEMPLATE/1_broken_site.yml vendored
View file

@ -18,7 +18,7 @@ body:
options:
- label: I'm reporting that yt-dlp is broken on a **supported** site
required: true
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
required: true
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
required: true
@ -64,7 +64,7 @@ body:
[debug] Command-line config: ['-vU', 'test:youtube']
[debug] Portable config "yt-dlp.conf": ['-i']
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
[debug] Checking exe version: ffmpeg -bsfs
[debug] Checking exe version: ffprobe -bsfs
@ -72,8 +72,8 @@ body:
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
[debug] Proxy map: {}
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: 2023.06.22, Current version: 2023.06.22
yt-dlp is up to date (2023.06.22)
Latest version: 2023.07.06, Current version: 2023.07.06
yt-dlp is up to date (2023.07.06)
<more lines>
render: shell
validations:

8
.github/ISSUE_TEMPLATE/2_site_support_request.yml vendored
View file

@ -18,7 +18,7 @@ body:
options:
- label: I'm reporting a new site support request
required: true
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
required: true
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
required: true
@ -76,7 +76,7 @@ body:
[debug] Command-line config: ['-vU', 'test:youtube']
[debug] Portable config "yt-dlp.conf": ['-i']
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
[debug] Checking exe version: ffmpeg -bsfs
[debug] Checking exe version: ffprobe -bsfs
@ -84,8 +84,8 @@ body:
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
[debug] Proxy map: {}
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: 2023.06.22, Current version: 2023.06.22
yt-dlp is up to date (2023.06.22)
Latest version: 2023.07.06, Current version: 2023.07.06
yt-dlp is up to date (2023.07.06)
<more lines>
render: shell
validations:

8
.github/ISSUE_TEMPLATE/3_site_feature_request.yml vendored
View file

@ -18,7 +18,7 @@ body:
options:
- label: I'm requesting a site-specific feature
required: true
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
required: true
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
required: true
@ -72,7 +72,7 @@ body:
[debug] Command-line config: ['-vU', 'test:youtube']
[debug] Portable config "yt-dlp.conf": ['-i']
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
[debug] Checking exe version: ffmpeg -bsfs
[debug] Checking exe version: ffprobe -bsfs
@ -80,8 +80,8 @@ body:
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
[debug] Proxy map: {}
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: 2023.06.22, Current version: 2023.06.22
yt-dlp is up to date (2023.06.22)
Latest version: 2023.07.06, Current version: 2023.07.06
yt-dlp is up to date (2023.07.06)
<more lines>
render: shell
validations:

8
.github/ISSUE_TEMPLATE/4_bug_report.yml vendored
View file

@ -18,7 +18,7 @@ body:
options:
- label: I'm reporting a bug unrelated to a specific site
required: true
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
required: true
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
required: true
@ -57,7 +57,7 @@ body:
[debug] Command-line config: ['-vU', 'test:youtube']
[debug] Portable config "yt-dlp.conf": ['-i']
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
[debug] Checking exe version: ffmpeg -bsfs
[debug] Checking exe version: ffprobe -bsfs
@ -65,8 +65,8 @@ body:
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
[debug] Proxy map: {}
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: 2023.06.22, Current version: 2023.06.22
yt-dlp is up to date (2023.06.22)
Latest version: 2023.07.06, Current version: 2023.07.06
yt-dlp is up to date (2023.07.06)
<more lines>
render: shell
validations:

8
.github/ISSUE_TEMPLATE/5_feature_request.yml vendored
View file

@ -20,7 +20,7 @@ body:
required: true
- label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
required: true
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
required: true
- label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
required: true
@ -53,7 +53,7 @@ body:
[debug] Command-line config: ['-vU', 'test:youtube']
[debug] Portable config "yt-dlp.conf": ['-i']
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
[debug] Checking exe version: ffmpeg -bsfs
[debug] Checking exe version: ffprobe -bsfs
@ -61,7 +61,7 @@ body:
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
[debug] Proxy map: {}
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: 2023.06.22, Current version: 2023.06.22
yt-dlp is up to date (2023.06.22)
Latest version: 2023.07.06, Current version: 2023.07.06
yt-dlp is up to date (2023.07.06)
<more lines>
render: shell

8
.github/ISSUE_TEMPLATE/6_question.yml vendored
View file

@ -26,7 +26,7 @@ body:
required: true
- label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
required: true
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
required: true
- label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
required: true
@ -59,7 +59,7 @@ body:
[debug] Command-line config: ['-vU', 'test:youtube']
[debug] Portable config "yt-dlp.conf": ['-i']
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
[debug] Checking exe version: ffmpeg -bsfs
[debug] Checking exe version: ffprobe -bsfs
@ -67,7 +67,7 @@ body:
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
[debug] Proxy map: {}
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: 2023.06.22, Current version: 2023.06.22
yt-dlp is up to date (2023.06.22)
Latest version: 2023.07.06, Current version: 2023.07.06
yt-dlp is up to date (2023.07.06)
<more lines>
render: shell

65
.github/workflows/codeql.yml vendored Normal file
View file

@ -0,0 +1,65 @@
name: "CodeQL"
on:
push:
branches: [ 'master', 'gh-pages', 'release' ]
pull_request:
# The branches below must be a subset of the branches above
branches: [ 'master' ]
schedule:
- cron: '59 11 * * 5'
jobs:
analyze:
name: Analyze
runs-on: ubuntu-latest
permissions:
actions: read
contents: read
security-events: write
strategy:
fail-fast: false
matrix:
language: [ 'python' ]
# CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
# Use only 'java' to analyze code written in Java, Kotlin or both
# Use only 'javascript' to analyze code written in JavaScript, TypeScript or both
# Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
steps:
- name: Checkout repository
uses: actions/checkout@v3
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v2
with:
languages: ${{ matrix.language }}
# If you wish to specify custom queries, you can do so here or in a config file.
# By default, queries listed here will override any specified in a config file.
# Prefix the list here with "+" to use these queries and those in the config file.
# For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
# queries: security-extended,security-and-quality
# Autobuild attempts to build any compiled languages (C/C++, C#, Go, Java, or Swift).
# If this step fails, then you should remove it and run the build manually (see below)
- name: Autobuild
uses: github/codeql-action/autobuild@v2
# ℹ️ Command-line programs to run using the OS shell.
# 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
# If the Autobuild fails above, remove it and uncomment the following three lines.
# modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
# - run: |
# echo "Run, Build Application using script"
# ./location_of_script_within_repo/buildscript.sh
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v2
with:
category: "/language:${{matrix.language}}"

7
CONTRIBUTORS
View file

@ -460,3 +460,10 @@ berkanteber
OverlordQ
rexlambert22
Ti4eeT4e
AmanSal1
bbilly1
meliber
nnoboa
rdamas
RfadnjdExt
urectanc

58
Changelog.md
View file

@ -4,11 +4,65 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2023.07.06
#### Important changes
- Security: [[CVE-2023-35934](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2023-35934)] Fix [Cookie leak](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj)
- `--add-header Cookie:` is deprecated and auto-scoped to input URL domains
- Cookies are scoped when passed to external downloaders
- Add `cookies` field to info.json and deprecate `http_headers.Cookie`
#### Core changes
- [Allow extractors to mark formats as potentially DRM](https://github.com/yt-dlp/yt-dlp/commit/bc344cd456380999c1ee74554dfd432a38f32ec7) ([#7396](https://github.com/yt-dlp/yt-dlp/issues/7396)) by [pukkandan](https://github.com/pukkandan)
- [Bugfix for b4e0d75848e9447cee2cd3646ce54d4744a7ff56](https://github.com/yt-dlp/yt-dlp/commit/e59e20744eb32ce4b6ea0dece7c673be8376a710) by [pukkandan](https://github.com/pukkandan)
- [Change how `Cookie` headers are handled](https://github.com/yt-dlp/yt-dlp/commit/3121512228487c9c690d3d39bfd2579addf96e07) by [Grub4K](https://github.com/Grub4K)
- [Prevent `Cookie` leaks on HTTP redirect](https://github.com/yt-dlp/yt-dlp/commit/f8b4bcc0a791274223723488bfbfc23ea3276641) by [coletdjnz](https://github.com/coletdjnz)
- **formats**: [Fix best fallback for storyboards](https://github.com/yt-dlp/yt-dlp/commit/906c0bdcd8974340d619e99ccd613c163eb0d0c2) by [pukkandan](https://github.com/pukkandan)
- **outtmpl**: [Pad `playlist_index` etc even when with internal formatting](https://github.com/yt-dlp/yt-dlp/commit/47bcd437247152e0af5b3ebc5592db7bb66855c2) by [pukkandan](https://github.com/pukkandan)
- **utils**: clean_podcast_url: [Handle protocol in redirect URL](https://github.com/yt-dlp/yt-dlp/commit/91302ed349f34dc26cc1d661bb45a4b71f4417f7) by [pukkandan](https://github.com/pukkandan)
#### Extractor changes
- **abc**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/8f05fbae2a79ce0713077ccc68b354e63216bf20) ([#7434](https://github.com/yt-dlp/yt-dlp/issues/7434)) by [meliber](https://github.com/meliber)
- **AdultSwim**: [Extract subtitles from m3u8](https://github.com/yt-dlp/yt-dlp/commit/5e16cf92eb496b7c1541a6b1d727cb87542984db) ([#7421](https://github.com/yt-dlp/yt-dlp/issues/7421)) by [nnoboa](https://github.com/nnoboa)
- **crunchyroll**: music: [Fix `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/5b4b92769afcc398475e481bfa839f1158902fe9) ([#7439](https://github.com/yt-dlp/yt-dlp/issues/7439)) by [AmanSal1](https://github.com/AmanSal1), [rdamas](https://github.com/rdamas)
- **Douyin**: [Fix extraction from webpage](https://github.com/yt-dlp/yt-dlp/commit/a2be9781fbf4d7e4db245c277ca2ecc41cf3a7b2) by [bashonly](https://github.com/bashonly)
- **googledrive**: [Fix source format extraction](https://github.com/yt-dlp/yt-dlp/commit/3b7f5300c577fef40464d46d4e4037a69d51fe82) ([#7395](https://github.com/yt-dlp/yt-dlp/issues/7395)) by [RfadnjdExt](https://github.com/RfadnjdExt)
- **kick**: [Fix `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/ef8509c300ea50da86aea447eb214d3d6f6db6bb) by [bashonly](https://github.com/bashonly)
- **qdance**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/f0a1ff118145b6449982ba401f9a9f656ecd8062) ([#7420](https://github.com/yt-dlp/yt-dlp/issues/7420)) by [bashonly](https://github.com/bashonly)
- **sbs**: [Python 3.7 compat](https://github.com/yt-dlp/yt-dlp/commit/f393bbe724b1fc6c7f754a5da507e807b2b40ad2) by [pukkandan](https://github.com/pukkandan)
- **stacommu**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/af1fd12f675220df6793fc019dff320bc76e8080) ([#7432](https://github.com/yt-dlp/yt-dlp/issues/7432)) by [urectanc](https://github.com/urectanc)
- **twitter**
- [Fix unauthenticated extraction](https://github.com/yt-dlp/yt-dlp/commit/49296437a8e5fa91dacb5446e51ab588474c85d3) ([#7476](https://github.com/yt-dlp/yt-dlp/issues/7476)) by [bashonly](https://github.com/bashonly)
- spaces: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1cffd621cb371f1563563cfb2fe37d137e8a7bee) ([#7512](https://github.com/yt-dlp/yt-dlp/issues/7512)) by [bashonly](https://github.com/bashonly)
- **vidlii**: [Handle relative URLs](https://github.com/yt-dlp/yt-dlp/commit/ad8902f616ad2541f9b9626738f1393fad89a64c) by [pukkandan](https://github.com/pukkandan)
- **vk**: VKPlay, VKPlayLive: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/8776349ef6b1f644584a92dfa00a05208a48edc4) ([#7358](https://github.com/yt-dlp/yt-dlp/issues/7358)) by [c-basalt](https://github.com/c-basalt)
- **youtube**
- [Add extractor-arg `formats`](https://github.com/yt-dlp/yt-dlp/commit/58786a10f212bd63f9ad1d0b4d9e4d31c3b385e2) by [pukkandan](https://github.com/pukkandan)
- [Avoid false DRM detection](https://github.com/yt-dlp/yt-dlp/commit/94ed638a437fc766699d440e978982e24ce6a30a) ([#7396](https://github.com/yt-dlp/yt-dlp/issues/7396)) by [pukkandan](https://github.com/pukkandan)
- [Fix comments' `is_favorited`](https://github.com/yt-dlp/yt-dlp/commit/89bed013741a776506f60380b7fd89d27d0710b4) ([#7390](https://github.com/yt-dlp/yt-dlp/issues/7390)) by [bbilly1](https://github.com/bbilly1)
- [Ignore incomplete data for comment threads by default](https://github.com/yt-dlp/yt-dlp/commit/4dc4d8473c085900edc841c87c20041233d25b1f) ([#7475](https://github.com/yt-dlp/yt-dlp/issues/7475)) by [coletdjnz](https://github.com/coletdjnz)
- [Process `post_live` over 2 hours](https://github.com/yt-dlp/yt-dlp/commit/d949c10c45bfc359bdacd52e6a180169b8128958) by [pukkandan](https://github.com/pukkandan)
- stories: [Remove](https://github.com/yt-dlp/yt-dlp/commit/90db9a3c00ca80492c6a58c542e4cbf4c2710866) ([#7459](https://github.com/yt-dlp/yt-dlp/issues/7459)) by [pukkandan](https://github.com/pukkandan)
- tab: [Support shorts-only playlists](https://github.com/yt-dlp/yt-dlp/commit/fcbc9ed760be6e3455bbadfaf277b4504b06f068) ([#7425](https://github.com/yt-dlp/yt-dlp/issues/7425)) by [coletdjnz](https://github.com/coletdjnz)
#### Downloader changes
- **aria2c**: [Add `--no-conf`](https://github.com/yt-dlp/yt-dlp/commit/8a8af356e3bba98a7f7d333aff0777d5d92130c8) by [pukkandan](https://github.com/pukkandan)
- **external**: [Scope cookies](https://github.com/yt-dlp/yt-dlp/commit/1ceb657bdd254ad961489e5060f2ccc7d556b729) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz)
- **http**: [Avoid infinite loop when no data is received](https://github.com/yt-dlp/yt-dlp/commit/662ef1e910b72e57957f06589925b2332ba52821) by [pukkandan](https://github.com/pukkandan)
#### Misc. changes
- [Add CodeQL workflow](https://github.com/yt-dlp/yt-dlp/commit/6355b5f1e1e8e7f4ef866d71d51e03baf0e82f17) ([#7497](https://github.com/yt-dlp/yt-dlp/issues/7497)) by [jorgectf](https://github.com/jorgectf)
- **cleanup**: Miscellaneous: [337734d](https://github.com/yt-dlp/yt-dlp/commit/337734d4a8a6500bc65434843db346b5cbd05e81) by [pukkandan](https://github.com/pukkandan)
- **docs**: [Minor fixes](https://github.com/yt-dlp/yt-dlp/commit/b532a3481046e1eabb6232ee8196fb696c356ff6) by [pukkandan](https://github.com/pukkandan)
- **make_changelog**: [Skip reverted commits](https://github.com/yt-dlp/yt-dlp/commit/fa44802809d189fca0f4782263d48d6533384503) by [pukkandan](https://github.com/pukkandan)
### 2023.06.22
#### Core changes
- [Fix bug in db3ad8a67661d7b234a6954d9c6a4a9b1749f5eb](https://github.com/yt-dlp/yt-dlp/commit/d7cd97e8d8d42b500fea9abb2aa4ac9b0f98b2ad) by [pukkandan](https://github.com/pukkandan)
- [Improve `--download-sections`](https://github.com/yt-dlp/yt-dlp/commit/b4e0d75848e9447cee2cd3646ce54d4744a7ff56) by [pukkandan](https://github.com/pukkandan)
- Support negative time-ranges
- Add `*from-url` to obey time-ranges in URL
- [Indicate `filesize` approximated from `tbr` better](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) by [pukkandan](https://github.com/pukkandan)
#### Extractor changes
@ -19,7 +73,7 @@ #### Extractor changes
- **nebula**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/3f756c8c4095b942cf49788eb0862ceaf57847f2) ([#7156](https://github.com/yt-dlp/yt-dlp/issues/7156)) by [Lamieur](https://github.com/Lamieur), [rohieb](https://github.com/rohieb)
- **rheinmaintv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/98cb1eda7a4cf67c96078980dbd63e6c06ad7f7c) ([#7311](https://github.com/yt-dlp/yt-dlp/issues/7311)) by [barthelmannk](https://github.com/barthelmannk)
- **youtube**
- [Add `ios` to default clients used](https://github.com/yt-dlp/yt-dlp/commit/1e75d97db21152acc764b30a688e516f04b8a142)
- [Add `ios` to default clients used](https://github.com/yt-dlp/yt-dlp/commit/1e75d97db21152acc764b30a688e516f04b8a142) by [pukkandan](https://github.com/pukkandan)
- IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively
- IOS also has higher bit-rate 'premium' formats though they are not labeled as such
- [Improve description parsing performance](https://github.com/yt-dlp/yt-dlp/commit/71dc18fa29263a1ff0472c23d81bfc8dd4422d48) ([#7315](https://github.com/yt-dlp/yt-dlp/issues/7315)) by [berkanteber](https://github.com/berkanteber), [pukkandan](https://github.com/pukkandan)
@ -27,7 +81,7 @@ #### Extractor changes
- [Workaround 403 for android formats](https://github.com/yt-dlp/yt-dlp/commit/81ca451480051d7ce1a31c017e005358345a9149) by [pukkandan](https://github.com/pukkandan)
#### Misc. changes
- [Revert "Add automatic duplicate issue detection"](https://github.com/yt-dlp/yt-dlp/commit/a4486bfc1dc7057efca9dd3fe70d7fa25c56f700)
- [Revert "Add automatic duplicate issue detection"](https://github.com/yt-dlp/yt-dlp/commit/a4486bfc1dc7057efca9dd3fe70d7fa25c56f700) by [pukkandan](https://github.com/pukkandan)
- **cleanup**
- Miscellaneous
- [7f9c6a6](https://github.com/yt-dlp/yt-dlp/commit/7f9c6a63b16e145495479e9f666f5b9e2ee69e2f) by [bashonly](https://github.com/bashonly)

2
Makefile
View file

@ -74,7 +74,7 @@ offlinetest: codetest
$(PYTHON) -m pytest -k "not download"
# XXX: This is hard to maintain
CODE_FOLDERS = yt_dlp yt_dlp/downloader yt_dlp/extractor yt_dlp/postprocessor yt_dlp/compat yt_dlp/compat/urllib yt_dlp/utils yt_dlp/dependencies
CODE_FOLDERS = yt_dlp yt_dlp/downloader yt_dlp/extractor yt_dlp/postprocessor yt_dlp/compat yt_dlp/compat/urllib yt_dlp/utils yt_dlp/dependencies yt_dlp/networking
yt-dlp: yt_dlp/*.py yt_dlp/*/*.py
mkdir -p zip
for d in $(CODE_FOLDERS) ; do \

21
README.md
View file

@ -12,7 +12,7 @@
[![License: Unlicense](https://img.shields.io/badge/-Unlicense-blue.svg?style=for-the-badge)](LICENSE "License")
[![CI Status](https://img.shields.io/github/actions/workflow/status/yt-dlp/yt-dlp/core.yml?branch=master&label=Tests&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/actions "CI Status")
[![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?label=&style=for-the-badge&display_timestamp=committer)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?label=&style=for-the-badge&display_timestamp=committer)](https://github.com/yt-dlp/yt-dlp/pulse/monthly "Last activity")
</div>
<!-- MANPAGE: END EXCLUDED SECTION -->
@ -76,7 +76,7 @@
# NEW FEATURES
* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@42f2d4**](https://github.com/yt-dlp/yt-dlp/commit/42f2d4) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))
* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@42f2d4**](https://github.com/ytdl-org/youtube-dl/commit/07af47960f3bb262ead02490ce65c8c45c01741e) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))
* **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in YouTube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
@ -1323,7 +1323,7 @@ # OUTPUT TEMPLATE
- `extractor` (string): Name of the extractor
- `extractor_key` (string): Key name of the extractor
- `epoch` (numeric): Unix epoch of when the information extraction was completed
- `autonumber` (numeric): Number that will be increased with each download, starting at `--autonumber-start`
- `autonumber` (numeric): Number that will be increased with each download, starting at `--autonumber-start`, padded with leading zeros to 5 digits
- `video_autonumber` (numeric): Number that will be increased with each video
- `n_entries` (numeric): Total number of extracted items in the playlist
- `playlist_id` (string): Identifier of the playlist that contains the video
@ -1509,7 +1509,7 @@ # FORMAT SELECTION
## Filtering Formats
You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"` since filters without a selector are interpreted as `best`).
The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
@ -1545,7 +1545,7 @@ ## Filtering Formats
**Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "bv[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
Format selectors can also be grouped using parentheses; e.g. `-f "(mp4,webm)[height<480]"` will download the best pre-merged mp4 and webm formats with a height lower than 480.
@ -1569,7 +1569,7 @@ ## Sorting Formats
- `aext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other). If `--prefer-free-formats` is used, the order changes to `ogg` > `opus` > `webm` > `mp3` > `m4a` > `aac`
- `ext`: Equivalent to `vext,aext`
- `filesize`: Exact filesize, if known in advance
- `fs_approx`: Approximate filesize calculated from the manifests
- `fs_approx`: Approximate filesize
- `size`: Exact filesize if available, otherwise approximate filesize
- `height`: Height of video
- `width`: Width of video
@ -1580,7 +1580,7 @@ ## Sorting Formats
- `tbr`: Total average bitrate in KBit/s
- `vbr`: Average video bitrate in KBit/s
- `abr`: Average audio bitrate in KBit/s
- `br`: Equivalent to using `tbr,vbr,abr`
- `br`: Average bitrate in KBit/s, `tbr`/`vbr`/`abr`
- `asr`: Audio sample rate in Hz
**Deprecation warning**: Many of these fields have (currently undocumented) aliases, that may be removed in a future version. It is recommended to use only the documented field names.
@ -1805,8 +1805,7 @@ #### youtube
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
* `max_comments`: Limit the amount of comments to gather. Comma-separated list of integers representing `max-comments,max-parents,max-replies,max-replies-per-thread`. Default is `all,all,all,all`
* 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
* `include_duplicate_formats`: Extract formats with identical content but different URLs or protocol. This is useful if some of the formats are unavailable or throttled.
* `include_incomplete_formats`: Extract formats that cannot be downloaded completely (live dash and post-live m3u8)
* `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
@ -1856,7 +1855,7 @@ #### rokfinchannel
#### twitter
* `legacy_api`: Force usage of the legacy Twitter API instead of the GraphQL API for tweet extraction. Has no effect if login cookies are passed
#### wrestleuniverse
#### stacommu, wrestleuniverse
* `device_id`: UUID value assigned by the website and used to enforce device limits for paid livestream content. Can be found in browser local storage
#### twitch
@ -1954,7 +1953,7 @@ # EMBEDDING YT-DLP
ydl.download(URLS)
```
Most likely, you'll want to use various options. For a list of options available, have a look at [`yt_dlp/YoutubeDL.py`](yt_dlp/YoutubeDL.py#L184).
Most likely, you'll want to use various options. For a list of options available, have a look at [`yt_dlp/YoutubeDL.py`](yt_dlp/YoutubeDL.py#L183) or `help(yt_dlp.YoutubeDL)` in a Python shell. If you are already familiar with the CLI, you can use [`devscripts/cli_to_api.py`](https://github.com/yt-dlp/yt-dlp/blob/master/devscripts/cli_to_api.py) to translate any CLI switches to `YoutubeDL` params.
**Tip**: If you are porting your code from youtube-dl to yt-dlp, one important point to look out for is that we do not guarantee the return value of `YoutubeDL.extract_info` to be json serializable, or even be a dictionary. It will be dictionary-like, but if you want to ensure it is a serializable dictionary, pass it through `YoutubeDL.sanitize_info` as shown in the [example below](#extracting-information)

25
devscripts/changelog_override.json
View file

@ -1,12 +1,12 @@
[
{
"action": "add",
"when": "776d1c3f0c9b00399896dd2e40e78e9a43218109",
"when": "29cb20bd563c02671b31dd840139e93dd37150a1",
"short": "[priority] **A new release type has been added!**\n * [`nightly`](https://github.com/yt-dlp/yt-dlp/releases/tag/nightly) builds will be made after each push, containing the latest fixes (but also possibly bugs).\n * When using `--update`/`-U`, a release binary will only update to its current channel (either `stable` or `nightly`).\n * The `--update-to` option has been added allowing the user more control over program upgrades (or downgrades).\n * `--update-to` can change the release channel (`stable`, `nightly`) and also upgrade or downgrade to specific tags.\n * **Usage**: `--update-to CHANNEL`, `--update-to TAG`, `--update-to CHANNEL@TAG`"
},
{
"action": "add",
"when": "776d1c3f0c9b00399896dd2e40e78e9a43218109",
"when": "5038f6d713303e0967d002216e7a88652401c22a",
"short": "[priority] **YouTube throttling fixes!**"
},
{
@ -38,13 +38,15 @@
},
{
"action": "change",
"when": "7b37e8b23691613f331bd4ebc9d639dd6f93c972",
"short": "Improve `--download-sections`\n - Support negative time-ranges\n - Add `*from-url` to obey time-ranges in URL"
"when": "b4e0d75848e9447cee2cd3646ce54d4744a7ff56",
"short": "Improve `--download-sections`\n - Support negative time-ranges\n - Add `*from-url` to obey time-ranges in URL",
"authors": ["pukkandan"]
},
{
"action": "change",
"when": "1e75d97db21152acc764b30a688e516f04b8a142",
"short": "[extractor/youtube] Add `ios` to default clients used\n - IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively\n - IOS also has higher bit-rate 'premium' formats though they are not labeled as such"
"short": "[extractor/youtube] Add `ios` to default clients used\n - IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively\n - IOS also has higher bit-rate 'premium' formats though they are not labeled as such",
"authors": ["pukkandan"]
},
{
"action": "change",
@ -55,6 +57,17 @@
{
"action": "change",
"when": "a4486bfc1dc7057efca9dd3fe70d7fa25c56f700",
"short": "[misc] Revert \"Add automatic duplicate issue detection\""
"short": "[misc] Revert \"Add automatic duplicate issue detection\"",
"authors": ["pukkandan"]
},
{
"action": "add",
"when": "1ceb657bdd254ad961489e5060f2ccc7d556b729",
"short": "[priority] Security: [[CVE-2023-35934](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2023-35934)] Fix [Cookie leak](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj)\n - `--add-header Cookie:` is deprecated and auto-scoped to input URL domains\n - Cookies are scoped when passed to external downloaders\n - Add `cookies` field to info.json and deprecate `http_headers.Cookie`"
},
{
"action": "change",
"when": "b03fa7834579a01cc5fba48c0e73488a16683d48",
"short": "[ie/twitter] Revert 92315c03774cfabb3a921884326beb4b981f786b"
}
]

23
devscripts/make_changelog.py
View file

@ -53,7 +53,9 @@ def commit_lookup(cls):
'cookies',
'core',
'dependencies',
'formats',
'jsinterp',
'networking',
'outtmpl',
'plugins',
'update',
@ -68,9 +70,9 @@ def commit_lookup(cls):
'misc',
'test',
},
cls.EXTRACTOR: {'extractor'},
cls.DOWNLOADER: {'downloader'},
cls.POSTPROCESSOR: {'postprocessor'},
cls.EXTRACTOR: {'extractor', 'ie'},
cls.DOWNLOADER: {'downloader', 'fd'},
cls.POSTPROCESSOR: {'postprocessor', 'pp'},
}.items()
for name in names
}
@ -252,6 +254,7 @@ class CommitRange:
(?:\ \((?P<issues>\#\d+(?:,\ \#\d+)*)\))?
''', re.VERBOSE | re.DOTALL)
EXTRACTOR_INDICATOR_RE = re.compile(r'(?:Fix|Add)\s+Extractors?', re.IGNORECASE)
REVERT_RE = re.compile(r'(?:\[[^\]]+\]\s+)?(?i:Revert)\s+([\da-f]{40})')
FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert)\s+([\da-f]{40})')
UPSTREAM_MERGE_RE = re.compile(r'Update to ytdl-commit-([\da-f]+)')
@ -279,7 +282,7 @@ def _get_commits_and_fixes(self, default_author):
self.COMMAND, 'log', f'--format=%H%n%s%n%b%n{self.COMMIT_SEPARATOR}',
f'{self._start}..{self._end}' if self._start else self._end).stdout
commits = {}
commits, reverts = {}, {}
fixes = defaultdict(list)
lines = iter(result.splitlines(False))
for i, commit_hash in enumerate(lines):
@ -300,6 +303,11 @@ def _get_commits_and_fixes(self, default_author):
logger.debug(f'Reached Release commit, breaking: {commit}')
break
revert_match = self.REVERT_RE.fullmatch(commit.short)
if revert_match:
reverts[revert_match.group(1)] = commit
continue
fix_match = self.FIXES_RE.search(commit.short)
if fix_match:
commitish = fix_match.group(1)
@ -307,6 +315,13 @@ def _get_commits_and_fixes(self, default_author):
commits[commit.hash] = commit
for commitish, revert_commit in reverts.items():
reverted = commits.pop(commitish, None)
if reverted:
logger.debug(f'{commit} fully reverted {reverted}')
else:
commits[revert_commit.hash] = revert_commit
for commitish, fix_commits in fixes.items():
if commitish in commits:
hashes = ', '.join(commit.hash[:HASH_LENGTH] for commit in fix_commits)

1
setup.cfg
View file

@ -8,7 +8,6 @@ ignore = E402,E501,E731,E741,W503
max_line_length = 120
per_file_ignores =
devscripts/lazy_load_template.py: F401
yt_dlp/utils/__init__.py: F401, F403
[autoflake]

3
setup.py
View file

@ -65,7 +65,8 @@ def py2exe_params():
'excludes': ['Crypto', 'Cryptodome'], # py2exe cannot import Crypto
'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'],
# Modules that are only imported dynamically must be added here
'includes': ['yt_dlp.compat._legacy'],
'includes': ['yt_dlp.compat._legacy', 'yt_dlp.compat._deprecated',
'yt_dlp.utils._legacy', 'yt_dlp.utils._deprecated'],
},
'zipfile': None,
}

6
supportedsites.md
View file

@ -1136,6 +1136,7 @@ # Supported sites
- **puhutv:serie**
- **Puls4**
- **Pyvideo**
- **QDance**: [*qdance*](## "netrc machine")
- **QingTing**
- **qqmusic**: QQ音乐
- **qqmusic:album**: QQ音乐 - 专辑
@ -1363,6 +1364,8 @@ # Supported sites
- **sr:mediathek**: Saarländischer Rundfunk
- **SRGSSR**
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
- **StacommuLive**: [*stacommu*](## "netrc machine")
- **StacommuVOD**: [*stacommu*](## "netrc machine")
- **StagePlusVODConcert**: [*stageplus*](## "netrc machine")
- **stanfordoc**: Stanford Open ClassRoom
- **StarTrek**
@ -1647,6 +1650,8 @@ # Supported sites
- **vk**: [*vk*](## "netrc machine") VK
- **vk:uservideos**: [*vk*](## "netrc machine") VK - User's Videos
- **vk:wallpost**: [*vk*](## "netrc machine")
- **VKPlay**
- **VKPlayLive**
- **vm.tiktok**
- **Vocaroo**
- **Vodlocker**
@ -1800,7 +1805,6 @@ # Supported sites
- **youtube:​search:date**: YouTube search, newest videos first; "ytsearchdate:" prefix
- **youtube:search_url**: YouTube search URLs with sorting and filter support
- **youtube:​shorts:pivot:audio**: YouTube Shorts audio pivot (Shorts using audio of a given video)
- **youtube:stories**: YouTube channel stories; "ytstories:" prefix
- **youtube:subscriptions**: YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)
- **youtube:tab**: YouTube Tabs
- **youtube:user**: YouTube user videos; "ytuser:" prefix

129
test/test_YoutubeDL.py
View file

@ -11,7 +11,7 @@
import copy
import json
from test.helper import FakeYDL, assertRegexpMatches
from test.helper import FakeYDL, assertRegexpMatches, try_rm
from yt_dlp import YoutubeDL
from yt_dlp.compat import compat_os_name
from yt_dlp.extractor import YoutubeIE
@ -24,6 +24,7 @@
int_or_none,
match_filter_func,
)
from yt_dlp.utils.traversal import traverse_obj
TEST_URL = 'http://localhost/sample.mp4'
@ -684,7 +685,8 @@ def test(tmpl, expected, *, info=None, **params):
test('%(id)s.%(ext)s', '1234.mp4')
test('%(duration_string)s', ('27:46:40', '27-46-40'))
test('%(resolution)s', '1080p')
test('%(playlist_index)s', '001')
test('%(playlist_index|)s', '001')
test('%(playlist_index&{}!)s', '1!')
test('%(playlist_autonumber)s', '02')
test('%(autonumber)s', '00001')
test('%(autonumber+2)03d', '005', autonumber_start=3)
@ -1213,6 +1215,129 @@ def _real_extract(self, url):
self.assertEqual(downloaded['extractor'], 'Video')
self.assertEqual(downloaded['extractor_key'], 'Video')
def test_header_cookies(self):
from http.cookiejar import Cookie
ydl = FakeYDL()
ydl.report_warning = lambda *_, **__: None
def cookie(name, value, version=None, domain='', path='', secure=False, expires=None):
return Cookie(
version or 0, name, value, None, False,
domain, bool(domain), bool(domain), path, bool(path),
secure, expires, False, None, None, rest={})
_test_url = 'https://yt.dlp/test'
def test(encoded_cookies, cookies, *, headers=False, round_trip=None, error_re=None):
def _test():
ydl.cookiejar.clear()
ydl._load_cookies(encoded_cookies, autoscope=headers)
if headers:
ydl._apply_header_cookies(_test_url)
data = {'url': _test_url}
ydl._calc_headers(data)
self.assertCountEqual(
map(vars, ydl.cookiejar), map(vars, cookies),
'Extracted cookiejar.Cookie is not the same')
if not headers:
self.assertEqual(
data.get('cookies'), round_trip or encoded_cookies,
'Cookie is not the same as round trip')
ydl.__dict__['_YoutubeDL__header_cookies'] = []
with self.subTest(msg=encoded_cookies):
if not error_re:
_test()
return
with self.assertRaisesRegex(Exception, error_re):
_test()
test('test=value; Domain=.yt.dlp', [cookie('test', 'value', domain='.yt.dlp')])
test('test=value', [cookie('test', 'value')], error_re=r'Unscoped cookies are not allowed')
test('cookie1=value1; Domain=.yt.dlp; Path=/test; cookie2=value2; Domain=.yt.dlp; Path=/', [
cookie('cookie1', 'value1', domain='.yt.dlp', path='/test'),
cookie('cookie2', 'value2', domain='.yt.dlp', path='/')])
test('test=value; Domain=.yt.dlp; Path=/test; Secure; Expires=9999999999', [
cookie('test', 'value', domain='.yt.dlp', path='/test', secure=True, expires=9999999999)])
test('test="value; "; path=/test; domain=.yt.dlp', [
cookie('test', 'value; ', domain='.yt.dlp', path='/test')],
round_trip='test="value\\073 "; Domain=.yt.dlp; Path=/test')
test('name=; Domain=.yt.dlp', [cookie('name', '', domain='.yt.dlp')],
round_trip='name=""; Domain=.yt.dlp')
test('test=value', [cookie('test', 'value', domain='.yt.dlp')], headers=True)
test('cookie1=value; Domain=.yt.dlp; cookie2=value', [], headers=True, error_re=r'Invalid syntax')
ydl.deprecated_feature = ydl.report_error
test('test=value', [], headers=True, error_re=r'Passing cookies as a header is a potential security risk')
def test_infojson_cookies(self):
TEST_FILE = 'test_infojson_cookies.info.json'
TEST_URL = 'https://example.com/example.mp4'
COOKIES = 'a=b; Domain=.example.com; c=d; Domain=.example.com'
COOKIE_HEADER = {'Cookie': 'a=b; c=d'}
ydl = FakeYDL()
ydl.process_info = lambda x: ydl._write_info_json('test', x, TEST_FILE)
def make_info(info_header_cookies=False, fmts_header_cookies=False, cookies_field=False):
fmt = {'url': TEST_URL}
if fmts_header_cookies:
fmt['http_headers'] = COOKIE_HEADER
if cookies_field:
fmt['cookies'] = COOKIES
return _make_result([fmt], http_headers=COOKIE_HEADER if info_header_cookies else None)
def test(initial_info, note):
result = {}
result['processed'] = ydl.process_ie_result(initial_info)
self.assertTrue(ydl.cookiejar.get_cookies_for_url(TEST_URL),
msg=f'No cookies set in cookiejar after initial process when {note}')
ydl.cookiejar.clear()
with open(TEST_FILE) as infojson:
result['loaded'] = ydl.sanitize_info(json.load(infojson), True)
result['final'] = ydl.process_ie_result(result['loaded'].copy(), download=False)
self.assertTrue(ydl.cookiejar.get_cookies_for_url(TEST_URL),
msg=f'No cookies set in cookiejar after final process when {note}')
ydl.cookiejar.clear()
for key in ('processed', 'loaded', 'final'):
info = result[key]
self.assertIsNone(
traverse_obj(info, ((None, ('formats', 0)), 'http_headers', 'Cookie'), casesense=False, get_all=False),
msg=f'Cookie header not removed in {key} result when {note}')
self.assertEqual(
traverse_obj(info, ((None, ('formats', 0)), 'cookies'), get_all=False), COOKIES,
msg=f'No cookies field found in {key} result when {note}')
test({'url': TEST_URL, 'http_headers': COOKIE_HEADER, 'id': '1', 'title': 'x'}, 'no formats field')
test(make_info(info_header_cookies=True), 'info_dict header cokies')
test(make_info(fmts_header_cookies=True), 'format header cookies')
test(make_info(info_header_cookies=True, fmts_header_cookies=True), 'info_dict and format header cookies')
test(make_info(info_header_cookies=True, fmts_header_cookies=True, cookies_field=True), 'all cookies fields')
test(make_info(cookies_field=True), 'cookies format field')
test({'url': TEST_URL, 'cookies': COOKIES, 'id': '1', 'title': 'x'}, 'info_dict cookies field only')
try_rm(TEST_FILE)
def test_add_headers_cookie(self):
def check_for_cookie_header(result):
return traverse_obj(result, ((None, ('formats', 0)), 'http_headers', 'Cookie'), casesense=False, get_all=False)
ydl = FakeYDL({'http_headers': {'Cookie': 'a=b'}})
ydl._apply_header_cookies(_make_result([])['webpage_url']) # Scope to input webpage URL: .example.com
fmt = {'url': 'https://example.com/video.mp4'}
result = ydl.process_ie_result(_make_result([fmt]), download=False)
self.assertIsNone(check_for_cookie_header(result), msg='http_headers cookies in result info_dict')
self.assertEqual(result.get('cookies'), 'a=b; Domain=.example.com', msg='No cookies were set in cookies field')
self.assertIn('a=b', ydl.cookiejar.get_cookie_header(fmt['url']), msg='No cookies were set in cookiejar')
fmt = {'url': 'https://wrong.com/video.mp4'}
result = ydl.process_ie_result(_make_result([fmt]), download=False)
self.assertIsNone(check_for_cookie_header(result), msg='http_headers cookies for wrong domain')
self.assertFalse(result.get('cookies'), msg='Cookies set in cookies field for wrong domain')
self.assertFalse(ydl.cookiejar.get_cookie_header(fmt['url']), msg='Cookies set in cookiejar for wrong domain')
if __name__ == '__main__':
unittest.main()

18
test/test_YoutubeDLCookieJar.py
View file

@ -17,10 +17,10 @@
class TestYoutubeDLCookieJar(unittest.TestCase):
def test_keep_session_cookies(self):
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt')
cookiejar.load(ignore_discard=True, ignore_expires=True)
cookiejar.load()
tf = tempfile.NamedTemporaryFile(delete=False)
try:
cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True)
cookiejar.save(filename=tf.name)
temp = tf.read().decode()
self.assertTrue(re.search(
r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp))
@ -32,7 +32,7 @@ def test_keep_session_cookies(self):
def test_strip_httponly_prefix(self):
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt')
cookiejar.load(ignore_discard=True, ignore_expires=True)
cookiejar.load()
def assert_cookie_has_value(key):
self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE')
@ -42,17 +42,25 @@ def assert_cookie_has_value(key):
def test_malformed_cookies(self):
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/malformed_cookies.txt')
cookiejar.load(ignore_discard=True, ignore_expires=True)
cookiejar.load()
# Cookies should be empty since all malformed cookie file entries
# will be ignored
self.assertFalse(cookiejar._cookies)
def test_get_cookie_header(self):
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt')
cookiejar.load(ignore_discard=True, ignore_expires=True)
cookiejar.load()
header = cookiejar.get_cookie_header('https://www.foobar.foobar')
self.assertIn('HTTPONLY_COOKIE', header)
def test_get_cookies_for_url(self):
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt')
cookiejar.load()
cookies = cookiejar.get_cookies_for_url('https://www.foobar.foobar/')
self.assertEqual(len(cookies), 2)
cookies = cookiejar.get_cookies_for_url('https://foobar.foobar/')
self.assertFalse(cookies)
if __name__ == '__main__':
unittest.main()

6
test/test_compat.py
View file

@ -9,15 +9,16 @@
import struct
import urllib.parse
from yt_dlp import compat
from yt_dlp.compat import urllib # isort: split
from yt_dlp.compat import (
compat_etree_fromstring,
compat_expanduser,
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
)
from yt_dlp.compat.urllib.request import getproxies
class TestCompat(unittest.TestCase):
@ -28,8 +29,7 @@ def test_compat_passthrough(self):
with self.assertWarns(DeprecationWarning):
compat.WINDOWS_VT_MODE
# TODO: Test submodule
# compat.asyncio.events # Must not raise error
self.assertEqual(urllib.request.getproxies, getproxies)
with self.assertWarns(DeprecationWarning):
compat.compat_pycrypto_AES # Must not raise error

9
test/test_download.py
View file

@ -10,10 +10,7 @@
import collections
import hashlib
import http.client
import json
import socket
import urllib.error
from test.helper import (
assertGreaterEqual,
@ -29,6 +26,7 @@
import yt_dlp.YoutubeDL # isort: split
from yt_dlp.extractor import get_info_extractor
from yt_dlp.networking.exceptions import HTTPError, TransportError
from yt_dlp.utils import (
DownloadError,
ExtractorError,
@ -162,8 +160,7 @@ def try_rm_tcs_files(tcs=None):
force_generic_extractor=params.get('force_generic_extractor', False))
except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one
if (err.exc_info[0] not in (urllib.error.URLError, socket.timeout, UnavailableVideoError, http.client.BadStatusLine)
or (err.exc_info[0] == urllib.error.HTTPError and err.exc_info[1].code == 503)):
if not isinstance(err.exc_info[1], (TransportError, UnavailableVideoError)) or (isinstance(err.exc_info[1], HTTPError) and err.exc_info[1].status == 503):
err.msg = f'{getattr(err, "msg", err)} ({tname})'
raise
@ -249,7 +246,7 @@ def try_rm_tcs_files(tcs=None):
# extractor returns full results even with extract_flat
res_tcs = [{'info_dict': e} for e in res_dict['entries']]
try_rm_tcs_files(res_tcs)
ydl.close()
return test_template

139
test/test_downloader_external.py Normal file
View file

@ -0,0 +1,139 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import http.cookiejar
from test.helper import FakeYDL
from yt_dlp.downloader.external import (
Aria2cFD,
AxelFD,
CurlFD,
FFmpegFD,
HttpieFD,
WgetFD,
)
TEST_COOKIE = {
'version': 0,
'name': 'test',
'value': 'ytdlp',
'port': None,
'port_specified': False,
'domain': '.example.com',
'domain_specified': True,
'domain_initial_dot': False,
'path': '/',
'path_specified': True,
'secure': False,
'expires': None,
'discard': False,
'comment': None,
'comment_url': None,
'rest': {},
}
TEST_INFO = {'url': 'http://www.example.com/'}
class TestHttpieFD(unittest.TestCase):
def test_make_cmd(self):
with FakeYDL() as ydl:
downloader = HttpieFD(ydl, {})
self.assertEqual(
downloader._make_cmd('test', TEST_INFO),
['http', '--download', '--output', 'test', 'http://www.example.com/'])
# Test cookie header is added
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
self.assertEqual(
downloader._make_cmd('test', TEST_INFO),
['http', '--download', '--output', 'test', 'http://www.example.com/', 'Cookie:test=ytdlp'])
class TestAxelFD(unittest.TestCase):
def test_make_cmd(self):
with FakeYDL() as ydl:
downloader = AxelFD(ydl, {})
self.assertEqual(
downloader._make_cmd('test', TEST_INFO),
['axel', '-o', 'test', '--', 'http://www.example.com/'])
# Test cookie header is added
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
self.assertEqual(
downloader._make_cmd('test', TEST_INFO),
['axel', '-o', 'test', '-H', 'Cookie: test=ytdlp', '--max-redirect=0', '--', 'http://www.example.com/'])
class TestWgetFD(unittest.TestCase):
def test_make_cmd(self):
with FakeYDL() as ydl:
downloader = WgetFD(ydl, {})
self.assertNotIn('--load-cookies', downloader._make_cmd('test', TEST_INFO))
# Test cookiejar tempfile arg is added
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
self.assertIn('--load-cookies', downloader._make_cmd('test', TEST_INFO))
class TestCurlFD(unittest.TestCase):
def test_make_cmd(self):
with FakeYDL() as ydl:
downloader = CurlFD(ydl, {})
self.assertNotIn('--cookie', downloader._make_cmd('test', TEST_INFO))
# Test cookie header is added
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
self.assertIn('--cookie', downloader._make_cmd('test', TEST_INFO))
self.assertIn('test=ytdlp', downloader._make_cmd('test', TEST_INFO))
class TestAria2cFD(unittest.TestCase):
def test_make_cmd(self):
with FakeYDL() as ydl:
downloader = Aria2cFD(ydl, {})
downloader._make_cmd('test', TEST_INFO)
self.assertFalse(hasattr(downloader, '_cookies_tempfile'))
# Test cookiejar tempfile arg is added
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
cmd = downloader._make_cmd('test', TEST_INFO)
self.assertIn(f'--load-cookies={downloader._cookies_tempfile}', cmd)
@unittest.skipUnless(FFmpegFD.available(), 'ffmpeg not found')
class TestFFmpegFD(unittest.TestCase):
_args = []
def _test_cmd(self, args):
self._args = args
def test_make_cmd(self):
with FakeYDL() as ydl:
downloader = FFmpegFD(ydl, {})
downloader._debug_cmd = self._test_cmd
downloader._call_downloader('test', {**TEST_INFO, 'ext': 'mp4'})
self.assertEqual(self._args, [
'ffmpeg', '-y', '-hide_banner', '-i', 'http://www.example.com/',
'-c', 'copy', '-f', 'mp4', 'file:test'])
# Test cookies arg is added
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
downloader._call_downloader('test', {**TEST_INFO, 'ext': 'mp4'})
self.assertEqual(self._args, [
'ffmpeg', '-y', '-hide_banner', '-cookies', 'test=ytdlp; path=/; domain=.example.com;\r\n',
'-i', 'http://www.example.com/', '-c', 'copy', '-f', 'mp4', 'file:test'])
# Test with non-url input (ffmpeg reads from stdin '-' for websockets)
downloader._call_downloader('test', {'url': 'x', 'ext': 'mp4'})
self.assertEqual(self._args, [
'ffmpeg', '-y', '-hide_banner', '-i', 'x', '-c', 'copy', '-f', 'mp4', 'file:test'])
if __name__ == '__main__':
unittest.main()

12
test/test_downloader_http.py
View file

@ -16,6 +16,7 @@
from yt_dlp import YoutubeDL
from yt_dlp.downloader.http import HttpFD
from yt_dlp.utils import encodeFilename
from yt_dlp.utils._utils import _YDLLogger as FakeLogger
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
@ -67,17 +68,6 @@ def do_GET(self):
assert False
class FakeLogger:
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
pass
class TestHttpFD(unittest.TestCase):
def setUp(self):
self.httpd = http.server.HTTPServer(

500
test/test_http.py
View file

@ -1,500 +0,0 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import gzip
import http.cookiejar
import http.server
import io
import pathlib
import ssl
import tempfile
import threading
import urllib.error
import urllib.request
import zlib
from test.helper import http_server_port
from yt_dlp import YoutubeDL
from yt_dlp.dependencies import brotli
from yt_dlp.utils import sanitized_Request, urlencode_postdata
from .helper import FakeYDL
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
protocol_version = 'HTTP/1.1'
def log_message(self, format, *args):
pass
def _headers(self):
payload = str(self.headers).encode('utf-8')
self.send_response(200)
self.send_header('Content-Type', 'application/json')
self.send_header('Content-Length', str(len(payload)))
self.end_headers()
self.wfile.write(payload)
def _redirect(self):
self.send_response(int(self.path[len('/redirect_'):]))
self.send_header('Location', '/method')
self.send_header('Content-Length', '0')
self.end_headers()
def _method(self, method, payload=None):
self.send_response(200)
self.send_header('Content-Length', str(len(payload or '')))
self.send_header('Method', method)
self.end_headers()
if payload:
self.wfile.write(payload)
def _status(self, status):
payload = f'<html>{status} NOT FOUND</html>'.encode()
self.send_response(int(status))
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.send_header('Content-Length', str(len(payload)))
self.end_headers()
self.wfile.write(payload)
def _read_data(self):
if 'Content-Length' in self.headers:
return self.rfile.read(int(self.headers['Content-Length']))
def do_POST(self):
data = self._read_data()
if self.path.startswith('/redirect_'):
self._redirect()
elif self.path.startswith('/method'):
self._method('POST', data)
elif self.path.startswith('/headers'):
self._headers()
else:
self._status(404)
def do_HEAD(self):
if self.path.startswith('/redirect_'):
self._redirect()
elif self.path.startswith('/method'):
self._method('HEAD')
else:
self._status(404)
def do_PUT(self):
data = self._read_data()
if self.path.startswith('/redirect_'):
self._redirect()
elif self.path.startswith('/method'):
self._method('PUT', data)
else:
self._status(404)
def do_GET(self):
if self.path == '/video.html':
payload = b'<html><video src="/vid.mp4" /></html>'
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.send_header('Content-Length', str(len(payload))) # required for persistent connections
self.end_headers()
self.wfile.write(payload)
elif self.path == '/vid.mp4':
payload = b'\x00\x00\x00\x00\x20\x66\x74[video]'
self.send_response(200)
self.send_header('Content-Type', 'video/mp4')
self.send_header('Content-Length', str(len(payload)))
self.end_headers()
self.wfile.write(payload)
elif self.path == '/%E4%B8%AD%E6%96%87.html':
payload = b'<html><video src="/vid.mp4" /></html>'
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.send_header('Content-Length', str(len(payload)))
self.end_headers()
self.wfile.write(payload)
elif self.path == '/%c7%9f':
payload = b'<html><video src="/vid.mp4" /></html>'
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.send_header('Content-Length', str(len(payload)))
self.end_headers()
self.wfile.write(payload)
elif self.path.startswith('/redirect_'):
self._redirect()
elif self.path.startswith('/method'):
self._method('GET')
elif self.path.startswith('/headers'):
self._headers()
elif self.path == '/trailing_garbage':
payload = b'<html><video src="/vid.mp4" /></html>'
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.send_header('Content-Encoding', 'gzip')
buf = io.BytesIO()
with gzip.GzipFile(fileobj=buf, mode='wb') as f:
f.write(payload)
compressed = buf.getvalue() + b'trailing garbage'
self.send_header('Content-Length', str(len(compressed)))
self.end_headers()
self.wfile.write(compressed)
elif self.path == '/302-non-ascii-redirect':
new_url = f'http://127.0.0.1:{http_server_port(self.server)}/中文.html'
self.send_response(301)
self.send_header('Location', new_url)
self.send_header('Content-Length', '0')
self.end_headers()
elif self.path == '/content-encoding':
encodings = self.headers.get('ytdl-encoding', '')
payload = b'<html><video src="/vid.mp4" /></html>'
for encoding in filter(None, (e.strip() for e in encodings.split(','))):
if encoding == 'br' and brotli:
payload = brotli.compress(payload)
elif encoding == 'gzip':
buf = io.BytesIO()
with gzip.GzipFile(fileobj=buf, mode='wb') as f:
f.write(payload)
payload = buf.getvalue()
elif encoding == 'deflate':
payload = zlib.compress(payload)
elif encoding == 'unsupported':
payload = b'raw'
break
else:
self._status(415)
return
self.send_response(200)
self.send_header('Content-Encoding', encodings)
self.send_header('Content-Length', str(len(payload)))
self.end_headers()
self.wfile.write(payload)
else:
self._status(404)
def send_header(self, keyword, value):
"""
Forcibly allow HTTP server to send non percent-encoded non-ASCII characters in headers.
This is against what is defined in RFC 3986, however we need to test we support this
since some sites incorrectly do this.
"""
if keyword.lower() == 'connection':
return super().send_header(keyword, value)
if not hasattr(self, '_headers_buffer'):
self._headers_buffer = []
self._headers_buffer.append(f'{keyword}: {value}\r\n'.encode())
class FakeLogger:
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
pass
class TestHTTP(unittest.TestCase):
def setUp(self):
# HTTP server
self.http_httpd = http.server.ThreadingHTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
self.http_port = http_server_port(self.http_httpd)
self.http_server_thread = threading.Thread(target=self.http_httpd.serve_forever)
# FIXME: we should probably stop the http server thread after each test
# See: https://github.com/yt-dlp/yt-dlp/pull/7094#discussion_r1199746041
self.http_server_thread.daemon = True
self.http_server_thread.start()
# HTTPS server
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.https_httpd = http.server.ThreadingHTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.load_cert_chain(certfn, None)
self.https_httpd.socket = sslctx.wrap_socket(self.https_httpd.socket, server_side=True)
self.https_port = http_server_port(self.https_httpd)
self.https_server_thread = threading.Thread(target=self.https_httpd.serve_forever)
self.https_server_thread.daemon = True
self.https_server_thread.start()
def test_nocheckcertificate(self):
with FakeYDL({'logger': FakeLogger()}) as ydl:
with self.assertRaises(urllib.error.URLError):
ydl.urlopen(sanitized_Request(f'https://127.0.0.1:{self.https_port}/headers'))
with FakeYDL({'logger': FakeLogger(), 'nocheckcertificate': True}) as ydl:
r = ydl.urlopen(sanitized_Request(f'https://127.0.0.1:{self.https_port}/headers'))
self.assertEqual(r.status, 200)
r.close()
def test_percent_encode(self):
with FakeYDL() as ydl:
# Unicode characters should be encoded with uppercase percent-encoding
res = ydl.urlopen(sanitized_Request(f'http://127.0.0.1:{self.http_port}/中文.html'))
self.assertEqual(res.status, 200)
res.close()
# don't normalize existing percent encodings
res = ydl.urlopen(sanitized_Request(f'http://127.0.0.1:{self.http_port}/%c7%9f'))
self.assertEqual(res.status, 200)
res.close()
def test_unicode_path_redirection(self):
with FakeYDL() as ydl:
r = ydl.urlopen(sanitized_Request(f'http://127.0.0.1:{self.http_port}/302-non-ascii-redirect'))
self.assertEqual(r.url, f'http://127.0.0.1:{self.http_port}/%E4%B8%AD%E6%96%87.html')
r.close()
def test_redirect(self):
with FakeYDL() as ydl:
def do_req(redirect_status, method):
data = b'testdata' if method in ('POST', 'PUT') else None
res = ydl.urlopen(sanitized_Request(
f'http://127.0.0.1:{self.http_port}/redirect_{redirect_status}', method=method, data=data))
return res.read().decode('utf-8'), res.headers.get('method', '')
# A 303 must either use GET or HEAD for subsequent request
self.assertEqual(do_req(303, 'POST'), ('', 'GET'))
self.assertEqual(do_req(303, 'HEAD'), ('', 'HEAD'))
self.assertEqual(do_req(303, 'PUT'), ('', 'GET'))
# 301 and 302 turn POST only into a GET
self.assertEqual(do_req(301, 'POST'), ('', 'GET'))
self.assertEqual(do_req(301, 'HEAD'), ('', 'HEAD'))
self.assertEqual(do_req(302, 'POST'), ('', 'GET'))
self.assertEqual(do_req(302, 'HEAD'), ('', 'HEAD'))
self.assertEqual(do_req(301, 'PUT'), ('testdata', 'PUT'))
self.assertEqual(do_req(302, 'PUT'), ('testdata', 'PUT'))
# 307 and 308 should not change method
for m in ('POST', 'PUT'):
self.assertEqual(do_req(307, m), ('testdata', m))
self.assertEqual(do_req(308, m), ('testdata', m))
self.assertEqual(do_req(307, 'HEAD'), ('', 'HEAD'))
self.assertEqual(do_req(308, 'HEAD'), ('', 'HEAD'))
# These should not redirect and instead raise an HTTPError
for code in (300, 304, 305, 306):
with self.assertRaises(urllib.error.HTTPError):
do_req(code, 'GET')
def test_content_type(self):
# https://github.com/yt-dlp/yt-dlp/commit/379a4f161d4ad3e40932dcf5aca6e6fb9715ab28
with FakeYDL({'nocheckcertificate': True}) as ydl:
# method should be auto-detected as POST
r = sanitized_Request(f'https://localhost:{self.https_port}/headers', data=urlencode_postdata({'test': 'test'}))
headers = ydl.urlopen(r).read().decode('utf-8')
self.assertIn('Content-Type: application/x-www-form-urlencoded', headers)
# test http
r = sanitized_Request(f'http://localhost:{self.http_port}/headers', data=urlencode_postdata({'test': 'test'}))
headers = ydl.urlopen(r).read().decode('utf-8')
self.assertIn('Content-Type: application/x-www-form-urlencoded', headers)
def test_cookiejar(self):
with FakeYDL() as ydl:
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(
0, 'test', 'ytdlp', None, False, '127.0.0.1', True,
False, '/headers', True, False, None, False, None, None, {}))
data = ydl.urlopen(sanitized_Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
self.assertIn(b'Cookie: test=ytdlp', data)
def test_no_compression_compat_header(self):
with FakeYDL() as ydl:
data = ydl.urlopen(
sanitized_Request(
f'http://127.0.0.1:{self.http_port}/headers',
headers={'Youtubedl-no-compression': True})).read()
self.assertIn(b'Accept-Encoding: identity', data)
self.assertNotIn(b'youtubedl-no-compression', data.lower())
def test_gzip_trailing_garbage(self):
# https://github.com/ytdl-org/youtube-dl/commit/aa3e950764337ef9800c936f4de89b31c00dfcf5
# https://github.com/ytdl-org/youtube-dl/commit/6f2ec15cee79d35dba065677cad9da7491ec6e6f
with FakeYDL() as ydl:
data = ydl.urlopen(sanitized_Request(f'http://localhost:{self.http_port}/trailing_garbage')).read().decode('utf-8')
self.assertEqual(data, '<html><video src="/vid.mp4" /></html>')
@unittest.skipUnless(brotli, 'brotli support is not installed')
def test_brotli(self):
with FakeYDL() as ydl:
res = ydl.urlopen(
sanitized_Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': 'br'}))
self.assertEqual(res.headers.get('Content-Encoding'), 'br')
self.assertEqual(res.read(), b'<html><video src="/vid.mp4" /></html>')
def test_deflate(self):
with FakeYDL() as ydl:
res = ydl.urlopen(
sanitized_Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': 'deflate'}))
self.assertEqual(res.headers.get('Content-Encoding'), 'deflate')
self.assertEqual(res.read(), b'<html><video src="/vid.mp4" /></html>')
def test_gzip(self):
with FakeYDL() as ydl:
res = ydl.urlopen(
sanitized_Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': 'gzip'}))
self.assertEqual(res.headers.get('Content-Encoding'), 'gzip')
self.assertEqual(res.read(), b'<html><video src="/vid.mp4" /></html>')
def test_multiple_encodings(self):
# https://www.rfc-editor.org/rfc/rfc9110.html#section-8.4
with FakeYDL() as ydl:
for pair in ('gzip,deflate', 'deflate, gzip', 'gzip, gzip', 'deflate, deflate'):
res = ydl.urlopen(
sanitized_Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': pair}))
self.assertEqual(res.headers.get('Content-Encoding'), pair)
self.assertEqual(res.read(), b'<html><video src="/vid.mp4" /></html>')
def test_unsupported_encoding(self):
# it should return the raw content
with FakeYDL() as ydl:
res = ydl.urlopen(
sanitized_Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': 'unsupported'}))
self.assertEqual(res.headers.get('Content-Encoding'), 'unsupported')
self.assertEqual(res.read(), b'raw')
class TestClientCert(unittest.TestCase):
def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.certdir = os.path.join(TEST_DIR, 'testdata', 'certificate')
cacertfn = os.path.join(self.certdir, 'ca.crt')
self.httpd = http.server.HTTPServer(('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.verify_mode = ssl.CERT_REQUIRED
sslctx.load_verify_locations(cafile=cacertfn)
sslctx.load_cert_chain(certfn, None)
self.httpd.socket = sslctx.wrap_socket(self.httpd.socket, server_side=True)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
def _run_test(self, **params):
ydl = YoutubeDL({
'logger': FakeLogger(),
# Disable client-side validation of unacceptable self-signed testcert.pem
# The test is of a check on the server side, so unaffected
'nocheckcertificate': True,
**params,
})
r = ydl.extract_info(f'https://127.0.0.1:{self.port}/video.html')
self.assertEqual(r['url'], f'https://127.0.0.1:{self.port}/vid.mp4')
def test_certificate_combined_nopass(self):
self._run_test(client_certificate=os.path.join(self.certdir, 'clientwithkey.crt'))
def test_certificate_nocombined_nopass(self):
self._run_test(client_certificate=os.path.join(self.certdir, 'client.crt'),
client_certificate_key=os.path.join(self.certdir, 'client.key'))
def test_certificate_combined_pass(self):
self._run_test(client_certificate=os.path.join(self.certdir, 'clientwithencryptedkey.crt'),
client_certificate_password='foobar')
def test_certificate_nocombined_pass(self):
self._run_test(client_certificate=os.path.join(self.certdir, 'client.crt'),
client_certificate_key=os.path.join(self.certdir, 'clientencrypted.key'),
client_certificate_password='foobar')
def _build_proxy_handler(name):
class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
proxy_name = name
def log_message(self, format, *args):
pass
def do_GET(self):
self.send_response(200)
self.send_header('Content-Type', 'text/plain; charset=utf-8')
self.end_headers()
self.wfile.write(f'{self.proxy_name}: {self.path}'.encode())
return HTTPTestRequestHandler
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = http.server.HTTPServer(
('127.0.0.1', 0), _build_proxy_handler('normal'))
self.port = http_server_port(self.proxy)
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.geo_proxy = http.server.HTTPServer(
('127.0.0.1', 0), _build_proxy_handler('geo'))
self.geo_port = http_server_port(self.geo_proxy)
self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever)
self.geo_proxy_thread.daemon = True
self.geo_proxy_thread.start()
def test_proxy(self):
geo_proxy = f'127.0.0.1:{self.geo_port}'
ydl = YoutubeDL({
'proxy': f'127.0.0.1:{self.port}',
'geo_verification_proxy': geo_proxy,
})
url = 'http://foo.com/bar'
response = ydl.urlopen(url).read().decode()
self.assertEqual(response, f'normal: {url}')
req = urllib.request.Request(url)
req.add_header('Ytdl-request-proxy', geo_proxy)
response = ydl.urlopen(req).read().decode()
self.assertEqual(response, f'geo: {url}')
def test_proxy_with_idn(self):
ydl = YoutubeDL({
'proxy': f'127.0.0.1:{self.port}',
})
url = 'http://中文.tw/'
response = ydl.urlopen(url).read().decode()
# b'xn--fiq228c' is '中文'.encode('idna')
self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
class TestFileURL(unittest.TestCase):
# See https://github.com/ytdl-org/youtube-dl/issues/8227
def test_file_urls(self):
tf = tempfile.NamedTemporaryFile(delete=False)
tf.write(b'foobar')
tf.close()
url = pathlib.Path(tf.name).as_uri()
with FakeYDL() as ydl:
self.assertRaisesRegex(
urllib.error.URLError, 'file:// URLs are explicitly disabled in yt-dlp for security reasons', ydl.urlopen, url)
with FakeYDL({'enable_file_urls': True}) as ydl:
res = ydl.urlopen(url)
self.assertEqual(res.read(), b'foobar')
res.close()
os.unlink(tf.name)
if __name__ == '__main__':
unittest.main()

1382
test/test_networking.py Normal file
View file

File diff suppressed because it is too large Load diff

279
test/test_networking_utils.py Normal file
View file

@ -0,0 +1,279 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import sys
import pytest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import contextlib
import io
import platform
import random
import ssl
import urllib.error
import warnings
from yt_dlp.cookies import YoutubeDLCookieJar
from yt_dlp.dependencies import certifi
from yt_dlp.networking import Response
from yt_dlp.networking._helper import (
InstanceStoreMixin,
add_accept_encoding_header,
get_redirect_method,
make_socks_proxy_opts,
select_proxy,
ssl_load_certs,
)
from yt_dlp.networking.exceptions import (
HTTPError,
IncompleteRead,
_CompatHTTPError,
)
from yt_dlp.socks import ProxyType
from yt_dlp.utils.networking import HTTPHeaderDict
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
class TestNetworkingUtils:
def test_select_proxy(self):
proxies = {
'all': 'socks5://example.com',
'http': 'http://example.com:1080',
'no': 'bypass.example.com,yt-dl.org'
}
assert select_proxy('https://example.com', proxies) == proxies['all']
assert select_proxy('http://example.com', proxies) == proxies['http']
assert select_proxy('http://bypass.example.com', proxies) is None
assert select_proxy('https://yt-dl.org', proxies) is None
@pytest.mark.parametrize('socks_proxy,expected', [
('socks5h://example.com', {
'proxytype': ProxyType.SOCKS5,
'addr': 'example.com',
'port': 1080,
'rdns': True,
'username': None,
'password': None
}),
('socks5://user:@example.com:5555', {
'proxytype': ProxyType.SOCKS5,
'addr': 'example.com',
'port': 5555,
'rdns': False,
'username': 'user',
'password': ''
}),
('socks4://u%40ser:pa%20ss@127.0.0.1:1080', {
'proxytype': ProxyType.SOCKS4,
'addr': '127.0.0.1',
'port': 1080,
'rdns': False,
'username': 'u@ser',
'password': 'pa ss'
}),
('socks4a://:pa%20ss@127.0.0.1', {
'proxytype': ProxyType.SOCKS4A,
'addr': '127.0.0.1',
'port': 1080,
'rdns': True,
'username': '',
'password': 'pa ss'
})
])
def test_make_socks_proxy_opts(self, socks_proxy, expected):
assert make_socks_proxy_opts(socks_proxy) == expected
def test_make_socks_proxy_unknown(self):
with pytest.raises(ValueError, match='Unknown SOCKS proxy version: socks'):
make_socks_proxy_opts('socks://127.0.0.1')
@pytest.mark.skipif(not certifi, reason='certifi is not installed')
def test_load_certifi(self):
context = ssl.SSLContext(ssl.PROTOCOL_TLS_CLIENT)
context2 = ssl.SSLContext(ssl.PROTOCOL_TLS_CLIENT)
ssl_load_certs(context, use_certifi=True)
context2.load_verify_locations(cafile=certifi.where())
assert context.get_ca_certs() == context2.get_ca_certs()
# Test load normal certs
# XXX: could there be a case where system certs are the same as certifi?
context3 = ssl.SSLContext(ssl.PROTOCOL_TLS_CLIENT)
ssl_load_certs(context3, use_certifi=False)
assert context3.get_ca_certs() != context.get_ca_certs()
@pytest.mark.parametrize('method,status,expected', [
('GET', 303, 'GET'),
('HEAD', 303, 'HEAD'),
('PUT', 303, 'GET'),
('POST', 301, 'GET'),
('HEAD', 301, 'HEAD'),
('POST', 302, 'GET'),
('HEAD', 302, 'HEAD'),
('PUT', 302, 'PUT'),
('POST', 308, 'POST'),
('POST', 307, 'POST'),
('HEAD', 308, 'HEAD'),
('HEAD', 307, 'HEAD'),
])
def test_get_redirect_method(self, method, status, expected):
assert get_redirect_method(method, status) == expected
@pytest.mark.parametrize('headers,supported_encodings,expected', [
({'Accept-Encoding': 'br'}, ['gzip', 'br'], {'Accept-Encoding': 'br'}),
({}, ['gzip', 'br'], {'Accept-Encoding': 'gzip, br'}),
({'Content-type': 'application/json'}, [], {'Content-type': 'application/json', 'Accept-Encoding': 'identity'}),
])
def test_add_accept_encoding_header(self, headers, supported_encodings, expected):
headers = HTTPHeaderDict(headers)
add_accept_encoding_header(headers, supported_encodings)
assert headers == HTTPHeaderDict(expected)
class TestInstanceStoreMixin:
class FakeInstanceStoreMixin(InstanceStoreMixin):
def _create_instance(self, **kwargs):
return random.randint(0, 1000000)
def _close_instance(self, instance):
pass
def test_mixin(self):
mixin = self.FakeInstanceStoreMixin()
assert mixin._get_instance(d={'a': 1, 'b': 2, 'c': {'d', 4}}) == mixin._get_instance(d={'a': 1, 'b': 2, 'c': {'d', 4}})
assert mixin._get_instance(d={'a': 1, 'b': 2, 'c': {'e', 4}}) != mixin._get_instance(d={'a': 1, 'b': 2, 'c': {'d', 4}})
assert mixin._get_instance(d={'a': 1, 'b': 2, 'c': {'d', 4}} != mixin._get_instance(d={'a': 1, 'b': 2, 'g': {'d', 4}}))
assert mixin._get_instance(d={'a': 1}, e=[1, 2, 3]) == mixin._get_instance(d={'a': 1}, e=[1, 2, 3])
assert mixin._get_instance(d={'a': 1}, e=[1, 2, 3]) != mixin._get_instance(d={'a': 1}, e=[1, 2, 3, 4])
cookiejar = YoutubeDLCookieJar()
assert mixin._get_instance(b=[1, 2], c=cookiejar) == mixin._get_instance(b=[1, 2], c=cookiejar)
assert mixin._get_instance(b=[1, 2], c=cookiejar) != mixin._get_instance(b=[1, 2], c=YoutubeDLCookieJar())
# Different order
assert mixin._get_instance(c=cookiejar, b=[1, 2]) == mixin._get_instance(b=[1, 2], c=cookiejar)
m = mixin._get_instance(t=1234)
assert mixin._get_instance(t=1234) == m
mixin._clear_instances()
assert mixin._get_instance(t=1234) != m
class TestNetworkingExceptions:
@staticmethod
def create_response(status):
return Response(fp=io.BytesIO(b'test'), url='http://example.com', headers={'tesT': 'test'}, status=status)
@pytest.mark.parametrize('http_error_class', [HTTPError, lambda r: _CompatHTTPError(HTTPError(r))])
def test_http_error(self, http_error_class):
response = self.create_response(403)
error = http_error_class(response)
assert error.status == 403
assert str(error) == error.msg == 'HTTP Error 403: Forbidden'
assert error.reason == response.reason
assert error.response is response
data = error.response.read()
assert data == b'test'
assert repr(error) == '<HTTPError 403: Forbidden>'
@pytest.mark.parametrize('http_error_class', [HTTPError, lambda *args, **kwargs: _CompatHTTPError(HTTPError(*args, **kwargs))])
def test_redirect_http_error(self, http_error_class):
response = self.create_response(301)
error = http_error_class(response, redirect_loop=True)
assert str(error) == error.msg == 'HTTP Error 301: Moved Permanently (redirect loop detected)'
assert error.reason == 'Moved Permanently'
def test_compat_http_error(self):
response = self.create_response(403)
error = _CompatHTTPError(HTTPError(response))
assert isinstance(error, HTTPError)
assert isinstance(error, urllib.error.HTTPError)
@contextlib.contextmanager
def raises_deprecation_warning():
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter('always')
yield
if len(w) == 0:
pytest.fail('Did not raise DeprecationWarning')
if len(w) > 1:
pytest.fail(f'Raised multiple warnings: {w}')
if not issubclass(w[-1].category, DeprecationWarning):
pytest.fail(f'Expected DeprecationWarning, got {w[-1].category}')
w.clear()
with raises_deprecation_warning():
assert error.code == 403
with raises_deprecation_warning():
assert error.getcode() == 403
with raises_deprecation_warning():
assert error.hdrs is error.response.headers
with raises_deprecation_warning():
assert error.info() is error.response.headers
with raises_deprecation_warning():
assert error.headers is error.response.headers
with raises_deprecation_warning():
assert error.filename == error.response.url
with raises_deprecation_warning():
assert error.url == error.response.url
with raises_deprecation_warning():
assert error.geturl() == error.response.url
# Passthrough file operations
with raises_deprecation_warning():
assert error.read() == b'test'
with raises_deprecation_warning():
assert not error.closed
with raises_deprecation_warning():
# Technically Response operations are also passed through, which should not be used.
assert error.get_header('test') == 'test'
# Should not raise a warning
error.close()
@pytest.mark.skipif(
platform.python_implementation() == 'PyPy', reason='garbage collector works differently in pypy')
def test_compat_http_error_autoclose(self):
# Compat HTTPError should not autoclose response
response = self.create_response(403)
_CompatHTTPError(HTTPError(response))
assert not response.closed
def test_incomplete_read_error(self):
error = IncompleteRead(b'test', 3, cause='test')
assert isinstance(error, IncompleteRead)
assert repr(error) == '<IncompleteRead: 4 bytes read, 3 more expected>'
assert str(error) == error.msg == '4 bytes read, 3 more expected'
assert error.partial == b'test'
assert error.expected == 3
assert error.cause == 'test'
error = IncompleteRead(b'aaa')
assert repr(error) == '<IncompleteRead: 3 bytes read>'
assert str(error) == '3 bytes read'

54
test/test_utils.py
View file

@ -51,6 +51,7 @@
escape_url,
expand_path,
extract_attributes,
extract_basic_auth,
find_xpath_attr,
fix_xml_ampersands,
float_or_none,
@ -103,7 +104,6 @@
sanitize_filename,
sanitize_path,
sanitize_url,
sanitized_Request,
shell_quote,
smuggle_url,
str_or_none,
@ -132,6 +132,7 @@
xpath_text,
xpath_with_ns,
)
from yt_dlp.utils.networking import HTTPHeaderDict
class TestUtil(unittest.TestCase):
@ -258,15 +259,6 @@ def test_sanitize_url(self):
self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
self.assertEqual(sanitize_url('foo bar'), 'foo bar')
def test_extract_basic_auth(self):
auth_header = lambda url: sanitized_Request(url).get_header('Authorization')
self.assertFalse(auth_header('http://foo.bar'))
self.assertFalse(auth_header('http://:foo.bar'))
self.assertEqual(auth_header('http://@foo.bar'), 'Basic Og==')
self.assertEqual(auth_header('http://:pass@foo.bar'), 'Basic OnBhc3M=')
self.assertEqual(auth_header('http://user:@foo.bar'), 'Basic dXNlcjo=')
self.assertEqual(auth_header('http://user:pass@foo.bar'), 'Basic dXNlcjpwYXNz')
def test_expand_path(self):
def env(var):
return f'%{var}%' if sys.platform == 'win32' else f'${var}'
@ -668,6 +660,8 @@ def test_parse_duration(self):
self.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88)
self.assertEqual(parse_duration('01:02:03:050'), 3723.05)
self.assertEqual(parse_duration('103:050'), 103.05)
self.assertEqual(parse_duration('1HR 3MIN'), 3780)
self.assertEqual(parse_duration('2hrs 3mins'), 7380)
def test_fix_xml_ampersands(self):
self.assertEqual(
@ -1840,6 +1834,8 @@ def test_iri_to_uri(self):
def test_clean_podcast_url(self):
self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
self.assertEqual(clean_podcast_url('https://pdst.fm/e/2.gum.fm/chtbl.com/track/chrt.fm/track/34D33/pscrb.fm/rss/p/traffic.megaphone.fm/ITLLC7765286967.mp3?updated=1687282661'), 'https://traffic.megaphone.fm/ITLLC7765286967.mp3?updated=1687282661')
self.assertEqual(clean_podcast_url('https://pdst.fm/e/https://mgln.ai/e/441/www.buzzsprout.com/1121972/13019085-ep-252-the-deep-life-stack.mp3'), 'https://www.buzzsprout.com/1121972/13019085-ep-252-the-deep-life-stack.mp3')
def test_LazyList(self):
it = list(range(10))
@ -2327,6 +2323,44 @@ def test_traverse_obj(self):
self.assertEqual(traverse_obj(mobj, lambda k, _: k in (0, 'group')), ['0123', '3'],
msg='function on a `re.Match` should give group name as well')
def test_http_header_dict(self):
headers = HTTPHeaderDict()
headers['ytdl-test'] = 1
self.assertEqual(list(headers.items()), [('Ytdl-Test', '1')])
headers['Ytdl-test'] = '2'
self.assertEqual(list(headers.items()), [('Ytdl-Test', '2')])
self.assertTrue('ytDl-Test' in headers)
self.assertEqual(str(headers), str(dict(headers)))
self.assertEqual(repr(headers), str(dict(headers)))
headers.update({'X-dlp': 'data'})
self.assertEqual(set(headers.items()), {('Ytdl-Test', '2'), ('X-Dlp', 'data')})
self.assertEqual(dict(headers), {'Ytdl-Test': '2', 'X-Dlp': 'data'})
self.assertEqual(len(headers), 2)
self.assertEqual(headers.copy(), headers)
headers2 = HTTPHeaderDict({'X-dlp': 'data3'}, **headers, **{'X-dlp': 'data2'})
self.assertEqual(set(headers2.items()), {('Ytdl-Test', '2'), ('X-Dlp', 'data2')})
self.assertEqual(len(headers2), 2)
headers2.clear()
self.assertEqual(len(headers2), 0)
# ensure we prefer latter headers
headers3 = HTTPHeaderDict({'Ytdl-TeSt': 1}, {'Ytdl-test': 2})
self.assertEqual(set(headers3.items()), {('Ytdl-Test', '2')})
del headers3['ytdl-tesT']
self.assertEqual(dict(headers3), {})
headers4 = HTTPHeaderDict({'ytdl-test': 'data;'})
self.assertEqual(set(headers4.items()), {('Ytdl-Test', 'data;')})
def test_extract_basic_auth(self):
assert extract_basic_auth('http://:foo.bar') == ('http://:foo.bar', None)
assert extract_basic_auth('http://foo.bar') == ('http://foo.bar', None)
assert extract_basic_auth('http://@foo.bar') == ('http://foo.bar', 'Basic Og==')
assert extract_basic_auth('http://:pass@foo.bar') == ('http://foo.bar', 'Basic OnBhc3M=')
assert extract_basic_auth('http://user:@foo.bar') == ('http://foo.bar', 'Basic dXNlcjo=')
assert extract_basic_auth('http://user:pass@foo.bar') == ('http://foo.bar', 'Basic dXNlcjpwYXNz')
if __name__ == '__main__':
unittest.main()

392
yt_dlp/YoutubeDL.py
View file

@ -1,9 +1,10 @@
import collections
import contextlib
import copy
import datetime
import errno
import fileinput
import functools
import http.cookiejar
import io
import itertools
import json
@ -23,9 +24,9 @@
import unicodedata
from .cache import Cache
from .compat import urllib # isort: split
from .compat import compat_os_name, compat_shlex_quote
from .cookies import load_cookies
from .compat import functools, urllib # isort: split
from .compat import compat_os_name, compat_shlex_quote, urllib_req_to_req
from .cookies import LenientSimpleCookie, load_cookies
from .downloader import (
DashSegmentsFD,
FFmpegFD,
@ -37,6 +38,16 @@
from .extractor.common import UnsupportedURLIE
from .extractor.openload import PhantomJSwrapper
from .minicurses import format_text
from .networking import HEADRequest, Request, RequestDirector
from .networking.common import _REQUEST_HANDLERS
from .networking.exceptions import (
HTTPError,
NoSupportingHandlers,
RequestError,
SSLError,
_CompatHTTPError,
network_exceptions,
)
from .plugins import directories as plugin_directories
from .postprocessor import _PLUGIN_CLASSES as plugin_pps
from .postprocessor import (
@ -75,13 +86,11 @@
ExtractorError,
FormatSorter,
GeoRestrictedError,
HEADRequest,
ISO3166Utils,
LazyList,
MaxDownloadsReached,
Namespace,
PagedList,
PerRequestProxyHandler,
PlaylistEntries,
Popen,
PostProcessingError,
@ -90,9 +99,6 @@
SameFileError,
UnavailableVideoError,
UserNotLive,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
YoutubeDLRedirectHandler,
age_restricted,
args_to_str,
bug_reports_message,
@ -105,6 +111,7 @@
error_to_compat_str,
escapeHTML,
expand_path,
extract_basic_auth,
filter_dict,
float_or_none,
format_bytes,
@ -120,9 +127,6 @@
locked_file,
make_archive_id,
make_dir,
make_HTTPS_handler,
merge_headers,
network_exceptions,
number_of_digits,
orderedSet,
orderedSet_from_options,
@ -135,8 +139,6 @@
sanitize_filename,
sanitize_path,
sanitize_url,
sanitized_Request,
std_headers,
str_or_none,
strftime_or_none,
subtitles_filename,
@ -154,6 +156,13 @@
write_json_file,
write_string,
)
from .utils._utils import _YDLLogger
from .utils.networking import (
HTTPHeaderDict,
clean_headers,
clean_proxies,
std_headers,
)
from .version import CHANNEL, RELEASE_GIT_HEAD, VARIANT, __version__
if compat_os_name == 'nt':
@ -568,7 +577,7 @@ class YoutubeDL:
'width', 'height', 'aspect_ratio', 'resolution', 'dynamic_range', 'tbr', 'abr', 'acodec', 'asr', 'audio_channels',
'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx', 'rows', 'columns',
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start',
'preference', 'language', 'language_preference', 'quality', 'source_preference',
'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'hls_aes', 'downloader_options',
'page_url', 'app', 'play_path', 'tc_url', 'flash_version', 'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time'
}
@ -617,7 +626,8 @@ def __init__(self, params=None, auto_init=True):
if self.params.get('no_color'):
if self.params.get('color') is not None:
self.report_warning('Overwriting params from "color" with "no_color"')
self.params.setdefault('_warnings', []).append(
'Overwriting params from "color" with "no_color"')
self.params['color'] = 'no_color'
term_allow_color = os.environ.get('TERM', '').lower() != 'dumb'
@ -675,6 +685,13 @@ def process_color_policy(stream):
raise
self.params['compat_opts'] = set(self.params.get('compat_opts', ()))
self.params['http_headers'] = HTTPHeaderDict(std_headers, self.params.get('http_headers'))
self.__header_cookies = []
self._load_cookies(self.params['http_headers'].get('Cookie')) # compat
self.params['http_headers'].pop('Cookie', None)
self._request_director = self.build_request_director(
sorted(_REQUEST_HANDLERS.values(), key=lambda rh: rh.RH_NAME.lower()))
if auto_init and auto_init != 'no_verbose_header':
self.print_debug_header()
@ -745,9 +762,6 @@ def check_deprecated(param, option, suggestion):
else self.params['format'] if callable(self.params['format'])
else self.build_format_selector(self.params['format']))
# Set http_headers defaults according to std_headers
self.params['http_headers'] = merge_headers(std_headers, self.params.get('http_headers', {}))
hooks = {
'post_hooks': self.add_post_hook,
'progress_hooks': self.add_progress_hook,
@ -764,8 +778,6 @@ def check_deprecated(param, option, suggestion):
get_postprocessor(pp_def.pop('key'))(self, **pp_def),
when=when)
self._setup_opener()
def preload_download_archive(fn):
"""Preload the archive, if any is specified"""
archive = set()
@ -941,11 +953,17 @@ def __enter__(self):
self.save_console_title()
return self
def save_cookies(self):
if self.params.get('cookiefile') is not None:
self.cookiejar.save()
def __exit__(self, *args):
self.restore_console_title()
self.close()
if self.params.get('cookiefile') is not None:
self.cookiejar.save(ignore_discard=True, ignore_expires=True)
def close(self):
self.save_cookies()
self._request_director.close()
def trouble(self, message=None, tb=None, is_error=True):
"""Determine action to take when a download problem appears.
@ -988,6 +1006,7 @@ def trouble(self, message=None, tb=None, is_error=True):
ID='green',
DELIM='blue',
ERROR='red',
BAD_FORMAT='light red',
WARNING='yellow',
SUPPRESS='light black',
)
@ -1276,28 +1295,27 @@ def create_key(outer_mobj):
return outer_mobj.group(0)
key = outer_mobj.group('key')
mobj = re.match(INTERNAL_FORMAT_RE, key)
initial_field = mobj.group('fields') if mobj else ''
value, replacement, default = None, None, na
value, replacement, default, last_field = None, None, na, ''
while mobj:
mobj = mobj.groupdict()
default = mobj['default'] if mobj['default'] is not None else default
value = get_value(mobj)
replacement = mobj['replacement']
last_field, replacement = mobj['fields'], mobj['replacement']
if value is None and mobj['alternate']:
mobj = re.match(INTERNAL_FORMAT_RE, mobj['remaining'][1:])
else:
break
fmt = outer_mobj.group('format')
if fmt == 's' and value is not None and key in field_size_compat_map.keys():
fmt = f'0{field_size_compat_map[key]:d}d'
if None not in (value, replacement):
try:
value = replacement_formatter.format(replacement, value)
except ValueError:
value, default = None, na
fmt = outer_mobj.group('format')
if fmt == 's' and last_field in field_size_compat_map.keys() and isinstance(value, int):
fmt = f'0{field_size_compat_map[last_field]:d}d'
flags = outer_mobj.group('conversion') or ''
str_fmt = f'{fmt[:-1]}s'
if value is None:
@ -1327,7 +1345,7 @@ def create_key(outer_mobj):
value = format_decimal_suffix(value, f'%{num_fmt}f%s' if num_fmt else '%d%s',
factor=1024 if '#' in flags else 1000)
elif fmt[-1] == 'S': # filename sanitization
value, fmt = filename_sanitizer(initial_field, value, restricted='#' in flags), str_fmt
value, fmt = filename_sanitizer(last_field, value, restricted='#' in flags), str_fmt
elif fmt[-1] == 'c':
if value:
value = str(value)[0]
@ -1346,7 +1364,7 @@ def create_key(outer_mobj):
elif fmt[-1] == 'a':
value, fmt = ascii(value), str_fmt
if fmt[-1] in 'csra':
value = sanitizer(initial_field, value)
value = sanitizer(last_field, value)
key = '%s\0%s' % (key.replace('%', '%\0'), outer_mobj.group('format'))
TMPL_DICT[key] = value
@ -1481,7 +1499,10 @@ def check_filter():
return ret
if self.in_download_archive(info_dict):
reason = '%s has already been recorded in the archive' % video_title
reason = ''.join((
format_field(info_dict, 'id', f'{self._format_screen("%s", self.Styles.ID)}: '),
format_field(info_dict, 'title', f'{self._format_screen("%s", self.Styles.EMPHASIS)} '),
'has already been recorded in the archive'))
break_opt, break_err = 'break_on_existing', ExistingVideoReached
else:
try:
@ -1542,7 +1563,8 @@ def extract_info(self, url, download=True, ie_key=None, extra_info=None,
temp_id = ie.get_temp_id(url)
if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': key}):
self.to_screen(f'[{key}] {temp_id}: has already been recorded in the archive')
self.to_screen(f'[download] {self._format_screen(temp_id, self.Styles.ID)}: '
'has already been recorded in the archive')
if self.params.get('break_on_existing', False):
raise ExistingVideoReached()
break
@ -1630,8 +1652,67 @@ def progress(msg):
self.to_screen('')
raise
def _load_cookies(self, data, *, autoscope=True):
"""Loads cookies from a `Cookie` header
This tries to work around the security vulnerability of passing cookies to every domain.
See: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj
@param data The Cookie header as string to load the cookies from
@param autoscope If `False`, scope cookies using Set-Cookie syntax and error for cookie without domains
If `True`, save cookies for later to be stored in the jar with a limited scope
If a URL, save cookies in the jar with the domain of the URL
"""
for cookie in LenientSimpleCookie(data).values():
if autoscope and any(cookie.values()):
raise ValueError('Invalid syntax in Cookie Header')
domain = cookie.get('domain') or ''
expiry = cookie.get('expires')
if expiry == '': # 0 is valid
expiry = None
prepared_cookie = http.cookiejar.Cookie(
cookie.get('version') or 0, cookie.key, cookie.value, None, False,
domain, True, True, cookie.get('path') or '', bool(cookie.get('path')),
cookie.get('secure') or False, expiry, False, None, None, {})
if domain:
self.cookiejar.set_cookie(prepared_cookie)
elif autoscope is True:
self.deprecated_feature(
'Passing cookies as a header is a potential security risk; '
'they will be scoped to the domain of the downloaded urls. '
'Please consider loading cookies from a file or browser instead.')
self.__header_cookies.append(prepared_cookie)
elif autoscope:
self.report_warning(
'The extractor result contains an unscoped cookie as an HTTP header. '
f'If you are using yt-dlp with an input URL{bug_reports_message(before=",")}',
only_once=True)
self._apply_header_cookies(autoscope, [prepared_cookie])
else:
self.report_error('Unscoped cookies are not allowed; please specify some sort of scoping',
tb=False, is_error=False)
def _apply_header_cookies(self, url, cookies=None):
"""Applies stray header cookies to the provided url
This loads header cookies and scopes them to the domain provided in `url`.
While this is not ideal, it helps reduce the risk of them being sent
to an unintended destination while mostly maintaining compatibility.
"""
parsed = urllib.parse.urlparse(url)
if not parsed.hostname:
return
for cookie in map(copy.copy, cookies or self.__header_cookies):
cookie.domain = f'.{parsed.hostname}'
self.cookiejar.set_cookie(cookie)
@_handle_extraction_exceptions
def __extract_info(self, url, ie, download, extra_info, process):
self._apply_header_cookies(url)
try:
ie_result = ie.extract(url)
except UserNotLive as e:
@ -2091,8 +2172,6 @@ def syntax_error(note, start):
allow_multiple_streams = {'audio': self.params.get('allow_multiple_audio_streams', False),
'video': self.params.get('allow_multiple_video_streams', False)}
check_formats = self.params.get('check_formats') == 'selected'
def _parse_filter(tokens):
filter_parts = []
for type, string_, start, _, _ in tokens:
@ -2265,10 +2344,19 @@ def _merge(formats_pair):
return new_dict
def _check_formats(formats):
if not check_formats:
if (self.params.get('check_formats') is not None
or self.params.get('allow_unplayable_formats')):
yield from formats
return
yield from self._check_formats(formats)
elif self.params.get('check_formats') == 'selected':
yield from self._check_formats(formats)
return
for f in formats:
if f.get('has_drm'):
yield from self._check_formats([f])
else:
yield f
def _build_selector_function(selector):
if isinstance(selector, list): # ,
@ -2407,14 +2495,34 @@ def restore_last_token(self):
parsed_selector = _parse_format_selection(iter(TokenIterator(tokens)))
return _build_selector_function(parsed_selector)
def _calc_headers(self, info_dict):
res = merge_headers(self.params['http_headers'], info_dict.get('http_headers') or {})
if 'Youtubedl-No-Compression' in res: # deprecated
res.pop('Youtubedl-No-Compression', None)
res['Accept-Encoding'] = 'identity'
cookies = self.cookiejar.get_cookie_header(info_dict['url'])
def _calc_headers(self, info_dict, load_cookies=False):
res = HTTPHeaderDict(self.params['http_headers'], info_dict.get('http_headers'))
clean_headers(res)
if load_cookies: # For --load-info-json
self._load_cookies(res.get('Cookie'), autoscope=info_dict['url']) # compat
self._load_cookies(info_dict.get('cookies'), autoscope=False)
# The `Cookie` header is removed to prevent leaks and unscoped cookies.
# See: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj
res.pop('Cookie', None)
cookies = self.cookiejar.get_cookies_for_url(info_dict['url'])
if cookies:
res['Cookie'] = cookies
encoder = LenientSimpleCookie()
values = []
for cookie in cookies:
_, value = encoder.value_encode(cookie.value)
values.append(f'{cookie.name}={value}')
if cookie.domain:
values.append(f'Domain={cookie.domain}')
if cookie.path:
values.append(f'Path={cookie.path}')
if cookie.secure:
values.append('Secure')
if cookie.expires:
values.append(f'Expires={cookie.expires}')
if cookie.version:
values.append(f'Version={cookie.version}')
info_dict['cookies'] = '; '.join(values)
if 'X-Forwarded-For' not in res:
x_forwarded_for_ip = info_dict.get('__x_forwarded_for_ip')
@ -2620,10 +2728,10 @@ def sanitize_numeric_fields(info):
if field_preference:
info_dict['_format_sort_fields'] = field_preference
# or None ensures --clean-infojson removes it
info_dict['_has_drm'] = any(f.get('has_drm') for f in formats) or None
info_dict['_has_drm'] = any( # or None ensures --clean-infojson removes it
f.get('has_drm') and f['has_drm'] != 'maybe' for f in formats) or None
if not self.params.get('allow_unplayable_formats'):
formats = [f for f in formats if not f.get('has_drm')]
formats = [f for f in formats if not f.get('has_drm') or f['has_drm'] == 'maybe']
if formats and all(f.get('acodec') == f.get('vcodec') == 'none' for f in formats):
self.report_warning(
@ -2675,7 +2783,12 @@ def is_wellformed(f):
and info_dict.get('duration') and format.get('tbr')
and not format.get('filesize') and not format.get('filesize_approx')):
format['filesize_approx'] = int(info_dict['duration'] * format['tbr'] * (1024 / 8))
format['http_headers'] = self._calc_headers(collections.ChainMap(format, info_dict))
format['http_headers'] = self._calc_headers(collections.ChainMap(format, info_dict), load_cookies=True)
# Safeguard against old/insecure infojson when using --load-info-json
if info_dict.get('http_headers'):
info_dict['http_headers'] = HTTPHeaderDict(info_dict['http_headers'])
info_dict['http_headers'].pop('Cookie', None)
# This is copied to http_headers by the above _calc_headers and can now be removed
if '__x_forwarded_for_ip' in info_dict:
@ -2772,11 +2885,8 @@ def is_wellformed(f):
formats_to_download = list(format_selector({
'formats': formats,
'has_merged_format': any('none' not in (f.get('acodec'), f.get('vcodec')) for f in formats),
'incomplete_formats': (
# All formats are video-only or
all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats)
# all formats are audio-only
or all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats)),
'incomplete_formats': (all(f.get('vcodec') == 'none' for f in formats) # No formats with video
or all(f.get('acodec') == 'none' for f in formats)), # OR, No formats with audio
}))
if interactive_format_selection and not formats_to_download:
self.report_error('Requested format is not available', tb=False, is_error=False)
@ -3186,8 +3296,9 @@ def existing_video_file(*filepaths):
fd, success = None, True
if info_dict.get('protocol') or info_dict.get('url'):
fd = get_suitable_downloader(info_dict, self.params, to_stdout=temp_filename == '-')
if not (fd is FFmpegFD or fd is DashSegmentsFD) and 'no-direct-merge' not in self.params['compat_opts'] and (info_dict.get('section_start') or info_dict.get('section_end')):
msg = ('This format cannot be partially downloaded' if FFmpegFD.available()
if fd not in [FFmpegFD, DashSegmentsFD] and 'no-direct-merge' not in self.params['compat_opts'] and (
info_dict.get('section_start') or info_dict.get('section_end')):
msg = (f'This format cannot be partially downloaded {fd}' if FFmpegFD.available()
else 'You have requested downloading the video partially, but ffmpeg is not installed')
self.report_error(f'{msg}. Aborting')
return
@ -3346,7 +3457,7 @@ def ffmpeg_fixup(cndn, msg, cls):
postprocessed_by_ffmpeg = info_dict.get('requested_formats') or any((
isinstance(pp, FFmpegVideoConvertorPP)
and resolve_recode_mapping(ext, pp.mapping)[0] not in (ext, None)
) for pp in self._pps['post_process'])
) for pp in self._pps['post_process']) or fd == FFmpegFD
if not postprocessed_by_ffmpeg:
ffmpeg_fixup(ext == 'm4a' and info_dict.get('container') == 'm4a_dash',
@ -3692,7 +3803,7 @@ def render_formats_table(self, info_dict):
def simplified_codec(f, field):
assert field in ('acodec', 'vcodec')
codec = f.get(field, 'unknown')
codec = f.get(field)
if not codec:
return 'unknown'
elif codec != 'none':
@ -3727,14 +3838,13 @@ def simplified_codec(f, field):
simplified_codec(f, 'acodec'),
format_field(f, 'abr', '\t%dk', func=round),
format_field(f, 'asr', '\t%s', func=format_decimal_suffix),
join_nonempty(
self._format_out('UNSUPPORTED', 'light red') if f.get('ext') in ('f4f', 'f4m') else None,
self._format_out('DRM', 'light red') if f.get('has_drm') else None,
format_field(f, 'language', '[%s]'),
join_nonempty(format_field(f, 'format_note'),
format_field(f, 'container', ignore=(None, f.get('ext'))),
delim=', '),
delim=' '),
join_nonempty(format_field(f, 'language', '[%s]'), join_nonempty(
self._format_out('UNSUPPORTED', self.Styles.BAD_FORMAT) if f.get('ext') in ('f4f', 'f4m') else None,
(self._format_out('Maybe DRM', self.Styles.WARNING) if f.get('has_drm') == 'maybe'
else self._format_out('DRM', self.Styles.BAD_FORMAT) if f.get('has_drm') else None),
format_field(f, 'format_note'),
format_field(f, 'container', ignore=(None, f.get('ext'))),
delim=', '), delim=' '),
] for f in formats if f.get('preference') is None or f['preference'] >= -1000]
header_line = self._list_format_headers(
'ID', 'EXT', 'RESOLUTION', '\tFPS', 'HDR', 'CH', delim, '\tFILESIZE', '\tTBR', 'PROTO',
@ -3783,12 +3893,6 @@ def list_thumbnails(self, info_dict):
def list_subtitles(self, video_id, subtitles, name='subtitles'):
self.__list_table(video_id, name, self.render_subtitles_table, video_id, subtitles)
def urlopen(self, req):
""" Start an HTTP download """
if isinstance(req, str):
req = sanitized_Request(req)
return self._opener.open(req, timeout=self._socket_timeout)
def print_debug_header(self):
if not self.params.get('verbose'):
return
@ -3877,13 +3981,8 @@ def get_encoding(stream):
join_nonempty(*get_package_info(m)) for m in available_dependencies.values()
})) or 'none'))
self._setup_opener()
proxy_map = {}
for handler in self._opener.handlers:
if hasattr(handler, 'proxies'):
proxy_map.update(handler.proxies)
write_debug(f'Proxy map: {proxy_map}')
write_debug(f'Proxy map: {self.proxies}')
# write_debug(f'Request Handlers: {", ".join(rh.RH_NAME for rh in self._request_director.handlers)}')
for plugin_type, plugins in {'Extractor': plugin_ies, 'Post-Processor': plugin_pps}.items():
display_list = ['%s%s' % (
klass.__name__, '' if klass.__name__ == name else f' as {name}')
@ -3911,58 +4010,109 @@ def get_encoding(stream):
'See https://yt-dl.org/update if you need help updating.' %
latest_version)
def _setup_opener(self):
if hasattr(self, '_opener'):
return
timeout_val = self.params.get('socket_timeout')
self._socket_timeout = 20 if timeout_val is None else float(timeout_val)
opts_cookiesfrombrowser = self.params.get('cookiesfrombrowser')
opts_cookiefile = self.params.get('cookiefile')
@functools.cached_property
def proxies(self):
"""Global proxy configuration"""
opts_proxy = self.params.get('proxy')
self.cookiejar = load_cookies(opts_cookiefile, opts_cookiesfrombrowser, self)
cookie_processor = YoutubeDLCookieProcessor(self.cookiejar)
if opts_proxy is not None:
if opts_proxy == '':
proxies = {}
else:
proxies = {'http': opts_proxy, 'https': opts_proxy}
opts_proxy = '__noproxy__'
proxies = {'all': opts_proxy}
else:
proxies = urllib.request.getproxies()
# Set HTTPS proxy to HTTP one if given (https://github.com/ytdl-org/youtube-dl/issues/805)
# compat. Set HTTPS_PROXY to __noproxy__ to revert
if 'http' in proxies and 'https' not in proxies:
proxies['https'] = proxies['http']
proxy_handler = PerRequestProxyHandler(proxies)
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
redirect_handler = YoutubeDLRedirectHandler()
data_handler = urllib.request.DataHandler()
return proxies
# When passing our own FileHandler instance, build_opener won't add the
# default FileHandler and allows us to disable the file protocol, which
# can be used for malicious purposes (see
# https://github.com/ytdl-org/youtube-dl/issues/8227)
file_handler = urllib.request.FileHandler()
@functools.cached_property
def cookiejar(self):
"""Global cookiejar instance"""
return load_cookies(
self.params.get('cookiefile'), self.params.get('cookiesfrombrowser'), self)
if not self.params.get('enable_file_urls'):
def file_open(*args, **kwargs):
raise urllib.error.URLError(
'file:// URLs are explicitly disabled in yt-dlp for security reasons. '
'Use --enable-file-urls to enable at your own risk.')
file_handler.file_open = file_open
@property
def _opener(self):
"""
Get a urllib OpenerDirector from the Urllib handler (deprecated).
"""
self.deprecation_warning('YoutubeDL._opener is deprecated, use YoutubeDL.urlopen()')
handler = self._request_director.handlers['Urllib']
return handler._get_instance(cookiejar=self.cookiejar, proxies=self.proxies)
opener = urllib.request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler)
def urlopen(self, req):
""" Start an HTTP download """
if isinstance(req, str):
req = Request(req)
elif isinstance(req, urllib.request.Request):
self.deprecation_warning(
'Passing a urllib.request.Request object to YoutubeDL.urlopen() is deprecated. '
'Use yt_dlp.networking.common.Request instead.')
req = urllib_req_to_req(req)
assert isinstance(req, Request)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play
# (See https://github.com/ytdl-org/youtube-dl/issues/1309 for details)
opener.addheaders = []
self._opener = opener
# compat: Assume user:pass url params are basic auth
url, basic_auth_header = extract_basic_auth(req.url)
if basic_auth_header:
req.headers['Authorization'] = basic_auth_header
req.url = sanitize_url(url)
clean_proxies(proxies=req.proxies, headers=req.headers)
clean_headers(req.headers)
try:
return self._request_director.send(req)
except NoSupportingHandlers as e:
for ue in e.unsupported_errors:
if not (ue.handler and ue.msg):
continue
if ue.handler.RH_KEY == 'Urllib' and 'unsupported url scheme: "file"' in ue.msg.lower():
raise RequestError(
'file:// URLs are disabled by default in yt-dlp for security reasons. '
'Use --enable-file-urls to enable at your own risk.', cause=ue) from ue
raise
except SSLError as e:
if 'UNSAFE_LEGACY_RENEGOTIATION_DISABLED' in str(e):
raise RequestError('UNSAFE_LEGACY_RENEGOTIATION_DISABLED: Try using --legacy-server-connect', cause=e) from e
elif 'SSLV3_ALERT_HANDSHAKE_FAILURE' in str(e):
raise RequestError(
'SSLV3_ALERT_HANDSHAKE_FAILURE: The server may not support the current cipher list. '
'Try using --legacy-server-connect', cause=e) from e
raise
except HTTPError as e: # TODO: Remove in a future release
raise _CompatHTTPError(e) from e
def build_request_director(self, handlers):
logger = _YDLLogger(self)
headers = self.params.get('http_headers').copy()
proxies = self.proxies.copy()
clean_headers(headers)
clean_proxies(proxies, headers)
director = RequestDirector(logger=logger, verbose=self.params.get('debug_printtraffic'))
for handler in handlers:
director.add_handler(handler(
logger=logger,
headers=headers,
cookiejar=self.cookiejar,
proxies=proxies,
prefer_system_certs='no-certifi' in self.params['compat_opts'],
verify=not self.params.get('nocheckcertificate'),
**traverse_obj(self.params, {
'verbose': 'debug_printtraffic',
'source_address': 'source_address',
'timeout': 'socket_timeout',
'legacy_ssl_support': 'legacyserverconnect',
'enable_file_urls': 'enable_file_urls',
'client_cert': {
'client_certificate': 'client_certificate',
'client_certificate_key': 'client_certificate_key',
'client_certificate_password': 'client_certificate_password',
},
}),
))
return director
def encode(self, s):
if isinstance(s, bytes):
@ -4115,14 +4265,14 @@ def _write_thumbnails(self, label, info_dict, filename, thumb_filename_base=None
else:
self.to_screen(f'[info] Downloading {thumb_display_id} ...')
try:
uf = self.urlopen(sanitized_Request(t['url'], headers=t.get('http_headers', {})))
uf = self.urlopen(Request(t['url'], headers=t.get('http_headers', {})))
self.to_screen(f'[info] Writing {thumb_display_id} to: {thumb_filename}')
with open(encodeFilename(thumb_filename), 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
ret.append((thumb_filename, thumb_filename_final))
t['filepath'] = thumb_filename
except network_exceptions as err:
if isinstance(err, urllib.error.HTTPError) and err.code == 404:
if isinstance(err, HTTPError) and err.status == 404:
self.to_screen(f'[info] {thumb_display_id.title()} does not exist')
else:
self.report_warning(f'Unable to download {thumb_display_id}: {err}')

2
yt_dlp/__init__.py
View file

@ -58,11 +58,11 @@
read_stdin,
render_table,
setproctitle,
std_headers,
traverse_obj,
variadic,
write_string,
)
from .utils.networking import std_headers
from .YoutubeDL import YoutubeDL
_IN_CLI = False

3
yt_dlp/__pyinstaller/hook-yt_dlp.py
View file

@ -18,7 +18,8 @@ def pycryptodome_module():
def get_hidden_imports():
yield 'yt_dlp.compat._legacy'
yield from ('yt_dlp.compat._legacy', 'yt_dlp.compat._deprecated')
yield from ('yt_dlp.utils._legacy', 'yt_dlp.utils._deprecated')
yield pycryptodome_module()
yield from collect_submodules('websockets')
# These are auto-detected, but explicitly add them just in case

17
yt_dlp/compat/__init__.py
View file

@ -1,14 +1,11 @@
import os
import sys
import warnings
import xml.etree.ElementTree as etree
from ._deprecated import * # noqa: F401, F403
from .compat_utils import passthrough_module
# XXX: Implement this the same way as other DeprecationWarnings without circular import
passthrough_module(__name__, '._legacy', callback=lambda attr: warnings.warn(
DeprecationWarning(f'{__name__}.{attr} is deprecated'), stacklevel=5))
passthrough_module(__name__, '._deprecated')
del passthrough_module
# HTMLParseError has been deprecated in Python 3.3 and removed in
@ -70,3 +67,13 @@ def compat_expanduser(path):
return userhome + path[i:]
else:
compat_expanduser = os.path.expanduser
def urllib_req_to_req(urllib_request):
"""Convert urllib Request to a networking Request"""
from ..networking import Request
from ..utils.networking import HTTPHeaderDict
return Request(
urllib_request.get_full_url(), data=urllib_request.data, method=urllib_request.get_method(),
headers=HTTPHeaderDict(urllib_request.headers, urllib_request.unredirected_hdrs),
extensions={'timeout': urllib_request.timeout} if hasattr(urllib_request, 'timeout') else None)

9
yt_dlp/compat/_deprecated.py
View file

@ -1,4 +1,12 @@
"""Deprecated - New code should avoid these"""
import warnings
from .compat_utils import passthrough_module
# XXX: Implement this the same way as other DeprecationWarnings without circular import
passthrough_module(__name__, '.._legacy', callback=lambda attr: warnings.warn(
DeprecationWarning(f'{__name__}.{attr} is deprecated'), stacklevel=6))
del passthrough_module
import base64
import urllib.error
@ -8,7 +16,6 @@
compat_b64decode = base64.b64decode
compat_HTTPError = urllib.error.HTTPError
compat_urlparse = urllib.parse
compat_parse_qs = urllib.parse.parse_qs
compat_urllib_parse_unquote = urllib.parse.unquote

5
yt_dlp/compat/_legacy.py
View file

@ -16,12 +16,12 @@
import shutil
import socket
import struct
import subprocess
import tokenize
import urllib.error
import urllib.parse
import urllib.request
import xml.etree.ElementTree as etree
from subprocess import DEVNULL
# isort: split
import asyncio # noqa: F401
@ -70,6 +70,7 @@ def compat_setenv(key, value, env=os.environ):
compat_HTMLParser = compat_html_parser_HTMLParser = html.parser.HTMLParser
compat_http_client = http.client
compat_http_server = http.server
compat_HTTPError = urllib.error.HTTPError
compat_input = input
compat_integer_types = (int, )
compat_itertools_count = itertools.count
@ -84,7 +85,7 @@ def compat_setenv(key, value, env=os.environ):
compat_Struct = struct.Struct
compat_struct_pack = struct.pack
compat_struct_unpack = struct.unpack
compat_subprocess_get_DEVNULL = lambda: DEVNULL
compat_subprocess_get_DEVNULL = lambda: subprocess.DEVNULL
compat_tokenize_tokenize = tokenize.tokenize
compat_urllib_error = urllib.error
compat_urllib_HTTPError = urllib.error.HTTPError

13
yt_dlp/compat/types.py Normal file
View file

@ -0,0 +1,13 @@
# flake8: noqa: F405
from types import * # noqa: F403
from .compat_utils import passthrough_module
passthrough_module(__name__, 'types')
del passthrough_module
try:
# NB: pypy has builtin NoneType, so checking NameError won't work
from types import NoneType # >= 3.10
except ImportError:
NoneType = type(None)

3
yt_dlp/compat/urllib/__init__.py
View file

@ -1,6 +1,9 @@
# flake8: noqa: F405
from urllib import * # noqa: F403
del request
from . import request # noqa: F401
from ..compat_utils import passthrough_module
passthrough_module(__name__, 'urllib')

40
yt_dlp/cookies.py
View file

@ -41,30 +41,15 @@
try_call,
write_string,
)
from .utils._utils import _YDLLogger
CHROMIUM_BASED_BROWSERS = {'brave', 'chrome', 'chromium', 'edge', 'opera', 'vivaldi'}
SUPPORTED_BROWSERS = CHROMIUM_BASED_BROWSERS | {'firefox', 'safari'}
class YDLLogger:
def __init__(self, ydl=None):
self._ydl = ydl
def debug(self, message):
if self._ydl:
self._ydl.write_debug(message)
def info(self, message):
if self._ydl:
self._ydl.to_screen(f'[Cookies] {message}')
def warning(self, message, only_once=False):
if self._ydl:
self._ydl.report_warning(message, only_once)
def error(self, message):
if self._ydl:
self._ydl.report_error(message)
class YDLLogger(_YDLLogger):
def warning(self, message, only_once=False): # compat
return super().warning(message, once=only_once)
class ProgressBar(MultilinePrinter):
_DELAY, _timer = 0.1, 0
@ -112,7 +97,7 @@ def load_cookies(cookie_file, browser_specification, ydl):
jar = YoutubeDLCookieJar(cookie_file)
if not is_filename or os.access(cookie_file, os.R_OK):
jar.load(ignore_discard=True, ignore_expires=True)
jar.load()
cookie_jars.append(jar)
return _merge_cookie_jars(cookie_jars)
@ -1228,7 +1213,7 @@ def open(self, file, *, write=False):
file.truncate(0)
yield file
def _really_save(self, f, ignore_discard=False, ignore_expires=False):
def _really_save(self, f, ignore_discard, ignore_expires):
now = time.time()
for cookie in self:
if (not ignore_discard and cookie.discard
@ -1249,7 +1234,7 @@ def _really_save(self, f, ignore_discard=False, ignore_expires=False):
name, value
)))
def save(self, filename=None, *args, **kwargs):
def save(self, filename=None, ignore_discard=True, ignore_expires=True):
"""
Save cookies to a file.
Code is taken from CPython 3.6
@ -1268,9 +1253,9 @@ def save(self, filename=None, *args, **kwargs):
with self.open(filename, write=True) as f:
f.write(self._HEADER)
self._really_save(f, *args, **kwargs)
self._really_save(f, ignore_discard, ignore_expires)
def load(self, filename=None, ignore_discard=False, ignore_expires=False):
def load(self, filename=None, ignore_discard=True, ignore_expires=True):
"""Load cookies from a file."""
if filename is None:
if self.filename is not None:
@ -1327,6 +1312,13 @@ def get_cookie_header(self, url):
self.add_cookie_header(cookie_req)
return cookie_req.get_header('Cookie')
def get_cookies_for_url(self, url):
"""Generate a list of Cookie objects for a given url"""
# Policy `_now` attribute must be set before calling `_cookies_for_request`
# Ref: https://github.com/python/cpython/blob/3.7/Lib/http/cookiejar.py#L1360
self._policy._now = self._now = int(time.time())
return self._cookies_for_request(urllib.request.Request(escape_url(sanitize_url(url))))
def clear(self, *args, **kwargs):
with contextlib.suppress(KeyError):
return super().clear(*args, **kwargs)

4
yt_dlp/downloader/common.py
View file

@ -255,7 +255,8 @@ def sanitize_open(self, filename, open_mode):
@wrap_file_access('remove')
def try_remove(self, filename):
os.remove(filename)
if os.path.isfile(filename):
os.remove(filename)
@wrap_file_access('rename')
def try_rename(self, old_filename, new_filename):
@ -418,7 +419,6 @@ def download(self, filename, info_dict, subtitle=False):
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
"""
nooverwrites_and_exists = (
not self.params.get('overwrites', True)
and os.path.exists(encodeFilename(filename))

54
yt_dlp/downloader/external.py
View file

@ -1,14 +1,16 @@
import enum
import json
import os.path
import os
import re
import subprocess
import sys
import tempfile
import time
import uuid
from .fragment import FragmentFD
from ..compat import functools
from ..networking import Request
from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
from ..utils import (
Popen,
@ -24,7 +26,6 @@
encodeFilename,
find_available_port,
remove_end,
sanitized_Request,
traverse_obj,
)
@ -42,6 +43,7 @@ class ExternalFD(FragmentFD):
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
self._cookies_tempfile = None
try:
started = time.time()
@ -54,6 +56,9 @@ def real_download(self, filename, info_dict):
# should take place
retval = 0
self.to_screen('[%s] Interrupted by user' % self.get_basename())
finally:
if self._cookies_tempfile:
self.try_remove(self._cookies_tempfile)
if retval == 0:
status = {
@ -125,6 +130,16 @@ def _configuration_args(self, keys=None, *args, **kwargs):
self.get_basename(), self.params.get('external_downloader_args'), self.EXE_NAME,
keys, *args, **kwargs)
def _write_cookies(self):
if not self.ydl.cookiejar.filename:
tmp_cookies = tempfile.NamedTemporaryFile(suffix='.cookies', delete=False)
tmp_cookies.close()
self._cookies_tempfile = tmp_cookies.name
self.to_screen(f'[download] Writing temporary cookies file to "{self._cookies_tempfile}"')
# real_download resets _cookies_tempfile; if it's None then save() will write to cookiejar.filename
self.ydl.cookiejar.save(self._cookies_tempfile)
return self.ydl.cookiejar.filename or self._cookies_tempfile
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
@ -184,6 +199,9 @@ class CurlFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename, '--compressed']
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
if cookie_header:
cmd += ['--cookie', cookie_header]
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', f'{key}: {val}']
@ -214,6 +232,9 @@ def _make_cmd(self, tmpfilename, info_dict):
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['-H', f'{key}: {val}']
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
if cookie_header:
cmd += ['-H', f'Cookie: {cookie_header}', '--max-redirect=0']
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
@ -223,7 +244,9 @@ class WgetFD(ExternalFD):
AVAILABLE_OPT = '--version'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies', '--compression=auto']
cmd = [self.exe, '-O', tmpfilename, '-nv', '--compression=auto']
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
cmd += ['--load-cookies', self._write_cookies()]
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', f'{key}: {val}']
@ -271,7 +294,7 @@ def _call_downloader(self, tmpfilename, info_dict):
return super()._call_downloader(tmpfilename, info_dict)
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c',
cmd = [self.exe, '-c', '--no-conf',
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
'--http-accept-gzip=true', '--file-allocation=none', '-x16', '-j16', '-s16']
if 'fragments' in info_dict:
@ -279,6 +302,8 @@ def _make_cmd(self, tmpfilename, info_dict):
else:
cmd += ['--min-split-size', '1M']
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
cmd += [f'--load-cookies={self._write_cookies()}']
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', f'{key}: {val}']
@ -333,13 +358,12 @@ def aria2c_rpc(self, rpc_port, rpc_secret, method, params=()):
'method': method,
'params': [f'token:{rpc_secret}', *params],
}).encode('utf-8')
request = sanitized_Request(
request = Request(
f'http://localhost:{rpc_port}/jsonrpc',
data=d, headers={
'Content-Type': 'application/json',
'Content-Length': f'{len(d)}',
'Ytdl-request-proxy': '__noproxy__',
})
}, proxies={'all': None})
with self.ydl.urlopen(request) as r:
resp = json.load(r)
assert resp.get('id') == sanitycheck, 'Something went wrong with RPC server'
@ -417,6 +441,14 @@ def _make_cmd(self, tmpfilename, info_dict):
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += [f'{key}:{val}']
# httpie 3.1.0+ removes the Cookie header on redirect, so this should be safe for now. [1]
# If we ever need cookie handling for redirects, we can export the cookiejar into a session. [2]
# 1: https://github.com/httpie/httpie/security/advisories/GHSA-9w4w-cpc8-h2fq
# 2: https://httpie.io/docs/cli/sessions
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
if cookie_header:
cmd += [f'Cookie:{cookie_header}']
return cmd
@ -527,7 +559,13 @@ def _call_downloader(self, tmpfilename, info_dict):
selected_formats = info_dict.get('requested_formats') or [info_dict]
for i, fmt in enumerate(selected_formats):
if fmt.get('http_headers') and 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(
f'{cookie.name}={cookie.value}; path={cookie.path}; domain={cookie.domain};\r\n'
for cookie in cookies)])
if fmt.get('http_headers') and is_http:
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
args.extend(['-headers', ''.join(f'{key}: {val}\r\n' for key, val in fmt['http_headers'].items())])

8
yt_dlp/downloader/f4m.py
View file

@ -3,11 +3,11 @@
import itertools
import struct
import time
import urllib.error
import urllib.parse
from .fragment import FragmentFD
from ..compat import compat_etree_fromstring
from ..networking.exceptions import HTTPError
from ..utils import fix_xml_ampersands, xpath_text
@ -312,7 +312,7 @@ def real_download(self, filename, info_dict):
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.geturl()
man_url = urlh.url
# Some manifests may be malformed, e.g. prosiebensat1 generated manifests
# (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244
# and https://github.com/ytdl-org/youtube-dl/issues/7823)
@ -407,8 +407,8 @@ def real_download(self, filename, info_dict):
if box_type == b'mdat':
self._append_fragment(ctx, box_data)
break
except urllib.error.HTTPError as err:
if live and (err.code == 404 or err.code == 410):
except HTTPError as err:
if live and (err.status == 404 or err.status == 410):
# We didn't keep up with the live window. Continue
# with the next available fragment.
msg = 'Fragment %d unavailable' % frag_i

23
yt_dlp/downloader/fragment.py
View file

@ -1,24 +1,19 @@
import concurrent.futures
import contextlib
import http.client
import json
import math
import os
import struct
import time
import urllib.error
from .common import FileDownloader
from .http import HttpFD
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import compat_os_name
from ..utils import (
DownloadError,
RetryManager,
encodeFilename,
sanitized_Request,
traverse_obj,
)
from ..networking import Request
from ..networking.exceptions import HTTPError, IncompleteRead
from ..utils import DownloadError, RetryManager, encodeFilename, traverse_obj
from ..utils.networking import HTTPHeaderDict
class HttpQuietDownloader(HttpFD):
@ -75,7 +70,7 @@ def report_skip_fragment(self, frag_index, err=None):
def _prepare_url(self, info_dict, url):
headers = info_dict.get('http_headers')
return sanitized_Request(url, None, headers) if headers else url
return Request(url, None, headers) if headers else url
def _prepare_and_start_frag_download(self, ctx, info_dict):
self._prepare_frag_download(ctx)
@ -300,9 +295,7 @@ def frag_progress_hook(s):
def _finish_frag_download(self, ctx, info_dict):
ctx['dest_stream'].close()
if self.__do_ytdl_file(ctx):
ytdl_filename = encodeFilename(self.ytdl_filename(ctx['filename']))
if os.path.isfile(ytdl_filename):
self.try_remove(ytdl_filename)
self.try_remove(self.ytdl_filename(ctx['filename']))
elapsed = time.time() - ctx['started']
to_file = ctx['tmpfilename'] != '-'
@ -459,7 +452,7 @@ def download_fragment(fragment, ctx):
frag_index = ctx['fragment_index'] = fragment['frag_index']
ctx['last_error'] = None
headers = info_dict.get('http_headers', {}).copy()
headers = HTTPHeaderDict(info_dict.get('http_headers'))
byte_range = fragment.get('byte_range')
if byte_range:
headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
@ -479,7 +472,7 @@ def error_callback(err, count, retries):
if not self._download_fragment(
ctx, fragment['url'], info_dict, headers, info_dict.get('request_data')):
return
except (urllib.error.HTTPError, http.client.IncompleteRead) as err:
except (HTTPError, IncompleteRead) as err:
retry.error = err
continue
except DownloadError: # has own retry settings

32
yt_dlp/downloader/hls.py
View file

@ -28,7 +28,16 @@ class HlsFD(FragmentFD):
FD_NAME = 'hlsnative'
@staticmethod
def can_download(manifest, info_dict, allow_unplayable_formats=False):
def _has_drm(manifest): # TODO: https://github.com/yt-dlp/yt-dlp/pull/5039
return bool(re.search('|'.join((
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
r'#EXT-X-(?:SESSION-)?KEY:.*?KEYFORMAT="com\.apple\.streamingkeydelivery"', # Apple FairPlay
r'#EXT-X-(?:SESSION-)?KEY:.*?KEYFORMAT="com\.microsoft\.playready"', # Microsoft PlayReady
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
)), manifest))
@classmethod
def can_download(cls, manifest, info_dict, allow_unplayable_formats=False):
UNSUPPORTED_FEATURES = [
# r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
@ -50,13 +59,15 @@ def can_download(manifest, info_dict, allow_unplayable_formats=False):
]
if not allow_unplayable_formats:
UNSUPPORTED_FEATURES += [
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1], but not necessarily DRM
]
def check_results():
yield not info_dict.get('is_live')
for feature in UNSUPPORTED_FEATURES:
yield not re.search(feature, manifest)
if not allow_unplayable_formats:
yield not cls._has_drm(manifest)
return all(check_results())
def real_download(self, filename, info_dict):
@ -64,7 +75,7 @@ def real_download(self, filename, info_dict):
self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.geturl()
man_url = urlh.url
s = urlh.read().decode('utf-8', 'ignore')
can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None
@ -81,14 +92,13 @@ def real_download(self, filename, info_dict):
message = ('Live HLS streams are not supported by the native downloader. If this is a livestream, '
f'please {install_ffmpeg}add "--downloader ffmpeg --hls-use-mpegts" to your command')
if not can_download:
has_drm = re.search('|'.join([
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
]), s)
if has_drm and not self.params.get('allow_unplayable_formats'):
self.report_error(
'This video is DRM protected; Try selecting another format with --format or '
'add --check-formats to automatically fallback to the next best format')
if self._has_drm(s) and not self.params.get('allow_unplayable_formats'):
if info_dict.get('has_drm') and self.params.get('test'):
self.to_screen(f'[{self.FD_NAME}] This format is DRM protected', skip_eol=True)
else:
self.report_error(
'This format is DRM protected; Try selecting another format with --format or '
'add --check-formats to automatically fallback to the next best format', tb=False)
return False
message = message or 'Unsupported features have been detected'
fd = FFmpegFD(self.ydl, self.params)

73
yt_dlp/downloader/http.py
View file

@ -1,12 +1,14 @@
import http.client
import os
import random
import socket
import ssl
import time
import urllib.error
from .common import FileDownloader
from ..networking import Request
from ..networking.exceptions import (
CertificateVerifyError,
HTTPError,
TransportError,
)
from ..utils import (
ContentTooShortError,
RetryManager,
@ -16,18 +18,10 @@
encodeFilename,
int_or_none,
parse_http_range,
sanitized_Request,
try_call,
write_xattr,
)
RESPONSE_READ_EXCEPTIONS = (
TimeoutError,
socket.timeout, # compat: py < 3.10
ConnectionError,
ssl.SSLError,
http.client.HTTPException
)
from ..utils.networking import HTTPHeaderDict
class HttpFD(FileDownloader):
@ -46,10 +40,7 @@ class DownloadContext(dict):
ctx.stream = None
# Disable compression
headers = {'Accept-Encoding': 'identity'}
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
headers = HTTPHeaderDict({'Accept-Encoding': 'identity'}, info_dict.get('http_headers'))
is_test = self.params.get('test', False)
chunk_size = self._TEST_FILE_SIZE if is_test else (
@ -120,10 +111,10 @@ def establish_connection():
if try_call(lambda: range_end >= ctx.content_len):
range_end = ctx.content_len - 1
request = sanitized_Request(url, request_data, headers)
request = Request(url, request_data, headers)
has_range = range_start is not None
if has_range:
request.add_header('Range', f'bytes={int(range_start)}-{int_or_none(range_end) or ""}')
request.headers['Range'] = f'bytes={int(range_start)}-{int_or_none(range_end) or ""}'
# Establish connection
try:
ctx.data = self.ydl.urlopen(request)
@ -154,17 +145,17 @@ def establish_connection():
self.report_unable_to_resume()
ctx.resume_len = 0
ctx.open_mode = 'wb'
ctx.data_len = ctx.content_len = int_or_none(ctx.data.info().get('Content-length', None))
except urllib.error.HTTPError as err:
if err.code == 416:
ctx.data_len = ctx.content_len = int_or_none(ctx.data.headers.get('Content-length', None))
except HTTPError as err:
if err.status == 416:
# Unable to resume (requested range not satisfiable)
try:
# Open the connection again without the range header
ctx.data = self.ydl.urlopen(
sanitized_Request(url, request_data, headers))
content_length = ctx.data.info()['Content-Length']
except urllib.error.HTTPError as err:
if err.code < 500 or err.code >= 600:
Request(url, request_data, headers))
content_length = ctx.data.headers['Content-Length']
except HTTPError as err:
if err.status < 500 or err.status >= 600:
raise
else:
# Examine the reported length
@ -192,17 +183,13 @@ def establish_connection():
ctx.resume_len = 0
ctx.open_mode = 'wb'
return
elif err.code < 500 or err.code >= 600:
elif err.status < 500 or err.status >= 600:
# Unexpected HTTP error
raise
raise RetryDownload(err)
except urllib.error.URLError as err:
if isinstance(err.reason, ssl.CertificateError):
raise
raise RetryDownload(err)
# In urllib.request.AbstractHTTPHandler, the response is partially read on request.
# Any errors that occur during this will not be wrapped by URLError
except RESPONSE_READ_EXCEPTIONS as err:
except CertificateVerifyError:
raise
except TransportError as err:
raise RetryDownload(err)
def close_stream():
@ -212,9 +199,9 @@ def close_stream():
ctx.stream = None
def download():
data_len = ctx.data.info().get('Content-length')
data_len = ctx.data.headers.get('Content-length')
if ctx.data.info().get('Content-encoding'):
if ctx.data.headers.get('Content-encoding'):
# Content-encoding is present, Content-length is not reliable anymore as we are
# doing auto decompression. (See: https://github.com/yt-dlp/yt-dlp/pull/6176)
data_len = None
@ -258,7 +245,7 @@ def retry(e):
try:
# Download and write
data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
except RESPONSE_READ_EXCEPTIONS as err:
except TransportError as err:
retry(err)
byte_counter += len(data_block)
@ -339,15 +326,15 @@ def retry(e):
elif speed:
ctx.throttle_start = None
if not is_test and ctx.chunk_size and ctx.content_len is not None and byte_counter < ctx.content_len:
ctx.resume_len = byte_counter
# ctx.block_size = block_size
raise NextFragment()
if ctx.stream is None:
self.to_stderr('\n')
self.report_error('Did not get any data blocks')
return False
if not is_test and ctx.chunk_size and ctx.content_len is not None and byte_counter < ctx.content_len:
ctx.resume_len = byte_counter
raise NextFragment()
if ctx.tmpfilename != '-':
ctx.stream.close()
@ -359,7 +346,7 @@ def retry(e):
# Update file modification time
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.info().get('last-modified', None))
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.headers.get('last-modified', None))
self._hook_progress({
'downloaded_bytes': byte_counter,

4
yt_dlp/downloader/ism.py
View file

@ -2,9 +2,9 @@
import io
import struct
import time
import urllib.error
from .fragment import FragmentFD
from ..networking.exceptions import HTTPError
from ..utils import RetryManager
u8 = struct.Struct('>B')
@ -271,7 +271,7 @@ def real_download(self, filename, info_dict):
write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
extra_state['ism_track_written'] = True
self._append_fragment(ctx, frag_content)
except urllib.error.HTTPError as err:
except HTTPError as err:
retry.error = err
continue

11
yt_dlp/downloader/niconico.py
View file

@ -5,13 +5,8 @@
from . import get_suitable_downloader
from .common import FileDownloader
from .external import FFmpegFD
from ..utils import (
DownloadError,
WebSocketsWrapper,
sanitized_Request,
str_or_none,
try_get,
)
from ..networking import Request
from ..utils import DownloadError, WebSocketsWrapper, str_or_none, try_get
class NiconicoDmcFD(FileDownloader):
@ -33,7 +28,7 @@ def real_download(self, filename, info_dict):
heartbeat_data = heartbeat_info_dict['data'].encode()
heartbeat_interval = heartbeat_info_dict.get('interval', 30)
request = sanitized_Request(heartbeat_url, heartbeat_data)
request = Request(heartbeat_url, heartbeat_data)
def heartbeat():
try:

10
yt_dlp/downloader/youtube_live_chat.py
View file

@ -1,8 +1,8 @@
import json
import time
import urllib.error
from .fragment import FragmentFD
from ..networking.exceptions import HTTPError
from ..utils import (
RegexNotFoundError,
RetryManager,
@ -10,6 +10,7 @@
int_or_none,
try_get,
)
from ..utils.networking import HTTPHeaderDict
class YoutubeLiveChatFD(FragmentFD):
@ -37,10 +38,7 @@ def real_download(self, filename, info_dict):
start_time = int(time.time() * 1000)
def dl_fragment(url, data=None, headers=None):
http_headers = info_dict.get('http_headers', {})
if headers:
http_headers = http_headers.copy()
http_headers.update(headers)
http_headers = HTTPHeaderDict(info_dict.get('http_headers'), headers)
return self._download_fragment(ctx, url, info_dict, http_headers, data)
def parse_actions_replay(live_chat_continuation):
@ -129,7 +127,7 @@ def download_and_parse_fragment(url, frag_index, request_data=None, headers=None
or frag_index == 1 and try_refresh_replay_beginning
or parse_actions_replay)
return (True, *func(live_chat_continuation))
except urllib.error.HTTPError as err:
except HTTPError as err:
retry.error = err
continue
return False, None, None, None

12
yt_dlp/extractor/_extractors.py
View file

@ -15,7 +15,6 @@
YoutubeSearchURLIE,
YoutubeMusicSearchURLIE,
YoutubeSubscriptionsIE,
YoutubeStoriesIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
YoutubeYtBeIE,
@ -215,6 +214,7 @@
from .bilibili import (
BiliBiliIE,
BiliBiliBangumiIE,
BiliBiliBangumiSeasonIE,
BiliBiliBangumiMediaIE,
BiliBiliSearchIE,
BilibiliCategoryIE,
@ -1012,6 +1012,7 @@
LyndaCourseIE
)
from .m6 import M6IE
from .magellantv import MagellanTVIE
from .magentamusik360 import MagentaMusik360IE
from .mailru import (
MailRuIE,
@ -1141,6 +1142,7 @@
)
from .muenchentv import MuenchenTVIE
from .murrtube import MurrtubeIE, MurrtubeUserIE
from .museai import MuseAIIE
from .musescore import MuseScoreIE
from .musicdex import (
MusicdexSongIE,
@ -1531,6 +1533,7 @@
)
from .puls4 import Puls4IE
from .pyvideo import PyvideoIE
from .qdance import QDanceIE
from .qingting import QingTingIE
from .qqmusic import (
QQMusicIE,
@ -1854,6 +1857,10 @@
SRGSSRPlayIE,
)
from .srmediathek import SRMediathekIE
from .stacommu import (
StacommuLiveIE,
StacommuVODIE,
)
from .stanfordoc import StanfordOpenClassroomIE
from .startv import StarTVIE
from .steam import (
@ -1866,7 +1873,6 @@
StoryFireSeriesIE,
)
from .streamable import StreamableIE
from .streamanity import StreamanityIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streamff import StreamFFIE
@ -2267,6 +2273,8 @@
VKIE,
VKUserVideosIE,
VKWallPostIE,
VKPlayIE,
VKPlayLiveIE,
)
from .vocaroo import VocarooIE
from .vodlocker import VodlockerIE

15
yt_dlp/extractor/abc.py
View file

@ -12,6 +12,7 @@
int_or_none,
parse_iso8601,
str_or_none,
traverse_obj,
try_get,
unescapeHTML,
update_url_query,
@ -85,6 +86,15 @@ class ABCIE(InfoExtractor):
'uploader': 'Behind the News',
'uploader_id': 'behindthenews',
}
}, {
'url': 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540',
'info_dict': {
'id': '102520540',
'title': 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus',
'ext': 'mp4',
'description': 'Wagner troops leave Rostov-on-Don and\xa0Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.',
'thumbnail': 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485',
}
}]
def _real_extract(self, url):
@ -107,7 +117,7 @@ def _real_extract(self, url):
video = True
if mobj is None:
mobj = re.search(r'(?P<type>)"sources": (?P<json_data>\[[^\]]+\]),', webpage)
mobj = re.search(r'(?P<type>)"(?:sources|files|renditions)":\s*(?P<json_data>\[[^\]]+\])', webpage)
if mobj is None:
mobj = re.search(
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
@ -121,7 +131,8 @@ def _real_extract(self, url):
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
youtube = mobj.group('type') == 'YouTube'
video = mobj.group('type') == 'Video' or urls_info[0]['contentType'] == 'video/mp4'
video = mobj.group('type') == 'Video' or traverse_obj(
urls_info, (0, ('contentType', 'MIMEType')), get_all=False) == 'video/mp4'
if not isinstance(urls_info, list):
urls_info = [urls_info]

82
yt_dlp/extractor/abematv.py
View file

@ -22,80 +22,23 @@
int_or_none,
intlist_to_bytes,
OnDemandPagedList,
request_to_url,
time_seconds,
traverse_obj,
update_url_query,
)
# NOTE: network handler related code is temporary thing until network stack overhaul PRs are merged (#2861/#2862)
def add_opener(ydl, handler):
''' Add a handler for opening URLs, like _download_webpage '''
def add_opener(ydl, handler): # FIXME: Create proper API in .networking
"""Add a handler for opening URLs, like _download_webpage"""
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
ydl._opener.add_handler(handler)
def remove_opener(ydl, handler):
'''
Remove handler(s) for opening URLs
@param handler Either handler object itself or handler type.
Specifying handler type will remove all handler which isinstance returns True.
'''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
opener = ydl._opener
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
if isinstance(handler, (type, tuple)):
find_cp = lambda x: isinstance(x, handler)
else:
find_cp = lambda x: x is handler
removed = []
for meth in dir(handler):
if meth in ["redirect_request", "do_open", "proxy_open"]:
# oops, coincidental match
continue
i = meth.find("_")
protocol = meth[:i]
condition = meth[i + 1:]
if condition.startswith("error"):
j = condition.find("_") + i + 1
kind = meth[j + 1:]
try:
kind = int(kind)
except ValueError:
pass
lookup = opener.handle_error.get(protocol, {})
opener.handle_error[protocol] = lookup
elif condition == "open":
kind = protocol
lookup = opener.handle_open
elif condition == "response":
kind = protocol
lookup = opener.process_response
elif condition == "request":
kind = protocol
lookup = opener.process_request
else:
continue
handlers = lookup.setdefault(kind, [])
if handlers:
handlers[:] = [x for x in handlers if not find_cp(x)]
removed.append(x for x in handlers if find_cp(x))
if removed:
for x in opener.handlers:
if find_cp(x):
x.add_parent(None)
opener.handlers[:] = [x for x in opener.handlers if not find_cp(x)]
rh = ydl._request_director.handlers['Urllib']
if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
return
opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=ydl.proxies)
assert isinstance(opener, urllib.request.OpenerDirector)
opener.add_handler(handler)
rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
class AbemaLicenseHandler(urllib.request.BaseHandler):
@ -137,11 +80,11 @@ def _get_videokey_from_ticket(self, ticket):
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = request_to_url(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': len(response_data),
'Content-Length': str(len(response_data)),
}, url=url, code=200)
@ -213,10 +156,7 @@ def _get_device_token(self):
})
AbemaTVBaseIE._USERTOKEN = user_data['token']
# don't allow adding it 2 times or more, though it's guarded
remove_opener(self._downloader, AbemaLicenseHandler)
add_opener(self._downloader, AbemaLicenseHandler(self))
return self._USERTOKEN
def _get_media_token(self, invalidate=False, to_show=True):

16
yt_dlp/extractor/adn.py
View file

@ -6,10 +6,8 @@
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import (
compat_HTTPError,
compat_b64decode,
)
from ..compat import compat_b64decode
from ..networking.exceptions import HTTPError
from ..utils import (
ass_subtitles_timecode,
bytes_to_intlist,
@ -142,9 +140,9 @@ def _perform_login(self, username, password):
self._HEADERS = {'authorization': 'Bearer ' + access_token}
except ExtractorError as e:
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
e.cause.response.read().decode(), None, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
@ -195,14 +193,14 @@ def _real_extract(self, url):
})
break
except ExtractorError as e:
if not isinstance(e.cause, compat_HTTPError):
if not isinstance(e.cause, HTTPError):
raise e
if e.cause.code == 401:
if e.cause.status == 401:
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
error = self._parse_json(e.cause.response.read(), video_id)
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)

22
yt_dlp/extractor/adobepass.py
View file

@ -2,11 +2,11 @@
import json
import re
import time
import urllib.error
import xml.etree.ElementTree as etree
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import (
NO_DEFAULT,
ExtractorError,
@ -1394,7 +1394,7 @@ def post_form(form_page_res, note, data={}):
form_page, urlh = form_page_res
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url):
post_url = compat_urlparse.urljoin(urlh.geturl(), post_url)
post_url = compat_urlparse.urljoin(urlh.url, post_url)
form_data = self._hidden_inputs(form_page)
form_data.update(data)
return self._download_webpage_handle(
@ -1473,7 +1473,7 @@ def extract_redirect_url(html, url=None, fatal=False):
elif 'automatically signed in with' in provider_redirect_page:
# Seems like comcast is rolling up new way of automatically signing customers
oauth_redirect_url = self._html_search_regex(
r'continue:\s*"(https://oauth.xfinity.com/oauth/authorize\?.+)"', provider_redirect_page,
r'continue:\s*"(https://oauth\.xfinity\.com/oauth/authorize\?.+)"', provider_redirect_page,
'oauth redirect (signed)')
# Just need to process the request. No useful data comes back
self._download_webpage(oauth_redirect_url, video_id, 'Confirming auto login')
@ -1619,7 +1619,7 @@ def extract_redirect_url(html, url=None, fatal=False):
hidden_data['history'] = 1
provider_login_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending first bookend',
urlh.url, video_id, 'Sending first bookend',
query=hidden_data)
provider_association_redirect, urlh = post_form(
@ -1629,7 +1629,7 @@ def extract_redirect_url(html, url=None, fatal=False):
})
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl())
provider_association_redirect, url=urlh.url)
last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
@ -1638,7 +1638,7 @@ def extract_redirect_url(html, url=None, fatal=False):
hidden_data['history'] = 3
mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending final bookend',
urlh.url, video_id, 'Sending final bookend',
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
@ -1652,7 +1652,7 @@ def extract_redirect_url(html, url=None, fatal=False):
hidden_data['history_val'] = 1
provider_login_redirect_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending First Bookend',
urlh.url, video_id, 'Sending First Bookend',
query=hidden_data)
provider_login_redirect_page, urlh = provider_login_redirect_page_res
@ -1680,7 +1680,7 @@ def extract_redirect_url(html, url=None, fatal=False):
})
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl())
provider_association_redirect, url=urlh.url)
last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
@ -1690,7 +1690,7 @@ def extract_redirect_url(html, url=None, fatal=False):
hidden_data['history_val'] = 3
mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending Final Bookend',
urlh.url, video_id, 'Sending Final Bookend',
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
@ -1699,7 +1699,7 @@ def extract_redirect_url(html, url=None, fatal=False):
# based redirect that should be followed.
provider_redirect_page, urlh = provider_redirect_page_res
provider_refresh_redirect_url = extract_redirect_url(
provider_redirect_page, url=urlh.geturl())
provider_redirect_page, url=urlh.url)
if provider_refresh_redirect_url:
provider_redirect_page_res = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
@ -1724,7 +1724,7 @@ def extract_redirect_url(html, url=None, fatal=False):
'requestor_id': requestor_id,
}), headers=mvpd_headers)
except ExtractorError as e:
if not mso_id and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401:
if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
raise_mvpd_required()
raise
if '<pendingLogout' in session:

6
yt_dlp/extractor/adultswim.py
View file

@ -170,8 +170,10 @@ def _real_extract(self, url):
continue
ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
if ext == 'm3u8':
info['formats'].extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
info['formats'].extend(fmts)
self._merge_subtitles(subs, target=info['subtitles'])
elif ext == 'f4m':
continue
# info['formats'].extend(self._extract_f4m_formats(

4
yt_dlp/extractor/ant1newsgr.py
View file

@ -1,8 +1,8 @@
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
HEADRequest,
ExtractorError,
determine_ext,
scale_thumbnails_to_max_format_width,
@ -121,7 +121,7 @@ def _real_extract(self, url):
canonical_url = self._request_webpage(
HEADRequest(url), video_id,
note='Resolve canonical player URL',
errnote='Could not resolve canonical player URL').geturl()
errnote='Could not resolve canonical player URL').url
_, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url)
cid = urllib.parse.parse_qs(query)['cid'][0]

12
yt_dlp/extractor/archiveorg.py
View file

@ -1,16 +1,16 @@
import json
import re
import urllib.error
import urllib.parse
from .common import InfoExtractor
from .naver import NaverBaseIE
from .youtube import YoutubeBaseInfoExtractor, YoutubeIE
from ..compat import compat_HTTPError, compat_urllib_parse_unquote
from ..compat import compat_urllib_parse_unquote
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
HEADRequest,
bug_reports_message,
clean_html,
dict_get,
@ -899,7 +899,7 @@ def _real_extract(self, url):
video_id, note='Fetching archived video file url', expected_status=True)
except ExtractorError as e:
# HTTP Error 404 is expected if the video is not saved.
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
if isinstance(e.cause, HTTPError) and e.cause.status == 404:
self.raise_no_formats(
'The requested video is not archived, indexed, or there is an issue with web.archive.org (try again later)', expected=True)
else:
@ -926,7 +926,7 @@ def _real_extract(self, url):
info['thumbnails'] = self._extract_thumbnails(video_id)
if urlh:
url = compat_urllib_parse_unquote(urlh.geturl())
url = compat_urllib_parse_unquote(urlh.url)
video_file_url_qs = parse_qs(url)
# Attempt to recover any ext & format info from playback url & response headers
format = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
@ -1052,7 +1052,7 @@ def _download_archived_page(self, url, video_id, *, timestamp='2', **kwargs):
try:
return self._download_webpage(f'https://web.archive.org/web/{timestamp}id_/{url}', video_id, **kwargs)
except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404:
if isinstance(e.cause, HTTPError) and e.cause.status == 404:
raise ExtractorError('Page was not archived', expected=True)
retry.error = e
continue

6
yt_dlp/extractor/atresplayer.py
View file

@ -1,5 +1,5 @@
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
@ -34,8 +34,8 @@ class AtresPlayerIE(InfoExtractor):
_API_BASE = 'https://api.atresplayer.com/'
def _handle_error(self, e, code):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
error = self._parse_json(e.cause.read(), None)
if isinstance(e.cause, HTTPError) and e.cause.status == code:
error = self._parse_json(e.cause.response.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)

14
yt_dlp/extractor/bbc.py
View file

@ -2,11 +2,11 @@
import itertools
import json
import re
import urllib.error
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import compat_HTTPError, compat_str, compat_urlparse
from ..compat import compat_str, compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -277,7 +277,7 @@ def _perform_login(self, username, password):
post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Referer': self._LOGIN_URL})
if self._LOGIN_URL in urlh.geturl():
if self._LOGIN_URL in urlh.url:
error = clean_html(get_element_by_class('form-message', response))
if error:
raise ExtractorError(
@ -388,8 +388,8 @@ def _process_media_selector(self, media_selection, programme_id):
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
except ExtractorError as e:
if not (isinstance(e.exc_info[1], urllib.error.HTTPError)
and e.exc_info[1].code in (403, 404)):
if not (isinstance(e.exc_info[1], HTTPError)
and e.exc_info[1].status in (403, 404)):
raise
fmts = []
formats.extend(fmts)
@ -472,7 +472,7 @@ def _download_playlist(self, playlist_id):
return programme_id, title, description, duration, formats, subtitles
except ExtractorError as ee:
if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
if not (isinstance(ee.cause, HTTPError) and ee.cause.status == 404):
raise
# fallback to legacy playlist
@ -983,7 +983,7 @@ def _real_extract(self, url):
# Some playlist URL may fail with 500, at the same time
# the other one may work fine (e.g.
# http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
if isinstance(e.cause, HTTPError) and e.cause.status == 500:
continue
raise
if entry:

133
yt_dlp/extractor/bilibili.py
View file

@ -4,11 +4,11 @@
import itertools
import math
import time
import urllib.error
import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from ..dependencies import Cryptodome
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
GeoRestrictedError,
@ -18,6 +18,7 @@
float_or_none,
format_field,
int_or_none,
join_nonempty,
make_archive_id,
merge_dicts,
mimetype2ext,
@ -135,6 +136,17 @@ def _get_all_children(self, reply):
for children in map(self._get_all_children, traverse_obj(reply, ('replies', ...))):
yield from children
def _get_episodes_from_season(self, ss_id, url):
season_info = self._download_json(
'https://api.bilibili.com/pgc/web/season/section', ss_id,
note='Downloading season info', query={'season_id': ss_id},
headers={'Referer': url, **self.geo_verification_headers()})
for entry in traverse_obj(season_info, (
'result', 'main_section', 'episodes',
lambda _, v: url_or_none(v['share_url']) and v['id'])):
yield self.url_result(entry['share_url'], BiliBiliBangumiIE, f'ep{entry["id"]}')
class BiliBiliIE(BilibiliBaseIE):
_VALID_URL = r'https?://www\.bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
@ -403,76 +415,93 @@ def _real_extract(self, url):
class BiliBiliBangumiIE(BilibiliBaseIE):
_VALID_URL = r'(?x)https?://www\.bilibili\.com/bangumi/play/(?P<id>(?:ss|ep)\d+)'
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/play/(?P<id>ep\d+)'
_TESTS = [{
'url': 'https://www.bilibili.com/bangumi/play/ss897',
'url': 'https://www.bilibili.com/bangumi/play/ep267851',
'info_dict': {
'id': 'ss897',
'id': '267851',
'ext': 'mp4',
'series': '神的记事本',
'season': '神的记事本',
'season_id': 897,
'series': '鬼灭之刃',
'series_id': '4358',
'season': '鬼灭之刃',
'season_id': '26801',
'season_number': 1,
'episode': '你与旅行包',
'episode_number': 2,
'title': '神的记事本：第2话 你与旅行包',
'duration': 1428.487,
'timestamp': 1310809380,
'upload_date': '20110716',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'episode': '残酷',
'episode_id': '267851',
'episode_number': 1,
'title': '1 残酷',
'duration': 1425.256,
'timestamp': 1554566400,
'upload_date': '20190406',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
},
}, {
'url': 'https://www.bilibili.com/bangumi/play/ep508406',
'only_matching': True,
'skip': 'According to the copyright owner\'s request, you may only watch the video after you are premium member.'
}]
def _real_extract(self, url):
video_id = self._match_id(url)
episode_id = video_id[2:]
webpage = self._download_webpage(url, video_id)
if '您所在的地区无法观看本片' in webpage:
raise GeoRestrictedError('This video is restricted')
elif ('开通大会员观看' in webpage and '__playinfo__' not in webpage
or '正在观看预览，大会员免费看全片' in webpage):
elif '正在观看预览，大会员免费看全片' in webpage:
self.raise_login_required('This video is for premium members only')
play_info = self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id)['data']
headers = {'Referer': url, **self.geo_verification_headers()}
play_info = self._download_json(
'https://api.bilibili.com/pgc/player/web/v2/playurl', video_id,
'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
headers=headers)
premium_only = play_info.get('code') == -10403
play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
formats = self.extract_formats(play_info)
if (not formats and '成为大会员抢先看' in webpage
and play_info.get('durl') and not play_info.get('dash')):
if not formats and (premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage):
self.raise_login_required('This video is for premium members only')
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
bangumi_info = self._download_json(
'https://api.bilibili.com/pgc/view/web/season', video_id, 'Get episode details',
query={'ep_id': episode_id}, headers=headers)['result']
season_id = traverse_obj(initial_state, ('mediaInfo', 'season_id'))
episode_number, episode_info = next((
(idx, ep) for idx, ep in enumerate(traverse_obj(
bangumi_info, ('episodes', ..., {dict})), 1)
if str_or_none(ep.get('id')) == episode_id), (1, {}))
season_id = bangumi_info.get('season_id')
season_number = season_id and next((
idx + 1 for idx, e in enumerate(
traverse_obj(initial_state, ('mediaInfo', 'seasons', ...)))
traverse_obj(bangumi_info, ('seasons', ...)))
if e.get('season_id') == season_id
), None)
aid = episode_info.get('aid')
return {
'id': video_id,
'formats': formats,
'title': traverse_obj(initial_state, 'h1Title'),
'episode': traverse_obj(initial_state, ('epInfo', 'long_title')),
'episode_number': int_or_none(traverse_obj(initial_state, ('epInfo', 'title'))),
'series': traverse_obj(initial_state, ('mediaInfo', 'series')),
'season': traverse_obj(initial_state, ('mediaInfo', 'season_title')),
'season_id': season_id,
**traverse_obj(bangumi_info, {
'series': ('series', 'series_title', {str}),
'series_id': ('series', 'series_id', {str_or_none}),
'thumbnail': ('square_cover', {url_or_none}),
}),
'title': join_nonempty('title', 'long_title', delim=' ', from_dict=episode_info),
'episode': episode_info.get('long_title'),
'episode_id': episode_id,
'episode_number': int_or_none(episode_info.get('title')) or episode_number,
'season_id': str_or_none(season_id),
'season_number': season_number,
'thumbnail': traverse_obj(initial_state, ('epInfo', 'cover')),
'timestamp': traverse_obj(initial_state, ('epInfo', 'pub_time')),
'timestamp': int_or_none(episode_info.get('pub_time')),
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(
video_id, initial_state, traverse_obj(initial_state, ('epInfo', 'cid'))),
'__post_extractor': self.extract_comments(traverse_obj(initial_state, ('epInfo', 'aid'))),
'http_headers': {'Referer': url, **self.geo_verification_headers()},
'subtitles': self.extract_subtitles(video_id, aid, episode_info.get('cid')),
'__post_extractor': self.extract_comments(aid),
'http_headers': headers,
}
class BiliBiliBangumiMediaIE(InfoExtractor):
class BiliBiliBangumiMediaIE(BilibiliBaseIE):
_VALID_URL = r'https?://www\.bilibili\.com/bangumi/media/md(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bilibili.com/bangumi/media/md24097891',
@ -485,16 +514,26 @@ class BiliBiliBangumiMediaIE(InfoExtractor):
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
ss_id = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)['mediaInfo']['season_id']
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)
episode_list = self._download_json(
'https://api.bilibili.com/pgc/web/season/section', media_id,
query={'season_id': initial_state['mediaInfo']['season_id']},
note='Downloading season info')['result']['main_section']['episodes']
return self.playlist_result(self._get_episodes_from_season(ss_id, url), media_id)
return self.playlist_result((
self.url_result(entry['share_url'], BiliBiliBangumiIE, entry['aid'])
for entry in episode_list), media_id)
class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
_VALID_URL = r'(?x)https?://www\.bilibili\.com/bangumi/play/ss(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bilibili.com/bangumi/play/ss26801',
'info_dict': {
'id': '26801'
},
'playlist_mincount': 26
}]
def _real_extract(self, url):
ss_id = self._match_id(url)
return self.playlist_result(self._get_episodes_from_season(ss_id, url), ss_id)
class BilibiliSpaceBaseIE(InfoExtractor):
@ -575,7 +614,7 @@ def fetch_page(page_idx):
response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search',
playlist_id, note=f'Downloading page {page_idx}', query=query)
except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 412:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True)
raise

2
yt_dlp/extractor/bitchute.py
View file

@ -2,9 +2,9 @@
import re
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
HEADRequest,
OnDemandPagedList,
clean_html,
get_element_by_class,

4
yt_dlp/extractor/bravotv.py
View file

@ -1,6 +1,6 @@
from .adobepass import AdobePassIE
from ..networking import HEADRequest
from ..utils import (
HEADRequest,
extract_attributes,
float_or_none,
get_element_html_by_class,
@ -155,7 +155,7 @@ def _real_extract(self, url):
chapters = None
m3u8_url = self._request_webpage(HEADRequest(
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').geturl()
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
if 'mpeg_cenc' in m3u8_url:
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')

6
yt_dlp/extractor/brightcove.py
View file

@ -7,10 +7,10 @@
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
compat_parse_qs,
compat_urlparse,
)
from ..networking.exceptions import HTTPError
from ..utils import (
clean_html,
dict_get,
@ -915,8 +915,8 @@ def extract_policy_key():
json_data = self._download_json(api_url, video_id, headers=headers)
break
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
json_data = self._parse_json(e.cause.response.read().decode(), video_id)[0]
message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message)

2
yt_dlp/extractor/canalplus.py
View file

@ -64,7 +64,7 @@ def _real_extract(self, url):
# response = self._request_webpage(
# HEADRequest(fmt_url), video_id,
# 'Checking if the video is georestricted')
# if '/blocage' in response.geturl():
# if '/blocage' in response.url:
# raise ExtractorError(
# 'The video is not available in your country',
# expected=True)

2
yt_dlp/extractor/cbsnews.py
View file

@ -7,9 +7,9 @@
from .anvato import AnvatoIE
from .common import InfoExtractor
from .paramountplus import ParamountPlusIE
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
HEADRequest,
UserNotLive,
determine_ext,
float_or_none,

30
yt_dlp/extractor/ceskatelevize.py
View file

@ -1,20 +1,20 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
)
from ..compat import compat_urllib_parse_unquote, compat_urllib_parse_urlparse
from ..networking import Request
from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
str_or_none,
traverse_obj,
urlencode_postdata,
USER_AGENTS,
)
USER_AGENTS = {
'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
}
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
@ -97,7 +97,7 @@ class CeskaTelevizeIE(InfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
parsed_url = compat_urllib_parse_urlparse(urlh.url)
site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
playlist_title = self._og_search_title(webpage, default=None)
if site_name and playlist_title:
@ -163,16 +163,16 @@ def _real_extract(self, url):
entries = []
for user_agent in (None, USER_AGENTS['Safari']):
req = sanitized_Request(
req = Request(
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
data=urlencode_postdata(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
req.add_header('x-addr', '127.0.0.1')
req.add_header('X-Requested-With', 'XMLHttpRequest')
req.headers['Content-type'] = 'application/x-www-form-urlencoded'
req.headers['x-addr'] = '127.0.0.1'
req.headers['X-Requested-With'] = 'XMLHttpRequest'
if user_agent:
req.add_header('User-Agent', user_agent)
req.add_header('Referer', url)
req.headers['User-Agent'] = user_agent
req.headers['Referer'] = url
playlistpage = self._download_json(req, playlist_id, fatal=False)
@ -183,8 +183,8 @@ def _real_extract(self, url):
if playlist_url == 'error_region':
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url)
req = Request(compat_urllib_parse_unquote(playlist_url))
req.headers['Referer'] = url
playlist = self._download_json(req, playlist_id, fatal=False)
if not playlist:

4
yt_dlp/extractor/cinetecamilano.py
View file

@ -1,6 +1,6 @@
import json
import urllib.error
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
@ -40,7 +40,7 @@ def _real_extract(self, url):
'Authorization': try_get(self._get_cookies('https://www.cinetecamilano.it'), lambda x: f'Bearer {x["cnt-token"].value}') or ''
})
except ExtractorError as e:
if ((isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 500)
if ((isinstance(e.cause, HTTPError) and e.cause.status == 500)
or isinstance(e.cause, json.JSONDecodeError)):
self.raise_login_required(method='cookies')
raise

6
yt_dlp/extractor/ciscowebex.py
View file

@ -33,7 +33,7 @@ def _real_extract(self, url):
if rcid:
webpage = self._download_webpage(url, None, note='Getting video ID')
url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url')
url = self._request_webpage(url, None, note='Resolving final URL').geturl()
url = self._request_webpage(url, None, note='Resolving final URL').url
mobj = self._match_valid_url(url)
subdomain = mobj.group('subdomain')
siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2')
@ -49,7 +49,7 @@ def _real_extract(self, url):
'https://%s.webex.com/webappng/api/v1/recordings/%s/stream' % (subdomain, video_id),
video_id, headers=headers, query={'siteurl': siteurl}, expected_status=(403, 429))
if urlh.getcode() == 403:
if urlh.status == 403:
if stream['code'] == 53004:
self.raise_login_required()
if stream['code'] == 53005:
@ -59,7 +59,7 @@ def _real_extract(self, url):
'This video is protected by a password, use the --video-password option', expected=True)
raise ExtractorError(f'{self.IE_NAME} said: {stream["code"]} - {stream["message"]}', expected=True)
if urlh.getcode() == 429:
if urlh.status == 429:
self.raise_login_required(
f'{self.IE_NAME} asks you to solve a CAPTCHA. Solve CAPTCHA in browser and',
method='cookies')

81
yt_dlp/extractor/common.py
View file

@ -17,15 +17,26 @@
import sys
import time
import types
import urllib.error
import urllib.parse
import urllib.request
import xml.etree.ElementTree
from ..compat import functools # isort: split
from ..compat import compat_etree_fromstring, compat_expanduser, compat_os_name
from ..compat import (
compat_etree_fromstring,
compat_expanduser,
compat_os_name,
urllib_req_to_req,
)
from ..cookies import LenientSimpleCookie
from ..downloader.f4m import get_base_url, remove_encrypted_media
from ..downloader.hls import HlsFD
from ..networking import HEADRequest, Request
from ..networking.exceptions import (
HTTPError,
IncompleteRead,
network_exceptions,
)
from ..utils import (
IDENTITY,
JSON_LD_RE,
@ -34,7 +45,6 @@
FormatSorter,
GeoRestrictedError,
GeoUtils,
HEADRequest,
LenientJSONDecoder,
Popen,
RegexNotFoundError,
@ -60,7 +70,6 @@
js_to_json,
mimetype2ext,
netrc_from_content,
network_exceptions,
orderedSet,
parse_bitrate,
parse_codecs,
@ -70,7 +79,6 @@
parse_resolution,
sanitize_filename,
sanitize_url,
sanitized_Request,
smuggle_url,
str_or_none,
str_to_int,
@ -82,8 +90,6 @@
unescapeHTML,
unified_strdate,
unified_timestamp,
update_Request,
update_url_query,
url_basename,
url_or_none,
urlhandle_detect_ext,
@ -224,7 +230,8 @@ class InfoExtractor:
width : height ratio as float.
* no_resume The server does not support resuming the
(HTTP or RTMP) download. Boolean.
* has_drm The format has DRM and cannot be downloaded. Boolean
* has_drm True if the format has DRM and cannot be downloaded.
'maybe' if the format may have DRM and has to be tested before download.
* extra_param_to_segment_url A query string to append to each
fragment's URL, or to update each existing query string
with. Only applied by the native HLS/DASH downloaders.
@ -726,7 +733,7 @@ def extract(self, url):
e.ie = e.ie or self.IE_NAME,
e.traceback = e.traceback or sys.exc_info()[2]
raise
except http.client.IncompleteRead as e:
except IncompleteRead as e:
raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url))
except (KeyError, StopIteration) as e:
raise ExtractorError('An extractor error has occurred.', cause=e, video_id=self.get_temp_id(url))
@ -785,20 +792,25 @@ def IE_NAME(cls):
@staticmethod
def __can_accept_status_code(err, expected_status):
assert isinstance(err, urllib.error.HTTPError)
assert isinstance(err, HTTPError)
if expected_status is None:
return False
elif callable(expected_status):
return expected_status(err.code) is True
return expected_status(err.status) is True
else:
return err.code in variadic(expected_status)
return err.status in variadic(expected_status)
def _create_request(self, url_or_request, data=None, headers=None, query=None):
if isinstance(url_or_request, urllib.request.Request):
return update_Request(url_or_request, data=data, headers=headers, query=query)
if query:
url_or_request = update_url_query(url_or_request, query)
return sanitized_Request(url_or_request, data, headers or {})
self._downloader.deprecation_warning(
'Passing a urllib.request.Request to _create_request() is deprecated. '
'Use yt_dlp.networking.common.Request instead.')
url_or_request = urllib_req_to_req(url_or_request)
elif not isinstance(url_or_request, Request):
url_or_request = Request(url_or_request)
url_or_request.update(data=data, headers=headers, query=query)
return url_or_request
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None, expected_status=None):
"""
@ -834,14 +846,9 @@ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fa
try:
return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query))
except network_exceptions as err:
if isinstance(err, urllib.error.HTTPError):
if isinstance(err, HTTPError):
if self.__can_accept_status_code(err, expected_status):
# Retain reference to error to prevent file object from
# being closed before it can be read. Works around the
# effects of <https://bugs.python.org/issue15002>
# introduced in Python 3.4.1.
err.fp._error = err
return err.fp
return err.response
if errnote is False:
return False
@ -973,11 +980,11 @@ def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errno
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
if self.get_param('dump_intermediate_pages', False):
self.to_screen('Dumping request to ' + urlh.geturl())
self.to_screen('Dumping request to ' + urlh.url)
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
if self.get_param('write_pages'):
filename = self._request_dump_filename(urlh.geturl(), video_id)
filename = self._request_dump_filename(urlh.url, video_id)
self.to_screen(f'Saving request to {filename}')
with open(filename, 'wb') as outf:
outf.write(webpage_bytes)
@ -1035,7 +1042,7 @@ def download_content(self, url_or_request, video_id, note=note, errnote=errnote,
fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None):
if self.get_param('load_pages'):
url_or_request = self._create_request(url_or_request, data, headers, query)
filename = self._request_dump_filename(url_or_request.full_url, video_id)
filename = self._request_dump_filename(url_or_request.url, video_id)
self.to_screen(f'Loading request from {filename}')
try:
with open(filename, 'rb') as dumpf:
@ -1109,7 +1116,7 @@ def _download_webpage(
while True:
try:
return self.__download_webpage(url_or_request, video_id, note, errnote, None, fatal, *args, **kwargs)
except http.client.IncompleteRead as e:
except IncompleteRead as e:
try_count += 1
if try_count >= tries:
raise e
@ -1806,7 +1813,7 @@ def _extract_f4m_formats(self, manifest_url, video_id, preference=None, quality=
return []
manifest, urlh = res
manifest_url = urlh.geturl()
manifest_url = urlh.url
return self._parse_f4m_formats(
manifest, manifest_url, video_id, preference=preference, quality=quality, f4m_id=f4m_id,
@ -1965,7 +1972,7 @@ def _extract_m3u8_formats_and_subtitles(
return [], {}
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
m3u8_url = urlh.url
return self._parse_m3u8_formats_and_subtitles(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
@ -1979,11 +1986,7 @@ def _parse_m3u8_formats_and_subtitles(
errnote=None, fatal=True, data=None, headers={}, query={},
video_id=None):
formats, subtitles = [], {}
has_drm = re.search('|'.join([
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
]), m3u8_doc)
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)
@ -2247,7 +2250,7 @@ def _extract_smil_formats_and_subtitles(self, smil_url, video_id, fatal=True, f4
return [], {}
smil, urlh = res
smil_url = urlh.geturl()
smil_url = urlh.url
namespace = self._parse_smil_namespace(smil)
@ -2270,7 +2273,7 @@ def _extract_smil_info(self, smil_url, video_id, fatal=True, f4m_params=None):
return {}
smil, urlh = res
smil_url = urlh.geturl()
smil_url = urlh.url
return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
@ -2462,7 +2465,7 @@ def _extract_xspf_playlist(self, xspf_url, playlist_id, fatal=True):
return []
xspf, urlh = res
xspf_url = urlh.geturl()
xspf_url = urlh.url
return self._parse_xspf(
xspf, playlist_id, xspf_url=xspf_url,
@ -2533,7 +2536,7 @@ def _extract_mpd_formats_and_subtitles(
return [], {}
# We could have been redirected to a new url when we retrieved our mpd file.
mpd_url = urlh.geturl()
mpd_url = urlh.url
mpd_base_url = base_url(mpd_url)
return self._parse_mpd_formats_and_subtitles(
@ -2919,7 +2922,7 @@ def _extract_ism_formats_and_subtitles(self, ism_url, video_id, ism_id=None, not
if ism_doc is None:
return [], {}
return self._parse_ism_formats_and_subtitles(ism_doc, urlh.geturl(), ism_id)
return self._parse_ism_formats_and_subtitles(ism_doc, urlh.url, ism_id)
def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None):
"""

4
yt_dlp/extractor/crackle.py
View file

@ -4,7 +4,7 @@
import time
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
determine_ext,
float_or_none,
@ -113,7 +113,7 @@ def _real_extract(self, url):
errnote='Unable to download media JSON')
except ExtractorError as e:
# 401 means geo restriction, trying next country
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
continue
raise

97
yt_dlp/extractor/crunchyroll.py
View file

@ -1,7 +1,7 @@
import base64
import urllib.error
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
@ -27,11 +27,24 @@ class CrunchyrollBaseIE(InfoExtractor):
_AUTH_HEADERS = None
_API_ENDPOINT = None
_BASIC_AUTH = None
_QUERY = {}
_CLIENT_ID = ('cr_web', 'noaihdevm_6iyg0a8l0q')
_LOCALE_LOOKUP = {
'ar': 'ar-SA',
'de': 'de-DE',
'': 'en-US',
'es': 'es-419',
'es-es': 'es-ES',
'fr': 'fr-FR',
'it': 'it-IT',
'pt-br': 'pt-BR',
'pt-pt': 'pt-PT',
'ru': 'ru-RU',
'hi': 'hi-IN',
}
@property
def is_logged_in(self):
return self._get_cookies(self._BASE_URL).get('etp_rt')
return bool(self._get_cookies(self._BASE_URL).get('etp_rt'))
def _perform_login(self, username, password):
if self.is_logged_in:
@ -62,49 +75,49 @@ def _perform_login(self, username, password):
if not self.is_logged_in:
raise ExtractorError('Login succeeded but did not set etp_rt cookie')
def _update_query(self, lang):
if lang in CrunchyrollBaseIE._QUERY:
return
webpage = self._download_webpage(
f'{self._BASE_URL}/{lang}', None, note=f'Retrieving main page (lang={lang or None})')
initial_state = self._search_json(r'__INITIAL_STATE__\s*=', webpage, 'initial state', None)
CrunchyrollBaseIE._QUERY[lang] = traverse_obj(initial_state, {
'locale': ('localization', 'locale'),
}) or None
if CrunchyrollBaseIE._BASIC_AUTH:
return
app_config = self._search_json(r'__APP_CONFIG__\s*=', webpage, 'app config', None)
cx_api_param = app_config['cxApiParams']['accountAuthClientId' if self.is_logged_in else 'anonClientId']
self.write_debug(f'Using cxApiParam={cx_api_param}')
CrunchyrollBaseIE._BASIC_AUTH = 'Basic ' + base64.b64encode(f'{cx_api_param}:'.encode()).decode()
def _update_auth(self):
if CrunchyrollBaseIE._AUTH_HEADERS and CrunchyrollBaseIE._AUTH_REFRESH > time_seconds():
return
assert CrunchyrollBaseIE._BASIC_AUTH, '_update_query needs to be called at least one time beforehand'
if not CrunchyrollBaseIE._BASIC_AUTH:
cx_api_param = self._CLIENT_ID[self.is_logged_in]
self.write_debug(f'Using cxApiParam={cx_api_param}')
CrunchyrollBaseIE._BASIC_AUTH = 'Basic ' + base64.b64encode(f'{cx_api_param}:'.encode()).decode()
grant_type = 'etp_rt_cookie' if self.is_logged_in else 'client_id'
auth_response = self._download_json(
f'{self._BASE_URL}/auth/v1/token', None, note=f'Authenticating with grant_type={grant_type}',
headers={'Authorization': CrunchyrollBaseIE._BASIC_AUTH}, data=f'grant_type={grant_type}'.encode())
try:
auth_response = self._download_json(
f'{self._BASE_URL}/auth/v1/token', None, note=f'Authenticating with grant_type={grant_type}',
headers={'Authorization': CrunchyrollBaseIE._BASIC_AUTH}, data=f'grant_type={grant_type}'.encode())
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 403:
raise ExtractorError(
'Request blocked by Cloudflare; navigate to Crunchyroll in your browser, '
'then pass the fresh cookies (with --cookies-from-browser or --cookies) '
'and your browser\'s User-Agent (with --user-agent)', expected=True)
raise
CrunchyrollBaseIE._AUTH_HEADERS = {'Authorization': auth_response['token_type'] + ' ' + auth_response['access_token']}
CrunchyrollBaseIE._AUTH_REFRESH = time_seconds(seconds=traverse_obj(auth_response, ('expires_in', {float_or_none}), default=300) - 10)
def _locale_from_language(self, language):
config_locale = self._configuration_arg('metadata', ie_key=CrunchyrollBetaIE, casesense=True)
return config_locale[0] if config_locale else self._LOCALE_LOOKUP.get(language)
def _call_base_api(self, endpoint, internal_id, lang, note=None, query={}):
self._update_query(lang)
self._update_auth()
if not endpoint.startswith('/'):
endpoint = f'/{endpoint}'
query = query.copy()
locale = self._locale_from_language(lang)
if locale:
query['locale'] = locale
return self._download_json(
f'{self._BASE_URL}{endpoint}', internal_id, note or f'Calling API: {endpoint}',
headers=CrunchyrollBaseIE._AUTH_HEADERS, query={**CrunchyrollBaseIE._QUERY[lang], **query})
headers=CrunchyrollBaseIE._AUTH_HEADERS, query=query)
def _call_api(self, path, internal_id, lang, note='api', query={}):
if not path.startswith(f'/content/v2/{self._API_ENDPOINT}/'):
@ -114,7 +127,7 @@ def _call_api(self, path, internal_id, lang, note='api', query={}):
result = self._call_base_api(
path, internal_id, lang, f'Downloading {note} JSON ({self._API_ENDPOINT})', query=query)
except ExtractorError as error:
if isinstance(error.cause, urllib.error.HTTPError) and error.cause.code == 404:
if isinstance(error.cause, HTTPError) and error.cause.status == 404:
return None
raise
@ -206,7 +219,7 @@ class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
IE_NAME = 'crunchyroll'
_VALID_URL = r'''(?x)
https?://(?:beta\.|www\.)?crunchyroll\.com/
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
(?:(?P<lang>\w{2}(?:-\w{2})?)/)?
watch/(?!concert|musicvideo)(?P<id>\w+)'''
_TESTS = [{
# Premium only
@ -304,7 +317,7 @@ class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
},
'playlist_mincount': 5,
}, {
'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y',
'url': 'https://www.crunchyroll.com/de/watch/GY2P1Q98Y',
'only_matching': True,
}, {
'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
@ -490,8 +503,21 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE):
_VALID_URL = r'''(?x)
https?://(?:www\.)?crunchyroll\.com/
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
watch/(?P<type>concert|musicvideo)/(?P<id>\w{10})'''
watch/(?P<type>concert|musicvideo)/(?P<id>\w+)'''
_TESTS = [{
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79',
'info_dict': {
'ext': 'mp4',
'id': 'MV5B02C79',
'display_id': 'egaono-hana',
'title': 'Egaono Hana',
'track': 'Egaono Hana',
'artist': 'Goose house',
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'genre': ['J-Pop'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C',
'info_dict': {
'ext': 'mp4',
@ -519,11 +545,14 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE):
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79/egaono-hana',
'only_matching': True,
}, {
'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135/live-is-smile-always-364joker-at-yokohama-arena',
'only_matching': True,
}, {
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
'only_matching': True,
}]
_API_ENDPOINT = 'music'

6
yt_dlp/extractor/cultureunplugged.py
View file

@ -1,10 +1,8 @@
import time
from .common import InfoExtractor
from ..utils import (
int_or_none,
HEADRequest,
)
from ..networking import HEADRequest
from ..utils import int_or_none
class CultureUnpluggedIE(InfoExtractor):

4
yt_dlp/extractor/dacast.py
View file

@ -1,9 +1,9 @@
import hashlib
import re
import time
import urllib.error
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
classproperty,
@ -105,7 +105,7 @@ def _real_extract(self, url):
formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls')
except ExtractorError as e:
# CDN will randomly respond with 403
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
retry.error = e
continue
raise

6
yt_dlp/extractor/dailymotion.py
View file

@ -3,7 +3,7 @@
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -68,9 +68,9 @@ def _call_api(self, object_type, xid, object_fields, note, filter_extra=None):
None, 'Downloading Access Token',
data=urlencode_postdata(data))['access_token']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
raise ExtractorError(self._parse_json(
e.cause.read().decode(), xid)['error_description'], expected=True)
e.cause.response.read().decode(), xid)['error_description'], expected=True)
raise
self._set_dailymotion_cookie('access_token' if username else 'client_token', token)
self._HEADERS['Authorization'] = 'Bearer ' + token

6
yt_dlp/extractor/discovery.py
View file

@ -3,8 +3,8 @@
from .discoverygo import DiscoveryGoBaseIE
from ..compat import compat_urllib_parse_unquote
from ..networking.exceptions import HTTPError
from ..utils import ExtractorError
from ..compat import compat_HTTPError
class DiscoveryIE(DiscoveryGoBaseIE):
@ -100,9 +100,9 @@ def _real_extract(self, url):
self._API_BASE_URL + 'streaming/video/' + video_id,
display_id, 'Downloading streaming JSON metadata', headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
e_description = self._parse_json(
e.cause.read().decode(), display_id)['description']
e.cause.response.read().decode(), display_id)['description']
if 'resource not available for country' in e_description:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
if 'Authorized Networks' in e_description:

8
yt_dlp/extractor/dplay.py
View file

@ -2,7 +2,7 @@
import uuid
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
determine_ext,
ExtractorError,
@ -39,7 +39,7 @@ def _get_auth(self, disco_base, display_id, realm, needs_device_id=True):
return f'Bearer {token}'
def _process_errors(self, e, geo_countries):
info = self._parse_json(e.cause.read().decode('utf-8'), None)
info = self._parse_json(e.cause.response.read().decode('utf-8'), None)
error = info['errors'][0]
error_code = error.get('code')
if error_code == 'access.denied.geoblocked':
@ -87,7 +87,7 @@ def _get_disco_api_info(self, url, display_id, disco_host, realm, country, domai
'include': 'images,primaryChannel,show,tags'
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
self._process_errors(e, geo_countries)
raise
video_id = video['data']['id']
@ -99,7 +99,7 @@ def _get_disco_api_info(self, url, display_id, disco_host, realm, country, domai
streaming = self._download_video_playback_info(
disco_base, video_id, headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
self._process_errors(e, geo_countries)
raise
for format_dict in streaming:

6
yt_dlp/extractor/eagleplatform.py
View file

@ -2,7 +2,7 @@
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
@ -111,8 +111,8 @@ def _download_json(self, url_or_request, video_id, *args, **kwargs):
response = super(EaglePlatformIE, self)._download_json(
url_or_request, video_id, *args, **kwargs)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError):
response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
if isinstance(ee.cause, HTTPError):
response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
self._handle_error(response)
raise
return response

10
yt_dlp/extractor/eitb.py
View file

@ -1,10 +1,6 @@
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
sanitized_Request,
)
from ..networking import Request
from ..utils import float_or_none, int_or_none, parse_iso8601
class EitbIE(InfoExtractor):
@ -54,7 +50,7 @@ def _real_extract(self, url):
hls_url = media.get('HLS_SURL')
if hls_url:
request = sanitized_Request(
request = Request(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
headers={'Referer': url})
token_data = self._download_json(

2
yt_dlp/extractor/eporner.py
View file

@ -52,7 +52,7 @@ def _real_extract(self, url):
webpage, urlh = self._download_webpage_handle(url, display_id)
video_id = self._match_id(urlh.geturl())
video_id = self._match_id(urlh.url)
hash = self._search_regex(
r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash')

2
yt_dlp/extractor/ettutv.py
View file

@ -41,7 +41,7 @@ def _real_extract(self, url):
'device': 'desktop',
})
stream_response = self._download_json(player_settings['streamAccess'], video_id, data={})
stream_response = self._download_json(player_settings['streamAccess'], video_id, data=b'')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
stream_response['data']['stream'], video_id, 'mp4')

97
yt_dlp/extractor/facebook.py
View file

@ -8,6 +8,8 @@
compat_str,
compat_urllib_parse_unquote,
)
from ..networking import Request
from ..networking.exceptions import network_exceptions
from ..utils import (
ExtractorError,
clean_html,
@ -19,11 +21,10 @@
int_or_none,
js_to_json,
merge_dicts,
network_exceptions,
parse_count,
parse_qs,
qualities,
sanitized_Request,
str_or_none,
traverse_obj,
try_get,
url_or_none,
@ -90,16 +91,16 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
'title': 'Asif Nawab Butt',
'description': 'Asif Nawab Butt',
'title': 'Asif',
'description': '',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
'thumbnail': r're:^https?://.*',
'uploader_id': 'pfbid04scW44U4P9iTyLZAGy8y8W3pR3i2VugvHCimiRudUAVbN3MPp9eXBaYFcgVworZwl',
'duration': 131.03,
'concurrent_view_count': int,
},
'expected_warnings': [
'title'
]
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
@ -151,7 +152,7 @@ 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': '3f3798adb2b73423263e59376f1f5eb7',
'md5': 'ca63897a90c9452efee5f8c40d080e25',
'info_dict': {
'id': '10155529876156509',
'ext': 'mp4',
@ -162,6 +163,9 @@ class FacebookIE(InfoExtractor):
'uploader': 'CNN',
'thumbnail': r're:^https?://.*',
'view_count': int,
'uploader_id': '100059479812265',
'concurrent_view_count': int,
'duration': 44.478,
},
}, {
# bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
@ -170,12 +174,16 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '1417995061575415',
'ext': 'mp4',
'title': 'Ukrainian Scientists Worldwide | Довгоочікуване відео',
'title': 'Довгоочікуване відео | By Yaroslav - Facebook',
'description': 'Довгоочікуване відео',
'timestamp': 1486648771,
'timestamp': 1486648217,
'upload_date': '20170209',
'uploader': 'Yaroslav Korpan',
'uploader_id': '100000948048708',
'uploader_id': 'pfbid029y8j22EwH3ikeqgH3SEP9G3CAi9kmWKgXJJG9s5geV7mo3J2bvURqHCdgucRgAyhl',
'concurrent_view_count': int,
'thumbnail': r're:^https?://.*',
'view_count': int,
'duration': 11736.446,
},
'params': {
'skip_download': True,
@ -192,9 +200,7 @@ class FacebookIE(InfoExtractor):
'uploader': 'La Guía Del Varón',
'thumbnail': r're:^https?://.*',
},
'params': {
'skip_download': True,
},
'skip': 'Requires logging in',
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media
'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/',
@ -208,9 +214,7 @@ class FacebookIE(InfoExtractor):
'uploader': 'Elisabeth Ahtn',
'uploader_id': '100013949973717',
},
'params': {
'skip_download': True,
},
'skip': 'Requires logging in',
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
'only_matching': True,
@ -252,7 +256,11 @@ class FacebookIE(InfoExtractor):
'timestamp': 1527084179,
'upload_date': '20180523',
'uploader': 'ESL One Dota 2',
'uploader_id': '234218833769558',
'uploader_id': '100066514874195',
'duration': 4524.212,
'view_count': int,
'thumbnail': r're:^https?://.*',
'concurrent_view_count': int,
},
'params': {
'skip_download': True,
@ -262,8 +270,17 @@ class FacebookIE(InfoExtractor):
'url': 'https://www.facebook.com/100033620354545/videos/106560053808006/',
'info_dict': {
'id': '106560053808006',
'ext': 'mp4',
'title': 'Josef',
'thumbnail': r're:^https?://.*',
'concurrent_view_count': int,
'uploader_id': 'pfbid02gXHbDwxumkaKJQaTGUf3znYfYzTuidGEWawiramNx4YamSj2afwYSRkpcjtHtMRJl',
'timestamp': 1549275572,
'duration': 3.413,
'uploader': 'Josef Novak',
'description': '',
'upload_date': '20190204',
},
'playlist_count': 2,
}, {
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/watch/?v=647537299265662',
@ -276,6 +293,7 @@ class FacebookIE(InfoExtractor):
'id': '10157667649866271',
},
'playlist_count': 3,
'skip': 'Requires logging in',
}, {
# data.nodes[].comet_sections.content.story.attachments[].style_type_renderer.attachment.media
'url': 'https://m.facebook.com/Alliance.Police.Department/posts/4048563708499330',
@ -319,7 +337,7 @@ class FacebookIE(InfoExtractor):
}
def _perform_login(self, username, password):
login_page_req = sanitized_Request(self._LOGIN_URL)
login_page_req = Request(self._LOGIN_URL)
self._set_cookie('facebook.com', 'locale', 'en_US')
login_page = self._download_webpage(login_page_req, None,
note='Downloading login page',
@ -340,8 +358,8 @@ def _perform_login(self, username, password):
'timezone': '-60',
'trynum': '1',
}
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request = Request(self._LOGIN_URL, urlencode_postdata(login_form))
request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
try:
login_results = self._download_webpage(request, None,
note='Logging in', errnote='unable to fetch login page')
@ -367,8 +385,8 @@ def _perform_login(self, username, password):
'h': h,
'name_action_selected': 'dont_save',
}
check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
check_req = Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
check_req.headers['Content-Type'] = 'application/x-www-form-urlencoded'
check_response = self._download_webpage(check_req, None,
note='Confirming login')
if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
@ -497,6 +515,13 @@ def extract_relay_prefetched_data(_filter):
entries = []
def parse_graphql_video(video):
v_id = video.get('videoId') or video.get('id') or video_id
reel_info = traverse_obj(
video, ('creation_story', 'short_form_video_context', 'playback_video', {dict}))
if reel_info:
video = video['creation_story']
video['owner'] = traverse_obj(video, ('short_form_video_context', 'video_owner'))
video.update(reel_info)
formats = []
q = qualities(['sd', 'hd'])
for key, format_id in (('playable_url', 'sd'), ('playable_url_quality_hd', 'hd'),
@ -513,15 +538,15 @@ def parse_graphql_video(video):
'url': playable_url,
})
extract_dash_manifest(video, formats)
v_id = video.get('videoId') or video.get('id') or video_id
info = {
'id': v_id,
'formats': formats,
'thumbnail': traverse_obj(
video, ('thumbnailImage', 'uri'), ('preferred_thumbnail', 'image', 'uri')),
'uploader_id': try_get(video, lambda x: x['owner']['id']),
'timestamp': int_or_none(video.get('publish_time')),
'duration': float_or_none(video.get('playable_duration_in_ms'), 1000),
'uploader_id': traverse_obj(video, ('owner', 'id', {str_or_none})),
'timestamp': traverse_obj(video, 'publish_time', 'creation_time', expected_type=int_or_none),
'duration': (float_or_none(video.get('playable_duration_in_ms'), 1000)
or float_or_none(video.get('length_in_second'))),
}
process_formats(info)
description = try_get(video, lambda x: x['savable_description']['text'])
@ -782,18 +807,18 @@ class FacebookReelIE(InfoExtractor):
_TESTS = [{
'url': 'https://www.facebook.com/reel/1195289147628387',
'md5': 'c4ff9a7182ff9ff7d6f7a83603bae831',
'md5': 'f13dd37f2633595982db5ed8765474d3',
'info_dict': {
'id': '1195289147628387',
'ext': 'mp4',
'title': 'md5:9f5b142921b2dc57004fa13f76005f87',
'description': 'md5:24ea7ef062215d295bdde64e778f5474',
'uploader': 'Beast Camp Training',
'uploader_id': '1738535909799870',
'duration': 9.536,
'thumbnail': r're:^https?://.*',
'title': 'md5:b05800b5b1ad56c0ca78bd3807b6a61e',
'description': 'md5:22f03309b216ac84720183961441d8db',
'uploader': 'md5:723e6cb3091241160f20b3c5dc282af1',
'uploader_id': '100040874179269',
'duration': 9.579,
'timestamp': 1637502609,
'upload_date': '20211121',
'timestamp': 1637502604,
'thumbnail': r're:^https?://.*',
}
}]

6
yt_dlp/extractor/fc2.py
View file

@ -3,11 +3,11 @@
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..dependencies import websockets
from ..networking import Request
from ..utils import (
ExtractorError,
WebSocketsWrapper,
js_to_json,
sanitized_Request,
traverse_obj,
update_url_query,
urlencode_postdata,
@ -57,7 +57,7 @@ def _login(self):
}
login_data = urlencode_postdata(login_form_strs)
request = sanitized_Request(
request = Request(
'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
@ -66,7 +66,7 @@ def _login(self):
return False
# this is also needed
login_redir = sanitized_Request('http://id.fc2.com/?mode=redirect&login=done')
login_redir = Request('http://id.fc2.com/?mode=redirect&login=done')
self._download_webpage(
login_redir, None, note='Login redirect', errnote='Login redirect failed')

14
yt_dlp/extractor/filmon.py
View file

@ -1,8 +1,6 @@
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_HTTPError,
)
from ..compat import compat_str
from ..networking.exceptions import HTTPError
from ..utils import (
qualities,
strip_or_none,
@ -40,8 +38,8 @@ def _real_extract(self, url):
'https://www.filmon.com/api/vod/movie?id=%s' % video_id,
video_id)['response']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
errmsg = self._parse_json(e.cause.read().decode(), video_id)['reason']
if isinstance(e.cause, HTTPError):
errmsg = self._parse_json(e.cause.response.read().decode(), video_id)['reason']
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
raise
@ -124,8 +122,8 @@ def _real_extract(self, url):
channel_data = self._download_json(
'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
errmsg = self._parse_json(e.cause.read().decode(), channel_id)['message']
if isinstance(e.cause, HTTPError):
errmsg = self._parse_json(e.cause.response.read().decode(), channel_id)['message']
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
raise

10
yt_dlp/extractor/fox.py
View file

@ -3,10 +3,10 @@
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_parse_unquote,
)
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
@ -68,9 +68,9 @@ def _call_api(self, path, video_id, data=None):
'https://api3.fox.com/v2.0/' + path,
video_id, data=data, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
entitlement_issues = self._parse_json(
e.cause.read().decode(), video_id)['entitlementIssues']
e.cause.response.read().decode(), video_id)['entitlementIssues']
for e in entitlement_issues:
if e.get('errorCode') == 1005:
raise ExtractorError(
@ -123,8 +123,8 @@ def _real_extract(self, url):
try:
m3u8_url = self._download_json(release_url, video_id)['playURL']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read().decode(), video_id)
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
error = self._parse_json(e.cause.response.read().decode(), video_id)
if error.get('exception') == 'GeoLocationBlocked':
self.raise_geo_restricted(countries=['US'])
raise ExtractorError(error['description'], expected=True)

5
yt_dlp/extractor/foxsports.py
View file

@ -1,6 +1,7 @@
from .common import InfoExtractor
from .uplynk import UplynkPreplayIE
from ..utils import HEADRequest, float_or_none, make_archive_id, smuggle_url
from ..networking import HEADRequest
from ..utils import float_or_none, make_archive_id, smuggle_url
class FoxSportsIE(InfoExtractor):
@ -35,7 +36,7 @@ def _real_extract(self, url):
'x-api-key': 'cf289e299efdfa39fb6316f259d1de93',
})
preplay_url = self._request_webpage(
HEADRequest(data['url']), video_id, 'Fetching preplay URL').geturl()
HEADRequest(data['url']), video_id, 'Fetching preplay URL').url
return {
'_type': 'url_transparent',

2
yt_dlp/extractor/fujitv.py
View file

@ -1,5 +1,5 @@
from ..utils import HEADRequest
from .common import InfoExtractor
from ..networking import HEADRequest
class FujiTVFODPlus7IE(InfoExtractor):

6
yt_dlp/extractor/funimation.py
View file

@ -3,7 +3,7 @@
import string
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
@ -46,8 +46,8 @@ def _perform_login(self, username, password):
}))
FunimationBaseIE._TOKEN = data['token']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
error = self._parse_json(e.cause.read().decode(), None)['error']
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
error = self._parse_json(e.cause.response.read().decode(), None)['error']
raise ExtractorError(error, expected=True)
raise

15
yt_dlp/extractor/gdcvault.py
View file

@ -2,13 +2,8 @@
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
HEADRequest,
remove_start,
sanitized_Request,
smuggle_url,
urlencode_postdata,
)
from ..networking import HEADRequest, Request
from ..utils import remove_start, smuggle_url, urlencode_postdata
class GDCVaultIE(InfoExtractor):
@ -138,8 +133,8 @@ def _login(self, webpage_url, display_id):
'password': password,
}
request = sanitized_Request(login_url, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request = Request(login_url, urlencode_postdata(login_form))
request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
self._download_webpage(request, display_id, 'Logging in')
start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
self._download_webpage(logout_url, display_id, 'Logging out')
@ -163,7 +158,7 @@ def _real_extract(self, url):
video_url = 'http://www.gdcvault.com' + direct_url
# resolve the url so that we can detect the correct extension
video_url = self._request_webpage(
HEADRequest(video_url), video_id).geturl()
HEADRequest(video_url), video_id).url
return {
'id': video_id,

10
yt_dlp/extractor/generic.py
View file

@ -2431,7 +2431,7 @@ def _real_extract(self, url):
'Accept-Encoding': 'identity',
**smuggled_data.get('http_headers', {})
})
new_url = full_response.geturl()
new_url = full_response.url
url = urllib.parse.urlparse(url)._replace(scheme=urllib.parse.urlparse(new_url).scheme).geturl()
if new_url != extract_basic_auth(url)[0]:
self.report_following_redirect(new_url)
@ -2529,12 +2529,12 @@ def _real_extract(self, url):
return self.playlist_result(
self._parse_xspf(
doc, video_id, xspf_url=url,
xspf_base_url=full_response.geturl()),
xspf_base_url=full_response.url),
video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
doc,
mpd_base_url=full_response.geturl().rpartition('/')[0],
mpd_base_url=full_response.url.rpartition('/')[0],
mpd_url=url)
self._extra_manifest_info(info_dict, url)
self.report_detected('DASH manifest')
@ -2562,7 +2562,7 @@ def _real_extract(self, url):
self._downloader.write_debug('Looking for embeds')
embeds = list(self._extract_embeds(original_url, webpage, urlh=full_response, info_dict=info_dict))
if len(embeds) == 1:
return {**info_dict, **embeds[0]}
return merge_dicts(embeds[0], info_dict)
elif embeds:
return self.playlist_result(embeds, **info_dict)
raise UnsupportedError(url)
@ -2572,7 +2572,7 @@ def _extract_embeds(self, url, webpage, *, urlh=None, info_dict={}):
info_dict = types.MappingProxyType(info_dict) # Prevents accidental mutation
video_id = traverse_obj(info_dict, 'display_id', 'id') or self._generic_id(url)
url, smuggled_data = unsmuggle_url(url, {})
actual_url = urlh.geturl() if urlh else url
actual_url = urlh.url if urlh else url
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)

2
yt_dlp/extractor/globo.py
View file

@ -8,8 +8,8 @@
from ..compat import (
compat_str,
)
from ..networking import HEADRequest
from ..utils import (
HEADRequest,
ExtractorError,
float_or_none,
orderedSet,

21
yt_dlp/extractor/googledrive.py
View file

@ -5,7 +5,9 @@
from ..utils import (
ExtractorError,
determine_ext,
extract_attributes,
get_element_by_class,
get_element_html_by_id,
int_or_none,
lowercase_escape,
try_get,
@ -34,6 +36,7 @@ class GoogleDriveIE(InfoExtractor):
'ext': 'mp4',
'title': 'Big Buck Bunny.mp4',
'duration': 45,
'thumbnail': 'https://drive.google.com/thumbnail?id=0ByeS4oOUV-49Zzh4R1J6R09zazQ',
}
}, {
# video can't be watched anonymously due to view count limit reached,
@ -207,10 +210,10 @@ def get_value(key):
'export': 'download',
})
def request_source_file(source_url, kind):
def request_source_file(source_url, kind, data=None):
return self._request_webpage(
source_url, video_id, note='Requesting %s file' % kind,
errnote='Unable to request %s file' % kind, fatal=False)
errnote='Unable to request %s file' % kind, fatal=False, data=data)
urlh = request_source_file(source_url, 'source')
if urlh:
def add_source_format(urlh):
@ -225,7 +228,7 @@ def add_source_format(urlh):
# Using original URLs may result in redirect loop due to
# google.com's cookies mistakenly used for googleusercontent.com
# redirect URLs (see #23919).
'url': urlh.geturl(),
'url': urlh.url,
'ext': determine_ext(title, 'mp4').lower(),
'format_id': 'source',
'quality': 1,
@ -237,14 +240,10 @@ def add_source_format(urlh):
urlh, url, video_id, note='Downloading confirmation page',
errnote='Unable to confirm download', fatal=False)
if confirmation_webpage:
confirm = self._search_regex(
r'confirm=([^&"\']+)', confirmation_webpage,
'confirmation code', default=None)
if confirm:
confirmed_source_url = update_url_query(source_url, {
'confirm': confirm,
})
urlh = request_source_file(confirmed_source_url, 'confirmed source')
confirmed_source_url = extract_attributes(
get_element_html_by_id('download-form', confirmation_webpage) or '').get('action')
if confirmed_source_url:
urlh = request_source_file(confirmed_source_url, 'confirmed source', data=b'')
if urlh and urlh.headers.get('Content-Disposition'):
add_source_format(urlh)
else:

2
yt_dlp/extractor/hketv.py
View file

@ -126,7 +126,7 @@ def _real_extract(self, url):
# If we ever wanted to provide the final resolved URL that
# does not require cookies, albeit with a shorter lifespan:
# urlh = self._downloader.urlopen(file_url)
# resolved_url = urlh.geturl()
# resolved_url = urlh.url
label = fmt.get('label')
h = self._FORMAT_HEIGHTS.get(label)
w = h * width // height if h and width and height else None

14
yt_dlp/extractor/hotnewhiphop.py
View file

@ -1,11 +1,7 @@
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
ExtractorError,
HEADRequest,
sanitized_Request,
urlencode_postdata,
)
from ..networking import HEADRequest, Request
from ..utils import ExtractorError, urlencode_postdata
class HotNewHipHopIE(InfoExtractor):
@ -36,9 +32,9 @@ def _real_extract(self, url):
('mediaType', 's'),
('mediaId', video_id),
])
r = sanitized_Request(
r = Request(
'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
r.add_header('Content-Type', 'application/x-www-form-urlencoded')
r.headers['Content-Type'] = 'application/x-www-form-urlencoded'
mkd = self._download_json(
r, video_id, note='Requesting media key',
errnote='Could not download media key')
@ -50,7 +46,7 @@ def _real_extract(self, url):
req = self._request_webpage(
redirect_req, video_id,
note='Resolving final URL', errnote='Could not resolve final URL')
video_url = req.geturl()
video_url = req.url
if video_url.endswith('.html'):
raise ExtractorError('Redirect failed')

5
yt_dlp/extractor/hotstar.py
View file

@ -6,7 +6,8 @@
import uuid
from .common import InfoExtractor
from ..compat import compat_HTTPError, compat_str
from ..compat import compat_str
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
@ -233,7 +234,7 @@ def _real_extract(self, url):
'height': int_or_none(playback_set.get('height')),
}]
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
geo_restricted = True
continue

10
yt_dlp/extractor/hrti.py
View file

@ -1,13 +1,13 @@
import json
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import (
clean_html,
ExtractorError,
int_or_none,
parse_age_limit,
sanitized_Request,
try_get,
)
@ -42,7 +42,7 @@ def _initialize_pre_login(self):
'application_version': self._APP_VERSION
}
req = sanitized_Request(self._API_URL, data=json.dumps(app_data).encode('utf-8'))
req = Request(self._API_URL, data=json.dumps(app_data).encode('utf-8'))
req.get_method = lambda: 'PUT'
resources = self._download_json(
@ -73,8 +73,8 @@ def _perform_login(self, username, password):
self._login_url, None, note='Logging in', errnote='Unable to log in',
data=json.dumps(auth_data).encode('utf-8'))
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 406:
auth_info = self._parse_json(e.cause.read().encode('utf-8'), None)
if isinstance(e.cause, HTTPError) and e.cause.status == 406:
auth_info = self._parse_json(e.cause.response.read().encode('utf-8'), None)
else:
raise

17
yt_dlp/extractor/ign.py
View file

@ -1,8 +1,9 @@
import re
import urllib.error
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
@ -27,9 +28,9 @@ def _checked_call_api(self, slug):
try:
return self._call_api(slug)
except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404:
if isinstance(e.cause, HTTPError) and e.cause.status == 404:
e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason]
e.cause.response.url, e.cause.status, e.cause.reason]
raise ExtractorError(
'Content not found: expired?', cause=e.cause,
expected=True)
@ -226,7 +227,7 @@ def _real_extract(self, url):
parsed_url._replace(path=parsed_url.path.rsplit('/', 1)[0] + '/embed'))
webpage, urlh = self._download_webpage_handle(embed_url, video_id)
new_url = urlh.geturl()
new_url = urlh.url
ign_url = compat_parse_qs(
urllib.parse.urlparse(new_url).query).get('url', [None])[-1]
if ign_url:
@ -323,14 +324,14 @@ def _checked_call_api(self, slug):
try:
return self._call_api(slug)
except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError):
if isinstance(e.cause, HTTPError):
e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason]
if e.cause.code == 404:
e.cause.response.url, e.cause.status, e.cause.reason]
if e.cause.status == 404:
raise ExtractorError(
'Content not found: expired?', cause=e.cause,
expected=True)
elif e.cause.code == 503:
elif e.cause.status == 503:
self.report_warning(error_to_compat_str(e.cause))
return
raise

6
yt_dlp/extractor/imggaming.py
View file

@ -1,7 +1,7 @@
import json
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
@ -52,9 +52,9 @@ def _extract_dve_api_url(self, media_id, media_type):
return self._call_api(
stream_path, media_id)['playerUrlCallback']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
raise ExtractorError(
self._parse_json(e.cause.read().decode(), media_id)['messages'][0],
self._parse_json(e.cause.response.read().decode(), media_id)['messages'][0],
expected=True)
raise

6
yt_dlp/extractor/instagram.py
View file

@ -3,9 +3,9 @@
import json
import re
import time
import urllib.error
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
decode_base_n,
@ -442,7 +442,7 @@ def _real_extract(self, url):
shared_data = self._search_json(
r'window\._sharedData\s*=', webpage, 'shared data', video_id, fatal=False) or {}
if shared_data and self._LOGIN_URL not in urlh.geturl():
if shared_data and self._LOGIN_URL not in urlh.url:
media.update(traverse_obj(
shared_data, ('entry_data', 'PostPage', 0, 'graphql', 'shortcode_media'),
('entry_data', 'PostPage', 0, 'media'), expected_type=dict) or {})
@ -589,7 +589,7 @@ def _extract_graphql(self, data, url):
except ExtractorError as e:
# if it's an error caused by a bad query, and there are
# more GIS templates to try, ignore it and keep trying
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
if gis_tmpl != gis_tmpls[-1]:
continue
raise

4
yt_dlp/extractor/iprima.py
View file

@ -81,7 +81,7 @@ def _perform_login(self, username, password):
note='Logging in')
# a profile may need to be selected first, even when there is only a single one
if '/profile-select' in login_handle.geturl():
if '/profile-select' in login_handle.url:
profile_id = self._search_regex(
r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id')
@ -89,7 +89,7 @@ def _perform_login(self, username, password):
f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None,
query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile')
code = traverse_obj(login_handle.geturl(), ({parse_qs}, 'code', 0))
code = traverse_obj(login_handle.url, ({parse_qs}, 'code', 0))
if not code:
raise ExtractorError('Login failed', expected=True)

2
yt_dlp/extractor/iqiyi.py
View file

@ -527,7 +527,7 @@ def _extract_vms_player_js(self, webpage, video_id):
if player_js_cache:
return player_js_cache
webpack_js_url = self._proto_relative_url(self._search_regex(
r'<script src="((?:https?)?//stc.iqiyipic.com/_next/static/chunks/webpack-\w+\.js)"', webpage, 'webpack URL'))
r'<script src="((?:https?:)?//stc\.iqiyipic\.com/_next/static/chunks/webpack-\w+\.js)"', webpage, 'webpack URL'))
webpack_js = self._download_webpage(webpack_js_url, video_id, note='Downloading webpack JS', errnote='Unable to download webpack JS')
webpack_map = self._search_json(
r'["\']\s*\+\s*', webpack_js, 'JS locations', video_id,

6
yt_dlp/extractor/kakao.py
View file

@ -1,5 +1,5 @@
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
@ -101,8 +101,8 @@ def _real_extract(self, url):
cdn_api_base, video_id, query=query,
note='Downloading video URL for profile %s' % profile_name)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
resp = self._parse_json(e.cause.read().decode(), video_id)
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
resp = self._parse_json(e.cause.response.read().decode(), video_id)
if resp.get('code') == 'GeoBlocked':
self.raise_geo_restricted()
raise

5
yt_dlp/extractor/kick.py
View file

@ -1,7 +1,6 @@
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
HEADRequest,
UserNotLive,
float_or_none,
merge_dicts,
@ -30,7 +29,7 @@ def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, *
class KickIE(KickBaseIE):
_VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w_]+)'
_VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://kick.com/yuppy',
'info_dict': {

2
yt_dlp/extractor/kuwo.py
View file

@ -91,7 +91,7 @@ def _real_extract(self, url):
webpage, urlh = self._download_webpage_handle(
url, song_id, note='Download song detail info',
errnote='Unable to get song detail info')
if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
if song_id not in urlh.url or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
raise ExtractorError('this song has been offline because of copyright issues', expected=True)
song_name = self._html_search_regex(

9
yt_dlp/extractor/la7.py
View file

@ -1,13 +1,8 @@
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
HEADRequest,
int_or_none,
parse_duration,
unified_strdate,
)
from ..networking import HEADRequest
from ..utils import float_or_none, int_or_none, parse_duration, unified_strdate
class LA7IE(InfoExtractor):

4
yt_dlp/extractor/lbry.py
View file

@ -3,9 +3,9 @@
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
HEADRequest,
OnDemandPagedList,
UnsupportedError,
determine_ext,
@ -266,7 +266,7 @@ def _real_extract(self, url):
# HEAD request returns redirect response to m3u8 URL if available
final_url = self._request_webpage(
HEADRequest(streaming_url), display_id, headers=headers,
note='Downloading streaming redirect url info').geturl()
note='Downloading streaming redirect url info').url
elif result.get('value_type') == 'stream':
claim_id, is_live = result['signing_channel']['claim_id'], True

Some files were not shown because too many files have changed in this diff Show more