mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 06:27:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse source
This commit is contained in:
bashonly 2024-02-15 17:02:42 -06:00
parent 163533ee17 2e30b5567b
commit 3302588c77
No known key found for this signature in database
GPG key ID: 783F096F253D15B0
43 changed files with 2765 additions and 1050 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

104
.github/workflows/build.yml vendored
View file

@ -107,10 +107,10 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
- uses: actions/setup-python@v5
with:
python-version: "3.10"
- uses: conda-incubator/setup-miniconda@v2
- uses: conda-incubator/setup-miniconda@v3
with:
miniforge-variant: Mambaforge
use-mamba: true
@ -121,16 +121,14 @@ jobs:
- name: Install Requirements
run: |
sudo apt -y install zip pandoc man sed
reqs=$(mktemp)
cat > "$reqs" << EOF
cat > ./requirements.txt << EOF
python=3.10.*
pyinstaller
cffi
brotli-python
secretstorage
EOF
sed -E '/^(brotli|secretstorage).*/d' requirements.txt >> "$reqs"
mamba create -n build --file "$reqs"
python devscripts/install_deps.py --print \
--exclude brotli --exclude brotlicffi \
--include secretstorage --include pyinstaller >> ./requirements.txt
mamba create -n build --file ./requirements.txt
- name: Prepare
run: |
@ -144,9 +142,9 @@ jobs:
run: |
unset LD_LIBRARY_PATH # Harmful; set by setup-python
conda activate build
python pyinst.py --onedir
python -m bundle.pyinstaller --onedir
(cd ./dist/yt-dlp_linux && zip -r ../yt-dlp_linux.zip .)
python pyinst.py
python -m bundle.pyinstaller
mv ./dist/yt-dlp_linux ./yt-dlp_linux
mv ./dist/yt-dlp_linux.zip ./yt-dlp_linux.zip
@ -164,13 +162,15 @@ jobs:
done
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-${{ github.job }}
path: |
yt-dlp
yt-dlp.tar.gz
yt-dlp_linux
yt-dlp_linux.zip
compression-level: 0
linux_arm:
needs: process
@ -201,17 +201,18 @@ jobs:
dockerRunArgs: --volume "${PWD}/repo:/repo"
install: | # Installing Python 3.10 from the Deadsnakes repo raises errors
apt update
apt -y install zlib1g-dev python3.8 python3.8-dev python3.8-distutils python3-pip
apt -y install zlib1g-dev libffi-dev python3.8 python3.8-dev python3.8-distutils python3-pip
python3.8 -m pip install -U pip setuptools wheel
# Cannot access requirements.txt from the repo directory at this stage
python3.8 -m pip install -U Pyinstaller mutagen pycryptodomex websockets brotli certifi secretstorage
# Cannot access any files from the repo directory at this stage
python3.8 -m pip install -U Pyinstaller mutagen pycryptodomex websockets brotli certifi secretstorage cffi
run: |
cd repo
python3.8 -m pip install -U Pyinstaller secretstorage -r requirements.txt # Cached version may be out of date
python3.8 devscripts/install_deps.py -o --include build
python3.8 devscripts/install_deps.py --include pyinstaller --include secretstorage # Cached version may be out of date
python3.8 devscripts/update-version.py -c "${{ inputs.channel }}" -r "${{ needs.process.outputs.origin }}" "${{ inputs.version }}"
python3.8 devscripts/make_lazy_extractors.py
python3.8 pyinst.py
python3.8 -m bundle.pyinstaller
if ${{ vars.UPDATE_TO_VERIFICATION && 'true' || 'false' }}; then
arch="${{ (matrix.architecture == 'armv7' && 'armv7l') || matrix.architecture }}"
@ -224,10 +225,12 @@ jobs:
fi
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-linux_${{ matrix.architecture }}
path: | # run-on-arch-action designates armv7l as armv7
repo/dist/yt-dlp_linux_${{ (matrix.architecture == 'armv7' && 'armv7l') || matrix.architecture }}
compression-level: 0
macos:
needs: process
@ -240,9 +243,10 @@ jobs:
- name: Install Requirements
run: |
brew install coreutils
python3 -m pip install -U --user pip setuptools wheel
python3 devscripts/install_deps.py --user -o --include build
python3 devscripts/install_deps.py --print --include pyinstaller > requirements.txt
# We need to ignore wheels otherwise we break universal2 builds
python3 -m pip install -U --user --no-binary :all: Pyinstaller -r requirements.txt
python3 -m pip install -U --user --no-binary :all: -r requirements.txt
- name: Prepare
run: |
@ -250,9 +254,9 @@ jobs:
python3 devscripts/make_lazy_extractors.py
- name: Build
run: |
python3 pyinst.py --target-architecture universal2 --onedir
python3 -m bundle.pyinstaller --target-architecture universal2 --onedir
(cd ./dist/yt-dlp_macos && zip -r ../yt-dlp_macos.zip .)
python3 pyinst.py --target-architecture universal2
python3 -m bundle.pyinstaller --target-architecture universal2
- name: Verify --update-to
if: vars.UPDATE_TO_VERIFICATION
@ -265,11 +269,13 @@ jobs:
[[ "$version" != "$downgraded_version" ]]
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-${{ github.job }}
path: |
dist/yt-dlp_macos
dist/yt-dlp_macos.zip
compression-level: 0
macos_legacy:
needs: process
@ -293,8 +299,8 @@ jobs:
- name: Install Requirements
run: |
brew install coreutils
python3 -m pip install -U --user pip setuptools wheel
python3 -m pip install -U --user Pyinstaller -r requirements.txt
python3 devscripts/install_deps.py --user -o --include build
python3 devscripts/install_deps.py --user --include pyinstaller
- name: Prepare
run: |
@ -302,7 +308,7 @@ jobs:
python3 devscripts/make_lazy_extractors.py
- name: Build
run: |
python3 pyinst.py
python3 -m bundle.pyinstaller
mv dist/yt-dlp_macos dist/yt-dlp_macos_legacy
- name: Verify --update-to
@ -316,10 +322,12 @@ jobs:
[[ "$version" != "$downgraded_version" ]]
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-${{ github.job }}
path: |
dist/yt-dlp_macos_legacy
compression-level: 0
windows:
needs: process
@ -328,13 +336,14 @@ jobs:
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
- uses: actions/setup-python@v5
with: # 3.8 is used for Win7 support
python-version: "3.8"
- name: Install Requirements
run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
python -m pip install -U pip setuptools wheel py2exe
pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-5.8.0-py3-none-any.whl" -r requirements.txt
python devscripts/install_deps.py -o --include build
python devscripts/install_deps.py --include py2exe
python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-5.8.0-py3-none-any.whl"
- name: Prepare
run: |
@ -342,10 +351,10 @@ jobs:
python devscripts/make_lazy_extractors.py
- name: Build
run: |
python setup.py py2exe
python -m bundle.py2exe
Move-Item ./dist/yt-dlp.exe ./dist/yt-dlp_min.exe
python pyinst.py
python pyinst.py --onedir
python -m bundle.pyinstaller
python -m bundle.pyinstaller --onedir
Compress-Archive -Path ./dist/yt-dlp/* -DestinationPath ./dist/yt-dlp_win.zip
- name: Verify --update-to
@ -362,12 +371,14 @@ jobs:
}
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-${{ github.job }}
path: |
dist/yt-dlp.exe
dist/yt-dlp_min.exe
dist/yt-dlp_win.zip
compression-level: 0
windows32:
needs: process
@ -376,14 +387,15 @@ jobs:
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
- uses: actions/setup-python@v5
with:
python-version: "3.8"
architecture: "x86"
- name: Install Requirements
run: |
python -m pip install -U pip setuptools wheel
pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-5.8.0-py3-none-any.whl" -r requirements.txt
python devscripts/install_deps.py -o --include build
python devscripts/install_deps.py
python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-5.8.0-py3-none-any.whl"
- name: Prepare
run: |
@ -391,7 +403,7 @@ jobs:
python devscripts/make_lazy_extractors.py
- name: Build
run: |
python pyinst.py
python -m bundle.pyinstaller
- name: Verify --update-to
if: vars.UPDATE_TO_VERIFICATION
@ -407,10 +419,12 @@ jobs:
}
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-${{ github.job }}
path: |
dist/yt-dlp_x86.exe
compression-level: 0
meta_files:
if: inputs.meta_files && always() && !cancelled()
@ -424,7 +438,11 @@ jobs:
- windows32
runs-on: ubuntu-latest
steps:
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
path: artifact
pattern: build-*
merge-multiple: true
- name: Make SHA2-SUMS files
run: |
@ -459,8 +477,10 @@ jobs:
done
- name: Upload artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: build-${{ github.job }}
path: |
SHA*SUMS*
_update_spec
SHA*SUMS*
compression-level: 0

4
.github/workflows/core.yml vendored
View file

@ -49,11 +49,11 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install test requirements
run: pip install pytest -r requirements.txt
run: python3 ./devscripts/install_deps.py --include dev
- name: Run tests
continue-on-error: False
run: |

8
.github/workflows/download.yml vendored
View file

@ -11,11 +11,11 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: 3.9
- name: Install test requirements
run: pip install pytest -r requirements.txt
run: python3 ./devscripts/install_deps.py --include dev
- name: Run tests
continue-on-error: true
run: python3 ./devscripts/run_tests.py download
@ -38,11 +38,11 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install test requirements
run: pip install pytest -r requirements.txt
run: python3 ./devscripts/install_deps.py --include dev
- name: Run tests
continue-on-error: true
run: python3 ./devscripts/run_tests.py download

10
.github/workflows/quick-test.yml vendored
View file

@ -11,11 +11,11 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Set up Python 3.8
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.8'
- name: Install test requirements
run: pip install pytest -r requirements.txt
run: python3 ./devscripts/install_deps.py --include dev
- name: Run tests
run: |
python3 -m yt_dlp -v || true
@ -26,10 +26,10 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
- uses: actions/setup-python@v5
- name: Install flake8
run: pip install flake8
run: python3 ./devscripts/install_deps.py -o --include dev
- name: Make lazy extractors
run: python devscripts/make_lazy_extractors.py
run: python3 ./devscripts/make_lazy_extractors.py
- name: Run flake8
run: flake8 .

6
.github/workflows/release-master.yml vendored
View file

@ -6,8 +6,10 @@ on:
paths:
- "yt_dlp/**.py"
- "!yt_dlp/version.py"
- "setup.py"
- "pyinst.py"
- "bundle/*.py"
- "pyproject.toml"
- "Makefile"
- ".github/workflows/build.yml"
concurrency:
group: release-master
permissions:

9
.github/workflows/release-nightly.yml vendored
View file

@ -18,7 +18,14 @@ jobs:
- name: Check for new commits
id: check_for_new_commits
run: |
relevant_files=("yt_dlp/*.py" ':!yt_dlp/version.py' "setup.py" "pyinst.py")
relevant_files=(
"yt_dlp/*.py"
':!yt_dlp/version.py'
"bundle/*.py"
"pyproject.toml"
"Makefile"
".github/workflows/build.yml"
)
echo "commit=$(git log --format=%H -1 --since="24 hours ago" -- "${relevant_files[@]}")" | tee "$GITHUB_OUTPUT"
release:

26
.github/workflows/release.yml vendored
View file

@ -71,7 +71,7 @@ jobs:
with:
fetch-depth: 0
- uses: actions/setup-python@v4
- uses: actions/setup-python@v5
with:
python-version: "3.10"
@ -246,15 +246,16 @@ jobs:
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
with:
fetch-depth: 0
- uses: actions/setup-python@v5
with:
python-version: "3.10"
- name: Install Requirements
run: |
sudo apt -y install pandoc man
python -m pip install -U pip setuptools wheel twine
python -m pip install -U -r requirements.txt
python devscripts/install_deps.py -o --include build
- name: Prepare
env:
@ -266,14 +267,19 @@ jobs:
run: |
python devscripts/update-version.py -c "${{ env.channel }}" -r "${{ env.target_repo }}" -s "${{ env.suffix }}" "${{ env.version }}"
python devscripts/make_lazy_extractors.py
sed -i -E "s/(name=')[^']+(', # package name)/\1${{ env.pypi_project }}\2/" setup.py
sed -i -E '0,/(name = ")[^"]+(")/s//\1${{ env.pypi_project }}\2/' pyproject.toml
- name: Build
run: |
rm -rf dist/*
make pypi-files
printf '%s\n\n' \
'Official repository: <https://github.com/yt-dlp/yt-dlp>' \
'**PS**: Some links in this document will not work since this is a copy of the README.md from Github' > ./README.md.new
cat ./README.md >> ./README.md.new && mv -f ./README.md.new ./README.md
python devscripts/set-variant.py pip -M "You installed yt-dlp with pip or using the wheel from PyPi; Use that to update"
python setup.py sdist bdist_wheel
make clean-cache
python -m build --no-isolation .
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
@ -290,8 +296,12 @@ jobs:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: actions/download-artifact@v3
- uses: actions/setup-python@v4
- uses: actions/download-artifact@v4
with:
path: artifact
pattern: build-*
merge-multiple: true
- uses: actions/setup-python@v5
with:
python-version: "3.10"

10
MANIFEST.in
View file

@ -1,10 +0,0 @@
include AUTHORS
include Changelog.md
include LICENSE
include README.md
include completions/*/*
include supportedsites.md
include yt-dlp.1
include requirements.txt
recursive-include devscripts *
recursive-include test *

51
Makefile
View file

@ -6,11 +6,11 @@ doc: README.md CONTRIBUTING.md issuetemplates supportedsites
ot: offlinetest
tar: yt-dlp.tar.gz
# Keep this list in sync with MANIFEST.in
# Keep this list in sync with pyproject.toml includes/artifacts
# intended use: when building a source distribution,
# make pypi-files && python setup.py sdist
# make pypi-files && python3 -m build -sn .
pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
completions yt-dlp.1 requirements.txt setup.cfg devscripts/* test/*
completions yt-dlp.1 pyproject.toml setup.cfg devscripts/* test/*
.PHONY: all clean install test tar pypi-files completions ot offlinetest codetest supportedsites
@ -21,7 +21,7 @@ clean-test:
*.mp4 *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS .mailmap
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS
clean-cache:
find . \( \
-type d -name .pytest_cache -o -type d -name __pycache__ -o -name "*.pyc" -o -name "*.class" \
@ -38,11 +38,13 @@ MANDIR ?= $(PREFIX)/man
SHAREDIR ?= $(PREFIX)/share
PYTHON ?= /usr/bin/env python3
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
# $(shell) and $(error) are no-ops in BSD Make and the != variable assignment operator is not supported by GNU Make <4.0
VERSION_CHECK != echo supported
VERSION_CHECK ?= $(error GNU Make 4+ or BSD Make is required)
CHECK_VERSION := $(VERSION_CHECK)
# set markdown input format to "markdown-smart" for pandoc version 2 and to "markdown" for pandoc prior to version 2
MARKDOWN = $(shell if [ `pandoc -v | head -n1 | cut -d" " -f2 | head -c1` = "2" ]; then echo markdown-smart; else echo markdown; fi)
# set markdown input format to "markdown-smart" for pandoc version 2+ and to "markdown" for pandoc prior to version 2
MARKDOWN != if [ "`pandoc -v | head -n1 | cut -d' ' -f2 | head -c1`" -ge "2" ]; then echo markdown-smart; else echo markdown; fi
install: lazy-extractors yt-dlp yt-dlp.1 completions
mkdir -p $(DESTDIR)$(BINDIR)
@ -73,24 +75,24 @@ test:
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 yt_dlp/networking
yt-dlp: yt_dlp/*.py yt_dlp/*/*.py
CODE_FOLDERS != find yt_dlp -type f -name '__init__.py' -exec dirname {} \+ | grep -v '/__' | sort
CODE_FILES != for f in $(CODE_FOLDERS) ; do echo "$$f" | sed 's,$$,/*.py,' ; done
yt-dlp: $(CODE_FILES)
mkdir -p zip
for d in $(CODE_FOLDERS) ; do \
mkdir -p zip/$$d ;\
cp -pPR $$d/*.py zip/$$d/ ;\
done
touch -t 200001010101 zip/yt_dlp/*.py zip/yt_dlp/*/*.py
(cd zip && touch -t 200001010101 $(CODE_FILES))
mv zip/yt_dlp/__main__.py zip/
cd zip ; zip -q ../yt-dlp yt_dlp/*.py yt_dlp/*/*.py __main__.py
(cd zip && zip -q ../yt-dlp $(CODE_FILES) __main__.py)
rm -rf zip
echo '#!$(PYTHON)' > yt-dlp
cat yt-dlp.zip >> yt-dlp
rm yt-dlp.zip
chmod a+x yt-dlp
README.md: yt_dlp/*.py yt_dlp/*/*.py devscripts/make_readme.py
README.md: $(CODE_FILES) devscripts/make_readme.py
COLUMNS=80 $(PYTHON) yt_dlp/__main__.py --ignore-config --help | $(PYTHON) devscripts/make_readme.py
CONTRIBUTING.md: README.md devscripts/make_contributing.py
@ -115,19 +117,19 @@ yt-dlp.1: README.md devscripts/prepare_manpage.py
pandoc -s -f $(MARKDOWN) -t man yt-dlp.1.temp.md -o yt-dlp.1
rm -f yt-dlp.1.temp.md
completions/bash/yt-dlp: yt_dlp/*.py yt_dlp/*/*.py devscripts/bash-completion.in
completions/bash/yt-dlp: $(CODE_FILES) devscripts/bash-completion.in
mkdir -p completions/bash
$(PYTHON) devscripts/bash-completion.py
completions/zsh/_yt-dlp: yt_dlp/*.py yt_dlp/*/*.py devscripts/zsh-completion.in
completions/zsh/_yt-dlp: $(CODE_FILES) devscripts/zsh-completion.in
mkdir -p completions/zsh
$(PYTHON) devscripts/zsh-completion.py
completions/fish/yt-dlp.fish: yt_dlp/*.py yt_dlp/*/*.py devscripts/fish-completion.in
completions/fish/yt-dlp.fish: $(CODE_FILES) devscripts/fish-completion.in
mkdir -p completions/fish
$(PYTHON) devscripts/fish-completion.py
_EXTRACTOR_FILES = $(shell find yt_dlp/extractor -name '*.py' -and -not -name 'lazy_extractors.py')
_EXTRACTOR_FILES != find yt_dlp/extractor -name '*.py' -and -not -name 'lazy_extractors.py'
yt_dlp/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
$(PYTHON) devscripts/make_lazy_extractors.py $@
@ -141,15 +143,12 @@ yt-dlp.tar.gz: all
--exclude '__pycache__' \
--exclude '.pytest_cache' \
--exclude '.git' \
--exclude '__pyinstaller' \
-- \
README.md supportedsites.md Changelog.md LICENSE \
CONTRIBUTING.md Collaborators.md CONTRIBUTORS AUTHORS \
Makefile MANIFEST.in yt-dlp.1 README.txt completions \
setup.py setup.cfg yt-dlp yt_dlp requirements.txt \
devscripts test
Makefile yt-dlp.1 README.txt completions .gitignore \
setup.cfg yt-dlp yt_dlp pyproject.toml devscripts test
AUTHORS: .mailmap
git shortlog -s -n | cut -f2 | sort > AUTHORS
.mailmap:
git shortlog -s -e -n | awk '!(out[$$NF]++) { $$1="";sub(/^[ \t]+/,""); print}' > .mailmap
AUTHORS:
git shortlog -s -n HEAD | cut -f2 | sort > AUTHORS

21
README.md
View file

@ -321,19 +321,21 @@ ### Deprecated
## COMPILE
### Standalone PyInstaller Builds
To build the standalone executable, you must have Python and `pyinstaller` (plus any of yt-dlp's [optional dependencies](#dependencies) if needed). Once you have all the necessary dependencies installed, simply run `pyinst.py`. The executable will be built for the same architecture (x86/ARM, 32/64 bit) as the Python used.
To build the standalone executable, you must have Python and `pyinstaller` (plus any of yt-dlp's [optional dependencies](#dependencies) if needed). The executable will be built for the same architecture (x86/ARM, 32/64 bit) as the Python used. You can run the following commands:
python3 -m pip install -U pyinstaller -r requirements.txt
```
python3 devscripts/install_deps.py --include pyinstaller
python3 devscripts/make_lazy_extractors.py
python3 pyinst.py
python3 -m bundle.pyinstaller
```
On some systems, you may need to use `py` or `python` instead of `python3`.
`pyinst.py` accepts any arguments that can be passed to `pyinstaller`, such as `--onefile/-F` or `--onedir/-D`, which is further [documented here](https://pyinstaller.org/en/stable/usage.html#what-to-generate).
`bundle/pyinstaller.py` accepts any arguments that can be passed to `pyinstaller`, such as `--onefile/-F` or `--onedir/-D`, which is further [documented here](https://pyinstaller.org/en/stable/usage.html#what-to-generate).
**Note**: Pyinstaller versions below 4.4 [do not support](https://github.com/pyinstaller/pyinstaller#requirements-and-tested-platforms) Python installed from the Windows store without using a virtual environment.
**Important**: Running `pyinstaller` directly **without** using `pyinst.py` is **not** officially supported. This may or may not work correctly.
**Important**: Running `pyinstaller` directly **without** using `bundle/pyinstaller.py` is **not** officially supported. This may or may not work correctly.
### Platform-independent Binary (UNIX)
You will need the build tools `python` (3.8+), `zip`, `make` (GNU), `pandoc`\* and `pytest`\*.
@ -346,14 +348,17 @@ ### Standalone Py2Exe Builds (Windows)
While we provide the option to build with [py2exe](https://www.py2exe.org), it is recommended to build [using PyInstaller](#standalone-pyinstaller-builds) instead since the py2exe builds **cannot contain `pycryptodomex`/`certifi` and needs VC++14** on the target computer to run.
If you wish to build it anyway, install Python and py2exe, and then simply run `setup.py py2exe`
If you wish to build it anyway, install Python (if it is not already installed) and you can run the following commands:
py -m pip install -U py2exe -r requirements.txt
```
py devscripts/install_deps.py --include py2exe
py devscripts/make_lazy_extractors.py
py setup.py py2exe
py -m bundle.py2exe
```
### Related scripts
* **`devscripts/install_deps.py`** - Install dependencies for yt-dlp.
* **`devscripts/update-version.py`** - Update the version number based on current date.
* **`devscripts/set-variant.py`** - Set the build variant of the executable.
* **`devscripts/make_changelog.py`** - Create a markdown changelog using short commit messages and update `CONTRIBUTORS` file.

1
bundle/__init__.py Normal file
View file

@ -0,0 +1 @@
# Empty file

59
bundle/py2exe.py Executable file
View file

@ -0,0 +1,59 @@
#!/usr/bin/env python3
# Allow execution from anywhere
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import warnings
from py2exe import freeze
from devscripts.utils import read_version
VERSION = read_version()
def main():
warnings.warn(
'py2exe builds do not support pycryptodomex and needs VC++14 to run. '
'It is recommended to run "pyinst.py" to build using pyinstaller instead')
return freeze(
console=[{
'script': './yt_dlp/__main__.py',
'dest_base': 'yt-dlp',
'icon_resources': [(1, 'devscripts/logo.ico')],
}],
version_info={
'version': VERSION,
'description': 'A youtube-dl fork with additional features and patches',
'comments': 'Official repository: <https://github.com/yt-dlp/yt-dlp>',
'product_name': 'yt-dlp',
'product_version': VERSION,
},
options={
'bundle_files': 0,
'compressed': 1,
'optimize': 2,
'dist_dir': './dist',
'excludes': [
# py2exe cannot import Crypto
'Crypto',
'Cryptodome',
# py2exe appears to confuse this with our socks library.
# We don't use pysocks and urllib3.contrib.socks would fail to import if tried.
'urllib3.contrib.socks'
],
'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'],
# Modules that are only imported dynamically must be added here
'includes': ['yt_dlp.compat._legacy', 'yt_dlp.compat._deprecated',
'yt_dlp.utils._legacy', 'yt_dlp.utils._deprecated'],
},
zipfile=None,
)
if __name__ == '__main__':
main()

2
pyinst.py → bundle/pyinstaller.py Normal file → Executable file
View file

@ -4,7 +4,7 @@
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import platform

66
devscripts/install_deps.py Executable file
View file

@ -0,0 +1,66 @@
#!/usr/bin/env python3
# Allow execution from anywhere
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import argparse
import re
import subprocess
from devscripts.tomlparse import parse_toml
from devscripts.utils import read_file
def parse_args():
parser = argparse.ArgumentParser(description='Install dependencies for yt-dlp')
parser.add_argument(
'input', nargs='?', metavar='TOMLFILE', default='pyproject.toml', help='Input file (default: %(default)s)')
parser.add_argument(
'-e', '--exclude', metavar='REQUIREMENT', action='append', help='Exclude a required dependency')
parser.add_argument(
'-i', '--include', metavar='GROUP', action='append', help='Include an optional dependency group')
parser.add_argument(
'-o', '--only-optional', action='store_true', help='Only install optional dependencies')
parser.add_argument(
'-p', '--print', action='store_true', help='Only print a requirements.txt to stdout')
parser.add_argument(
'-u', '--user', action='store_true', help='Install with pip as --user')
return parser.parse_args()
def main():
args = parse_args()
toml_data = parse_toml(read_file(args.input))
deps = toml_data['project']['dependencies']
targets = deps.copy() if not args.only_optional else []
for exclude in args.exclude or []:
for dep in deps:
simplified_dep = re.match(r'[\w-]+', dep)[0]
if dep in targets and (exclude.lower() == simplified_dep.lower() or exclude == dep):
targets.remove(dep)
optional_deps = toml_data['project']['optional-dependencies']
for include in args.include or []:
group = optional_deps.get(include)
if group:
targets.extend(group)
if args.print:
for target in targets:
print(target)
return
pip_args = [sys.executable, '-m', 'pip', 'install', '-U']
if args.user:
pip_args.append('--user')
pip_args.extend(targets)
return subprocess.call(pip_args)
if __name__ == '__main__':
sys.exit(main())

189
devscripts/tomlparse.py Executable file
View file

@ -0,0 +1,189 @@
#!/usr/bin/env python3
"""
Simple parser for spec compliant toml files
A simple toml parser for files that comply with the spec.
Should only be used to parse `pyproject.toml` for `install_deps.py`.
IMPORTANT: INVALID FILES OR MULTILINE STRINGS ARE NOT SUPPORTED!
"""
from __future__ import annotations
import datetime
import json
import re
WS = r'(?:[\ \t]*)'
STRING_RE = re.compile(r'"(?:\\.|[^\\"\n])*"|\'[^\'\n]*\'')
SINGLE_KEY_RE = re.compile(rf'{STRING_RE.pattern}|[A-Za-z0-9_-]+')
KEY_RE = re.compile(rf'{WS}(?:{SINGLE_KEY_RE.pattern}){WS}(?:\.{WS}(?:{SINGLE_KEY_RE.pattern}){WS})*')
EQUALS_RE = re.compile(rf'={WS}')
WS_RE = re.compile(WS)
_SUBTABLE = rf'(?P<subtable>^\[(?P<is_list>\[)?(?P<path>{KEY_RE.pattern})\]\]?)'
EXPRESSION_RE = re.compile(rf'^(?:{_SUBTABLE}|{KEY_RE.pattern}=)', re.MULTILINE)
LIST_WS_RE = re.compile(rf'{WS}((#[^\n]*)?\n{WS})*')
LEFTOVER_VALUE_RE = re.compile(r'[^,}\]\t\n#]+')
def parse_key(value: str):
for match in SINGLE_KEY_RE.finditer(value):
if match[0][0] == '"':
yield json.loads(match[0])
elif match[0][0] == '\'':
yield match[0][1:-1]
else:
yield match[0]
def get_target(root: dict, paths: list[str], is_list=False):
target = root
for index, key in enumerate(paths, 1):
use_list = is_list and index == len(paths)
result = target.get(key)
if result is None:
result = [] if use_list else {}
target[key] = result
if isinstance(result, dict):
target = result
elif use_list:
target = {}
result.append(target)
else:
target = result[-1]
assert isinstance(target, dict)
return target
def parse_enclosed(data: str, index: int, end: str, ws_re: re.Pattern):
index += 1
if match := ws_re.match(data, index):
index = match.end()
while data[index] != end:
index = yield True, index
if match := ws_re.match(data, index):
index = match.end()
if data[index] == ',':
index += 1
if match := ws_re.match(data, index):
index = match.end()
assert data[index] == end
yield False, index + 1
def parse_value(data: str, index: int):
if data[index] == '[':
result = []
indices = parse_enclosed(data, index, ']', LIST_WS_RE)
valid, index = next(indices)
while valid:
index, value = parse_value(data, index)
result.append(value)
valid, index = indices.send(index)
return index, result
if data[index] == '{':
result = {}
indices = parse_enclosed(data, index, '}', WS_RE)
valid, index = next(indices)
while valid:
valid, index = indices.send(parse_kv_pair(data, index, result))
return index, result
if match := STRING_RE.match(data, index):
return match.end(), json.loads(match[0]) if match[0][0] == '"' else match[0][1:-1]
match = LEFTOVER_VALUE_RE.match(data, index)
assert match
value = match[0].strip()
for func in [
int,
float,
datetime.time.fromisoformat,
datetime.date.fromisoformat,
datetime.datetime.fromisoformat,
{'true': True, 'false': False}.get,
]:
try:
value = func(value)
break
except Exception:
pass
return match.end(), value
def parse_kv_pair(data: str, index: int, target: dict):
match = KEY_RE.match(data, index)
if not match:
return None
*keys, key = parse_key(match[0])
match = EQUALS_RE.match(data, match.end())
assert match
index = match.end()
index, value = parse_value(data, index)
get_target(target, keys)[key] = value
return index
def parse_toml(data: str):
root = {}
target = root
index = 0
while True:
match = EXPRESSION_RE.search(data, index)
if not match:
break
if match.group('subtable'):
index = match.end()
path, is_list = match.group('path', 'is_list')
target = get_target(root, list(parse_key(path)), bool(is_list))
continue
index = parse_kv_pair(data, match.start(), target)
assert index is not None
return root
def main():
import argparse
from pathlib import Path
parser = argparse.ArgumentParser()
parser.add_argument('infile', type=Path, help='The TOML file to read as input')
args = parser.parse_args()
with args.infile.open('r', encoding='utf-8') as file:
data = file.read()
def default(obj):
if isinstance(obj, (datetime.date, datetime.time, datetime.datetime)):
return obj.isoformat()
print(json.dumps(parse_toml(data), default=default))
if __name__ == '__main__':
main()

123
pyproject.toml
View file

@ -1,5 +1,120 @@
[build-system]
build-backend = 'setuptools.build_meta'
# https://github.com/yt-dlp/yt-dlp/issues/5941
# https://github.com/pypa/distutils/issues/17
requires = ['setuptools > 50']
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "yt-dlp"
maintainers = [
{name = "pukkandan", email = "pukkandan.ytdlp@gmail.com"},
{name = "Grub4K", email = "contact@grub4k.xyz"},
{name = "bashonly", email = "bashonly@protonmail.com"},
]
description = "A youtube-dl fork with additional features and patches"
readme = "README.md"
requires-python = ">=3.8"
keywords = [
"youtube-dl",
"video-downloader",
"youtube-downloader",
"sponsorblock",
"youtube-dlc",
"yt-dlp",
]
license = {file = "LICENSE"}
classifiers = [
"Topic :: Multimedia :: Video",
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"Programming Language :: Python",
"Programming Language :: Python :: 3 :: Only",
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: Implementation",
"Programming Language :: Python :: Implementation :: CPython",
"Programming Language :: Python :: Implementation :: PyPy",
"License :: OSI Approved :: The Unlicense (Unlicense)",
"Operating System :: OS Independent",
]
dynamic = ["version"]
dependencies = [
"brotli; implementation_name=='cpython'",
"brotlicffi; implementation_name!='cpython'",
"certifi",
"mutagen",
"pycryptodomex",
"requests>=2.31.0,<3",
"urllib3>=1.26.17,<3",
"websockets>=12.0",
]
[project.optional-dependencies]
secretstorage = [
"cffi",
"secretstorage",
]
build = [
"build",
"hatchling",
"pip",
"wheel",
]
dev = [
"flake8",
"isort",
"pytest",
]
pyinstaller = ["pyinstaller>=6.3"]
py2exe = ["py2exe>=0.12"]
[project.urls]
Documentation = "https://github.com/yt-dlp/yt-dlp#readme"
Repository = "https://github.com/yt-dlp/yt-dlp"
Tracker = "https://github.com/yt-dlp/yt-dlp/issues"
Funding = "https://github.com/yt-dlp/yt-dlp/blob/master/Collaborators.md#collaborators"
[project.scripts]
yt-dlp = "yt_dlp:main"
[project.entry-points.pyinstaller40]
hook-dirs = "yt_dlp.__pyinstaller:get_hook_dirs"
[tool.hatch.build.targets.sdist]
include = [
"/yt_dlp",
"/devscripts",
"/test",
"/.gitignore", # included by default, needed for auto-excludes
"/Changelog.md",
"/LICENSE", # included as license
"/pyproject.toml", # included by default
"/README.md", # included as readme
"/setup.cfg",
"/supportedsites.md",
]
exclude = ["/yt_dlp/__pyinstaller"]
artifacts = [
"/yt_dlp/extractor/lazy_extractors.py",
"/completions",
"/AUTHORS", # included by default
"/README.txt",
"/yt-dlp.1",
]
[tool.hatch.build.targets.wheel]
packages = ["yt_dlp"]
exclude = ["/yt_dlp/__pyinstaller"]
artifacts = ["/yt_dlp/extractor/lazy_extractors.py"]
[tool.hatch.build.targets.wheel.shared-data]
"completions/bash/yt-dlp" = "share/bash-completion/completions/yt-dlp"
"completions/zsh/_yt-dlp" = "share/zsh/site-functions/_yt-dlp"
"completions/fish/yt-dlp.fish" = "share/fish/vendor_completions.d/yt-dlp.fish"
"README.txt" = "share/doc/yt_dlp/README.txt"
"yt-dlp.1" = "share/man/man1/yt-dlp.1"
[tool.hatch.version]
path = "yt_dlp/version.py"
pattern = "_pkg_version = '(?P<version>[^']+)'"

8
requirements.txt
View file

@ -1,8 +0,0 @@
mutagen
pycryptodomex
brotli; implementation_name=='cpython'
brotlicffi; implementation_name!='cpython'
certifi
requests>=2.31.0,<3
urllib3>=1.26.17,<3
websockets>=12.0

4
setup.cfg
View file

@ -1,7 +1,3 @@
[wheel]
universal = true
[flake8]
exclude = build,venv,.tox,.git,.pytest_cache
ignore = E402,E501,E731,E741,W503

183
setup.py
View file

@ -1,183 +0,0 @@
#!/usr/bin/env python3
# Allow execution from anywhere
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import subprocess
import warnings
try:
from setuptools import Command, find_packages, setup
setuptools_available = True
except ImportError:
from distutils.core import Command, setup
setuptools_available = False
from devscripts.utils import read_file, read_version
VERSION = read_version(varname='_pkg_version')
DESCRIPTION = 'A youtube-dl fork with additional features and patches'
LONG_DESCRIPTION = '\n\n'.join((
'Official repository: <https://github.com/yt-dlp/yt-dlp>',
'**PS**: Some links in this document will not work since this is a copy of the README.md from Github',
read_file('README.md')))
REQUIREMENTS = read_file('requirements.txt').splitlines()
def packages():
if setuptools_available:
return find_packages(exclude=('youtube_dl', 'youtube_dlc', 'test', 'ytdlp_plugins', 'devscripts'))
return [
'yt_dlp', 'yt_dlp.extractor', 'yt_dlp.downloader', 'yt_dlp.postprocessor', 'yt_dlp.compat',
]
def py2exe_params():
warnings.warn(
'py2exe builds do not support pycryptodomex and needs VC++14 to run. '
'It is recommended to run "pyinst.py" to build using pyinstaller instead')
return {
'console': [{
'script': './yt_dlp/__main__.py',
'dest_base': 'yt-dlp',
'icon_resources': [(1, 'devscripts/logo.ico')],
}],
'version_info': {
'version': VERSION,
'description': DESCRIPTION,
'comments': LONG_DESCRIPTION.split('\n')[0],
'product_name': 'yt-dlp',
'product_version': VERSION,
},
'options': {
'bundle_files': 0,
'compressed': 1,
'optimize': 2,
'dist_dir': './dist',
'excludes': [
# py2exe cannot import Crypto
'Crypto',
'Cryptodome',
# py2exe appears to confuse this with our socks library.
# We don't use pysocks and urllib3.contrib.socks would fail to import if tried.
'urllib3.contrib.socks'
],
'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'],
# Modules that are only imported dynamically must be added here
'includes': ['yt_dlp.compat._legacy', 'yt_dlp.compat._deprecated',
'yt_dlp.utils._legacy', 'yt_dlp.utils._deprecated'],
},
'zipfile': None,
}
def build_params():
files_spec = [
('share/bash-completion/completions', ['completions/bash/yt-dlp']),
('share/zsh/site-functions', ['completions/zsh/_yt-dlp']),
('share/fish/vendor_completions.d', ['completions/fish/yt-dlp.fish']),
('share/doc/yt_dlp', ['README.txt']),
('share/man/man1', ['yt-dlp.1'])
]
data_files = []
for dirname, files in files_spec:
resfiles = []
for fn in files:
if not os.path.exists(fn):
warnings.warn(f'Skipping file {fn} since it is not present. Try running " make pypi-files " first')
else:
resfiles.append(fn)
data_files.append((dirname, resfiles))
params = {'data_files': data_files}
if setuptools_available:
params['entry_points'] = {
'console_scripts': ['yt-dlp = yt_dlp:main'],
'pyinstaller40': ['hook-dirs = yt_dlp.__pyinstaller:get_hook_dirs'],
}
else:
params['scripts'] = ['yt-dlp']
return params
class build_lazy_extractors(Command):
description = 'Build the extractor lazy loading module'
user_options = []
def initialize_options(self):
pass
def finalize_options(self):
pass
def run(self):
if self.dry_run:
print('Skipping build of lazy extractors in dry run mode')
return
subprocess.run([sys.executable, 'devscripts/make_lazy_extractors.py'])
def main():
if sys.argv[1:2] == ['py2exe']:
params = py2exe_params()
try:
from py2exe import freeze
except ImportError:
import py2exe # noqa: F401
warnings.warn('You are using an outdated version of py2exe. Support for this version will be removed in the future')
params['console'][0].update(params.pop('version_info'))
params['options'] = {'py2exe': params.pop('options')}
else:
return freeze(**params)
else:
params = build_params()
setup(
name='yt-dlp', # package name (do not change/remove comment)
version=VERSION,
maintainer='pukkandan',
maintainer_email='pukkandan.ytdlp@gmail.com',
description=DESCRIPTION,
long_description=LONG_DESCRIPTION,
long_description_content_type='text/markdown',
url='https://github.com/yt-dlp/yt-dlp',
packages=packages(),
install_requires=REQUIREMENTS,
python_requires='>=3.8',
project_urls={
'Documentation': 'https://github.com/yt-dlp/yt-dlp#readme',
'Source': 'https://github.com/yt-dlp/yt-dlp',
'Tracker': 'https://github.com/yt-dlp/yt-dlp/issues',
'Funding': 'https://github.com/yt-dlp/yt-dlp/blob/master/Collaborators.md#collaborators',
},
classifiers=[
'Topic :: Multimedia :: Video',
'Development Status :: 5 - Production/Stable',
'Environment :: Console',
'Programming Language :: Python',
'Programming Language :: Python :: 3.8',
'Programming Language :: Python :: 3.9',
'Programming Language :: Python :: 3.10',
'Programming Language :: Python :: 3.11',
'Programming Language :: Python :: 3.12',
'Programming Language :: Python :: Implementation',
'Programming Language :: Python :: Implementation :: CPython',
'Programming Language :: Python :: Implementation :: PyPy',
'License :: Public Domain',
'Operating System :: OS Independent',
],
cmdclass={'build_lazy_extractors': build_lazy_extractors},
**params
)
main()

22
yt_dlp/extractor/_extractors.py
View file

@ -257,6 +257,7 @@
from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bongacams import BongaCamsIE
from .boosty import BoostyIE
from .bostonglobe import BostonGlobeIE
from .box import BoxIE
from .boxcast import BoxCastVideoIE
@ -1247,7 +1248,10 @@
NexxIE,
NexxEmbedIE,
)
from .nfb import NFBIE
from .nfb import (
NFBIE,
NFBSeriesIE,
)
from .nfhsnetwork import NFHSNetworkIE
from .nfl import (
NFLIE,
@ -1284,6 +1288,7 @@
NicovideoTagURLIE,
NiconicoLiveIE,
)
from .ninaprotocol import NinaProtocolIE
from .ninecninemedia import (
NineCNineMediaIE,
CPTwentyFourIE,
@ -1348,6 +1353,12 @@
NYTimesIE,
NYTimesArticleIE,
NYTimesCookingIE,
NYTimesCookingRecipeIE,
)
from .nuum import (
NuumLiveIE,
NuumTabIE,
NuumMediaIE,
)
from .nuvid import NuvidIE
from .nzherald import NZHeraldIE
@ -1390,6 +1401,7 @@
from .orf import (
ORFTVthekIE,
ORFFM4StoryIE,
ORFONIE,
ORFRadioIE,
ORFPodcastIE,
ORFIPTVIE,
@ -1514,7 +1526,7 @@
PuhuTVSerieIE,
)
from .pr0gramm import Pr0grammIE
from .prankcast import PrankCastIE
from .prankcast import PrankCastIE, PrankCastPostIE
from .premiershiprugby import PremiershipRugbyIE
from .presstv import PressTVIE
from .projectveritas import ProjectVeritasIE
@ -2309,11 +2321,6 @@
WashingtonPostIE,
WashingtonPostArticleIE,
)
from .wasdtv import (
WASDTVStreamIE,
WASDTVRecordIE,
WASDTVClipIE,
)
from .wat import WatIE
from .wdr import (
WDRIE,
@ -2492,6 +2499,7 @@
Zee5SeriesIE,
)
from .zeenews import ZeeNewsIE
from .zetland import ZetlandDKArticleIE
from .zhihu import ZhihuIE
from .zingmp3 import (
ZingMp3IE,

10
yt_dlp/extractor/antenna.py
View file

@ -78,14 +78,14 @@ class Ant1NewsGrArticleIE(AntennaBaseIE):
_TESTS = [{
'url': 'https://www.ant1news.gr/afieromata/article/549468/o-tzeims-mpont-sta-meteora-oi-apeiles-kai-o-xesikomos-ton-kalogeron',
'md5': '294f18331bb516539d72d85a82887dcc',
'md5': '57eb8d12181f0fa2b14b0b138e1de9b6',
'info_dict': {
'id': '_xvg/m_cmbatw=',
'ext': 'mp4',
'title': 'md5:a93e8ecf2e4073bfdffcb38f59945411',
'timestamp': 1603092840,
'upload_date': '20201019',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
'timestamp': 1666166520,
'upload_date': '20221019',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/1920/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
},
}, {
'url': 'https://ant1news.gr/Society/article/620286/symmoria-anilikon-dikigoros-thymaton-ithelan-na-toys-apoteleiosoyn',
@ -117,7 +117,7 @@ class Ant1NewsGrEmbedIE(AntennaBaseIE):
_BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
_VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
_EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
_API_PATH = '/news/templates/data/jsonPlayer'
_API_PATH = '/templates/data/jsonPlayer'
_TESTS = [{
'url': 'https://www.antenna.gr/templates/pages/player?cid=3f_li_c_az_jw_y_u=&w=670&h=377',

55
yt_dlp/extractor/bilibili.py
View file

@ -7,6 +7,7 @@
import re
import time
import urllib.parse
import uuid
from .common import InfoExtractor, SearchInfoExtractor
from ..dependencies import Cryptodome
@ -1304,6 +1305,26 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'upload_date': '20211127',
},
'playlist_mincount': 513,
}, {
'url': 'https://www.bilibili.com/list/1958703906?sid=547718&oid=687146339&bvid=BV1DU4y1r7tz',
'info_dict': {
'id': 'BV1DU4y1r7tz',
'ext': 'mp4',
'title': '【直播回放】8.20晚9:30 3d发布喵 2022年8月20日21点场',
'upload_date': '20220820',
'description': '',
'timestamp': 1661016330,
'uploader_id': '1958703906',
'uploader': '靡烟miya',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'duration': 9552.903,
'tags': list,
'comment_count': int,
'view_count': int,
'like_count': int,
'_old_archive_ids': ['bilibili 687146339_part1'],
},
'params': {'noplaylist': True},
}, {
'url': 'https://www.bilibili.com/medialist/play/1958703906?business=space_series&business_id=547718&desc=1',
'info_dict': {
@ -1355,6 +1376,11 @@ def _extract_medialist(self, query, list_id):
def _real_extract(self, url):
list_id = self._match_id(url)
bvid = traverse_obj(parse_qs(url), ('bvid', 0))
if not self._yes_playlist(list_id, bvid):
return self.url_result(f'https://www.bilibili.com/video/{bvid}', BiliBiliIE)
webpage = self._download_webpage(url, list_id)
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', list_id)
if traverse_obj(initial_state, ('error', 'code', {int_or_none})) != 200:
@ -1464,8 +1490,37 @@ class BiliBiliSearchIE(SearchInfoExtractor):
IE_DESC = 'Bilibili video search'
_MAX_RESULTS = 100000
_SEARCH_KEY = 'bilisearch'
_TESTS = [{
'url': 'bilisearch3:靡烟 出道一年，我怎么还在等你单推的女人睡觉后开播啊',
'playlist_count': 3,
'info_dict': {
'id': '靡烟 出道一年，我怎么还在等你单推的女人睡觉后开播啊',
'title': '靡烟 出道一年，我怎么还在等你单推的女人睡觉后开播啊',
},
'playlist': [{
'info_dict': {
'id': 'BV1n44y1Q7sc',
'ext': 'mp4',
'title': '“出道一年，我怎么还在等你单推的女人睡觉后开播啊？”【一分钟了解靡烟miya】',
'timestamp': 1669889987,
'upload_date': '20221201',
'description': 'md5:43343c0973defff527b5a4b403b4abf9',
'tags': list,
'uploader': '靡烟miya',
'duration': 123.156,
'uploader_id': '1958703906',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 988222410_part1'],
},
}],
}]
def _search_results(self, query):
if not self._get_cookies('https://api.bilibili.com').get('buvid3'):
self._set_cookie('.bilibili.com', 'buvid3', f'{uuid.uuid4()}infoc')
for page_num in itertools.count(1):
videos = self._download_json(
'https://api.bilibili.com/x/web-interface/search/type', query,

209
yt_dlp/extractor/boosty.py Normal file
View file

@ -0,0 +1,209 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
ExtractorError,
int_or_none,
qualities,
str_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BoostyIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?boosty\.to/(?P<user>[^/#?]+)/posts/(?P<post_id>[^/#?]+)'
_TESTS = [{
# single ok_video
'url': 'https://boosty.to/kuplinov/posts/e55d050c-e3bb-4873-a7db-ac7a49b40c38',
'info_dict': {
'id': 'd7473824-352e-48e2-ae53-d4aa39459968',
'title': 'phasma_3',
'channel': 'Kuplinov',
'channel_id': '7958701',
'timestamp': 1655031975,
'upload_date': '20220612',
'release_timestamp': 1655049000,
'release_date': '20220612',
'modified_timestamp': 1668680993,
'modified_date': '20221117',
'tags': ['куплинов', 'phasmophobia'],
'like_count': int,
'ext': 'mp4',
'duration': 105,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}, {
# multiple ok_video
'url': 'https://boosty.to/maddyson/posts/0c652798-3b35-471f-8b48-a76a0b28736f',
'info_dict': {
'id': '0c652798-3b35-471f-8b48-a76a0b28736f',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
},
'playlist_count': 3,
'playlist': [{
'info_dict': {
'id': 'cc325a9f-a563-41c6-bf47-516c1b506c9a',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
'ext': 'mp4',
'duration': 31204,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}, {
'info_dict': {
'id': 'd07b0a72-9493-4512-b54e-55ce468fd4b7',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
'ext': 'mp4',
'duration': 25704,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}, {
'info_dict': {
'id': '4a3bba32-78c8-422a-9432-2791aff60b42',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
'ext': 'mp4',
'duration': 31867,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}],
}, {
# single external video (youtube)
'url': 'https://boosty.to/denischuzhoy/posts/6094a487-bcec-4cf8-a453-43313b463c38',
'info_dict': {
'id': 'EXelTnve5lY',
'title': 'Послание Президента Федеральному Собранию | Класс народа',
'upload_date': '20210425',
'channel': 'Денис Чужой',
'tags': 'count:10',
'like_count': int,
'ext': 'mp4',
'duration': 816,
'view_count': int,
'thumbnail': r're:^https://i\.ytimg\.com/',
'age_limit': 0,
'availability': 'public',
'categories': list,
'channel_follower_count': int,
'channel_id': 'UCCzVNbWZfYpBfyofCCUD_0w',
'channel_is_verified': bool,
'channel_url': r're:^https://www\.youtube\.com/',
'comment_count': int,
'description': str,
'heatmap': 'count:100',
'live_status': str,
'playable_in_embed': bool,
'uploader': str,
'uploader_id': str,
'uploader_url': r're:^https://www\.youtube\.com/',
},
}]
_MP4_TYPES = ('tiny', 'lowest', 'low', 'medium', 'high', 'full_hd', 'quad_hd', 'ultra_hd')
def _extract_formats(self, player_urls, video_id):
formats = []
quality = qualities(self._MP4_TYPES)
for player_url in traverse_obj(player_urls, lambda _, v: url_or_none(v['url'])):
url = player_url['url']
format_type = player_url.get('type')
if format_type in ('hls', 'hls_live', 'live_ondemand_hls', 'live_playback_hls'):
formats.extend(self._extract_m3u8_formats(url, video_id, m3u8_id='hls', fatal=False))
elif format_type in ('dash', 'dash_live', 'live_playback_dash'):
formats.extend(self._extract_mpd_formats(url, video_id, mpd_id='dash', fatal=False))
elif format_type in self._MP4_TYPES:
formats.append({
'url': url,
'ext': 'mp4',
'format_id': format_type,
'quality': quality(format_type),
})
else:
self.report_warning(f'Unknown format type: {format_type!r}')
return formats
def _real_extract(self, url):
user, post_id = self._match_valid_url(url).group('user', 'post_id')
post = self._download_json(
f'https://api.boosty.to/v1/blog/{user}/post/{post_id}', post_id,
note='Downloading post data', errnote='Unable to download post data')
post_title = post.get('title')
if not post_title:
self.report_warning('Unable to extract post title. Falling back to parsing html page')
webpage = self._download_webpage(url, video_id=post_id)
post_title = self._og_search_title(webpage, default=None) or self._html_extract_title(webpage)
common_metadata = {
'title': post_title,
**traverse_obj(post, {
'channel': ('user', 'name', {str}),
'channel_id': ('user', 'id', {str_or_none}),
'timestamp': ('createdAt', {int_or_none}),
'release_timestamp': ('publishTime', {int_or_none}),
'modified_timestamp': ('updatedAt', {int_or_none}),
'tags': ('tags', ..., 'title', {str}),
'like_count': ('count', 'likes', {int_or_none}),
}),
}
entries = []
for item in traverse_obj(post, ('data', ..., {dict})):
item_type = item.get('type')
if item_type == 'video' and url_or_none(item.get('url')):
entries.append(self.url_result(item['url'], YoutubeIE))
elif item_type == 'ok_video':
video_id = item.get('id') or post_id
entries.append({
'id': video_id,
'formats': self._extract_formats(item.get('playerUrls'), video_id),
**common_metadata,
**traverse_obj(item, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'view_count': ('viewsCounter', {int_or_none}),
'thumbnail': (('previewUrl', 'defaultPreview'), {url_or_none}),
}, get_all=False)})
if not entries:
raise ExtractorError('No videos found', expected=True)
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries, post_id, post_title, **common_metadata)

6
yt_dlp/extractor/ccma.py
View file

@ -1,6 +1,7 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
int_or_none,
parse_duration,
parse_resolution,
@ -60,6 +61,7 @@ def _real_extract(self, url):
'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
'media': media_type,
'idint': media_id,
'format': 'dm',
})
formats = []
@ -69,6 +71,10 @@ def _real_extract(self, url):
format_url = url_or_none(format_.get('file'))
if not format_url:
continue
if determine_ext(format_url) == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, media_id, mpd_id='dash', fatal=False))
continue
label = format_.get('label')
f = parse_resolution(label)
f.update({

5
yt_dlp/extractor/cineverse.py
View file

@ -67,7 +67,10 @@ def _real_extract(self, url):
html = self._download_webpage(url, video_id)
idetails = self._search_nextjs_data(html, video_id)['props']['pageProps']['idetails']
if idetails.get('err_code') == 1200:
err_code = idetails.get('err_code')
if err_code == 1002:
self.raise_login_required()
elif err_code == 1200:
self.raise_geo_restricted(
'This video is not available from your location due to geo restriction. '
'You may be able to bypass it by using the /details/ page instead of the /watch/ page',

5
yt_dlp/extractor/crooksandliars.py
View file

@ -33,10 +33,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(
'http://embed.crooksandliars.com/embed/%s' % video_id, video_id)
manifest = self._parse_json(
self._search_regex(
r'var\s+manifest\s*=\s*({.+?})\n', webpage, 'manifest JSON'),
video_id)
manifest = self._search_json(r'var\s+manifest\s*=', webpage, 'manifest JSON', video_id)
quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))

13
yt_dlp/extractor/eporner.py
View file

@ -1,8 +1,10 @@
from .common import InfoExtractor
from ..utils import (
encode_base_n,
ExtractorError,
encode_base_n,
get_elements_by_class,
int_or_none,
join_nonempty,
merge_dicts,
parse_duration,
str_to_int,
@ -81,6 +83,7 @@ def calc_hash(s):
sources = video['sources']
formats = []
has_av1 = bool(get_elements_by_class('download-av1', webpage))
for kind, formats_dict in sources.items():
if not isinstance(formats_dict, dict):
continue
@ -106,6 +109,14 @@ def calc_hash(s):
'height': height,
'fps': fps,
})
if has_av1:
formats.append({
'url': src.replace('.mp4', '-av1.mp4'),
'format_id': join_nonempty('av1', format_id),
'height': height,
'fps': fps,
'vcodec': 'av1',
})
json_ld = self._search_json_ld(webpage, display_id, default={})

28
yt_dlp/extractor/funk.py
View file

@ -1,25 +1,29 @@
from .common import InfoExtractor
from .nexx import NexxIE
from ..utils import (
int_or_none,
str_or_none,
)
class FunkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|origin\.)?funk\.net/(?:channel|playlist)/[^/]+/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.funk.net/channel/ba-793/die-lustigsten-instrumente-aus-dem-internet-teil-2-1155821',
'md5': '8dd9d9ab59b4aa4173b3197f2ea48e81',
'md5': '8610449476156f338761a75391b0017d',
'info_dict': {
'id': '1155821',
'ext': 'mp4',
'title': 'Die LUSTIGSTEN INSTRUMENTE aus dem Internet - Teil 2',
'description': 'md5:a691d0413ef4835588c5b03ded670c1f',
'description': 'md5:2a03b67596eda0d1b5125c299f45e953',
'timestamp': 1514507395,
'upload_date': '20171229',
'duration': 426.0,
'cast': ['United Creators PMB GmbH'],
'thumbnail': 'https://assets.nexx.cloud/media/75/56/79/3YKUSJN1LACN0CRxL.jpg',
'display_id': 'die-lustigsten-instrumente-aus-dem-internet-teil-2',
'alt_title': 'Die LUSTIGSTEN INSTRUMENTE aus dem Internet Teil 2',
'season_number': 0,
'season': 'Season 0',
'episode_number': 0,
'episode': 'Episode 0',
},
}, {
'url': 'https://www.funk.net/playlist/neuesteVideos/kameras-auf-dem-fusion-festival-1618699',
'only_matching': True,
@ -27,18 +31,10 @@ class FunkIE(InfoExtractor):
def _real_extract(self, url):
display_id, nexx_id = self._match_valid_url(url).groups()
video = self._download_json(
'https://www.funk.net/api/v4.0/videos/' + nexx_id, nexx_id)
return {
'_type': 'url_transparent',
'url': 'nexx:741:' + nexx_id,
'url': f'nexx:741:{nexx_id}',
'ie_key': NexxIE.ie_key(),
'id': nexx_id,
'title': video.get('title'),
'description': video.get('description'),
'duration': int_or_none(video.get('duration')),
'channel_id': str_or_none(video.get('channelId')),
'display_id': display_id,
'tags': video.get('tags'),
'thumbnail': video.get('imageUrlLandscape'),
}

11
yt_dlp/extractor/lefigaro.py
View file

@ -13,7 +13,7 @@ class LeFigaroVideoEmbedIE(InfoExtractor):
_TESTS = [{
'url': 'https://video.lefigaro.fr/embed/figaro/video/les-francais-ne-veulent-ils-plus-travailler-suivez-en-direct-le-club-le-figaro-idees/',
'md5': 'e94de44cd80818084352fcf8de1ce82c',
'md5': 'a0c3069b7e4c4526abf0053a7713f56f',
'info_dict': {
'id': 'g9j7Eovo',
'title': 'Les Français ne veulent-ils plus travailler ? Retrouvez Le Club Le Figaro Idées',
@ -26,7 +26,7 @@ class LeFigaroVideoEmbedIE(InfoExtractor):
},
}, {
'url': 'https://video.lefigaro.fr/embed/figaro/video/intelligence-artificielle-faut-il-sen-mefier/',
'md5': '0b3f10332b812034b3a3eda1ef877c5f',
'md5': '319c662943dd777bab835cae1e2d73a5',
'info_dict': {
'id': 'LeAgybyc',
'title': 'Intelligence artificielle : faut-il s’en méfier ?',
@ -41,7 +41,7 @@ class LeFigaroVideoEmbedIE(InfoExtractor):
_WEBPAGE_TESTS = [{
'url': 'https://video.lefigaro.fr/figaro/video/suivez-en-direct-le-club-le-figaro-international-avec-philippe-gelie-9/',
'md5': '3972ddf2d5f8b98699f191687258e2f9',
'md5': '6289f9489efb969e38245f31721596fe',
'info_dict': {
'id': 'QChnbPYA',
'title': 'Où en est le couple franco-allemand ? Retrouvez Le Club Le Figaro International',
@ -55,7 +55,7 @@ class LeFigaroVideoEmbedIE(InfoExtractor):
},
}, {
'url': 'https://video.lefigaro.fr/figaro/video/la-philosophe-nathalie-sarthou-lajus-est-linvitee-du-figaro-live/',
'md5': '3ac0a0769546ee6be41ab52caea5d9a9',
'md5': 'f6df814cae53e85937621599d2967520',
'info_dict': {
'id': 'QJzqoNbf',
'title': 'La philosophe Nathalie Sarthou-Lajus est l’invitée du Figaro Live',
@ -73,7 +73,8 @@ def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_data = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['pageData']['playerData']
player_data = self._search_nextjs_data(
webpage, display_id)['props']['pageProps']['initialProps']['pageData']['playerData']
return self.url_result(
f'jwplatform:{player_data["videoId"]}', title=player_data.get('title'),

14
yt_dlp/extractor/magellantv.py
View file

@ -28,12 +28,24 @@ class MagellanTVIE(InfoExtractor):
'tags': ['Investigation', 'True Crime', 'Justice', 'Europe'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.magellantv.com/watch/celebration-nation',
'info_dict': {
'id': 'celebration-nation',
'ext': 'mp4',
'tags': ['Art & Culture', 'Human Interest', 'Anthropology', 'China', 'History'],
'duration': 2640.0,
'title': 'Ancestors',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['reactContext']['video']['detail']
data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
'props', 'pageProps', 'reactContext',
(('video', 'detail'), ('series', 'currentEpisode')), {dict}), get_all=False)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(data['jwpVideoUrl'], video_id)
return {

288
yt_dlp/extractor/nfb.py
View file

@ -1,10 +1,54 @@
from .common import InfoExtractor
from ..utils import int_or_none
from ..utils import (
int_or_none,
join_nonempty,
merge_dicts,
parse_count,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class NFBIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nfb\.ca/film/(?P<id>[^/?#&]+)'
class NFBBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?(?P<site>nfb|onf)\.ca'
_GEO_COUNTRIES = ['CA']
def _extract_ep_data(self, webpage, video_id, fatal=False):
return self._search_json(
r'const\s+episodesData\s*=', webpage, 'episode data', video_id,
contains_pattern=r'\[\s*{(?s:.+)}\s*\]', fatal=fatal) or []
def _extract_ep_info(self, data, video_id, slug=None):
info = traverse_obj(data, (lambda _, v: video_id in v['embed_url'], {
'description': ('description', {str}),
'thumbnail': ('thumbnail_url', {url_or_none}),
'uploader': ('data_layer', 'episodeMaker', {str}),
'release_year': ('data_layer', 'episodeYear', {int_or_none}),
'episode': ('data_layer', 'episodeTitle', {str}),
'season': ('data_layer', 'seasonTitle', {str}),
'season_number': ('data_layer', 'seasonTitle', {parse_count}),
'series': ('data_layer', 'seriesTitle', {str}),
}), get_all=False)
return {
**info,
'id': video_id,
'title': join_nonempty('series', 'episode', from_dict=info, delim=' - '),
'episode_number': int_or_none(self._search_regex(
r'[/-]e(?:pisode)?-?(\d+)(?:[/-]|$)', slug or video_id, 'episode number', default=None)),
}
class NFBIE(NFBBaseIE):
IE_NAME = 'nfb'
IE_DESC = 'nfb.ca and onf.ca films and episodes'
_VALID_URL = [
rf'{NFBBaseIE._VALID_URL_BASE}/(?P<type>film)/(?P<id>[^/?#&]+)',
rf'{NFBBaseIE._VALID_URL_BASE}/(?P<type>series?)/(?P<id>[^/?#&]+/s(?:ea|ai)son\d+/episode\d+)',
]
_TESTS = [{
'note': 'NFB film',
'url': 'https://www.nfb.ca/film/trafficopter/',
'info_dict': {
'id': 'trafficopter',
@ -14,29 +58,192 @@ class NFBIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Barrie Howells',
'release_year': 1972,
'duration': 600.0,
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF film',
'url': 'https://www.onf.ca/film/mal-du-siecle/',
'info_dict': {
'id': 'mal-du-siecle',
'ext': 'mp4',
'title': 'Le mal du siècle',
'description': 'md5:1abf774d77569ebe603419f2d344102b',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Catherine Lepage',
'release_year': 2019,
'duration': 300.0,
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB episode with English title',
'url': 'https://www.nfb.ca/series/true-north-inside-the-rise-of-toronto-basketball/season1/episode9/',
'info_dict': {
'id': 'true-north-episode9-true-north-finale-making-it',
'ext': 'mp4',
'title': 'True North: Inside the Rise of Toronto Basketball - Finale: Making It',
'description': 'We catch up with each player in the midst of their journey as they reflect on their road ahead.',
'series': 'True North: Inside the Rise of Toronto Basketball',
'release_year': 2018,
'season': 'Season 1',
'season_number': 1,
'episode': 'Finale: Making It',
'episode_number': 9,
'uploader': 'Ryan Sidhoo',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF episode with French title',
'url': 'https://www.onf.ca/serie/direction-nord-la-montee-du-basketball-a-toronto/saison1/episode9/',
'info_dict': {
'id': 'direction-nord-episode-9',
'ext': 'mp4',
'title': 'Direction nord – La montée du basketball à Toronto - Finale : Réussir',
'description': 'md5:349a57419b71432b97bf6083d92b029d',
'series': 'Direction nord – La montée du basketball à Toronto',
'release_year': 2018,
'season': 'Saison 1',
'season_number': 1,
'episode': 'Finale : Réussir',
'episode_number': 9,
'uploader': 'Ryan Sidhoo',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB episode with French title (needs geo-bypass)',
'url': 'https://www.nfb.ca/series/etoile-du-nord/saison1/episode1/',
'info_dict': {
'id': 'etoile-du-nord-episode-1-lobservation',
'ext': 'mp4',
'title': 'Étoile du Nord - L\'observation',
'description': 'md5:161a4617260dee3de70f509b2c9dd21b',
'series': 'Étoile du Nord',
'release_year': 2023,
'season': 'Saison 1',
'season_number': 1,
'episode': 'L\'observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF episode with English title (needs geo-bypass)',
'url': 'https://www.onf.ca/serie/north-star/season1/episode1/',
'info_dict': {
'id': 'north-star-episode-1-observation',
'ext': 'mp4',
'title': 'North Star - Observation',
'description': 'md5:c727f370839d8a817392b9e3f23655c7',
'series': 'North Star',
'release_year': 2023,
'season': 'Season 1',
'season_number': 1,
'episode': 'Observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB episode with /film/ URL and English title (needs geo-bypass)',
'url': 'https://www.nfb.ca/film/north-star-episode-1-observation/',
'info_dict': {
'id': 'north-star-episode-1-observation',
'ext': 'mp4',
'title': 'North Star - Observation',
'description': 'md5:c727f370839d8a817392b9e3f23655c7',
'series': 'North Star',
'release_year': 2023,
'season': 'Season 1',
'season_number': 1,
'episode': 'Observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF episode with /film/ URL and French title (needs geo-bypass)',
'url': 'https://www.onf.ca/film/etoile-du-nord-episode-1-lobservation/',
'info_dict': {
'id': 'etoile-du-nord-episode-1-lobservation',
'ext': 'mp4',
'title': 'Étoile du Nord - L\'observation',
'description': 'md5:161a4617260dee3de70f509b2c9dd21b',
'series': 'Étoile du Nord',
'release_year': 2023,
'season': 'Saison 1',
'season_number': 1,
'episode': 'L\'observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'Season 2 episode w/o episode num in id, extract from json ld',
'url': 'https://www.onf.ca/film/liste-des-choses-qui-existent-saison-2-ours',
'info_dict': {
'id': 'liste-des-choses-qui-existent-saison-2-ours',
'ext': 'mp4',
'title': 'La liste des choses qui existent - L\'ours en peluche',
'description': 'md5:d5e8d8fc5f3a7385a9cf0f509b37e28a',
'series': 'La liste des choses qui existent',
'release_year': 2022,
'season': 'Saison 2',
'season_number': 2,
'episode': 'L\'ours en peluche',
'episode_number': 12,
'uploader': 'Francis Papillon',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB film /embed/player/ page',
'url': 'https://www.nfb.ca/film/afterlife/embed/player/',
'info_dict': {
'id': 'afterlife',
'ext': 'mp4',
'title': 'Afterlife',
'description': 'md5:84951394f594f1fb1e62d9c43242fdf5',
'release_year': 1978,
'duration': 420.0,
'uploader': 'Ishu Patel',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
site, type_, slug = self._match_valid_url(url).group('site', 'type', 'id')
# Need to construct the URL since we match /embed/player/ URLs as well
webpage, urlh = self._download_webpage_handle(f'https://www.{site}.ca/{type_}/{slug}/', slug)
# type_ can change from film to serie(s) after redirect; new slug may have episode number
type_, slug = self._match_valid_url(urlh.url).group('type', 'id')
webpage = self._download_webpage('https://www.nfb.ca/film/%s/' % video_id, video_id)
embed_url = urljoin(f'https://www.{site}.ca', self._html_search_regex(
r'<[^>]+\bid=["\']player-iframe["\'][^>]*\bsrc=["\']([^"\']+)', webpage, 'embed url'))
video_id = self._match_id(embed_url) # embed url has unique slug
player = self._download_webpage(embed_url, video_id, 'Downloading player page')
if 'MESSAGE_GEOBLOCKED' in player:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
iframe = self._html_search_regex(
r'<[^>]+\bid=["\']player-iframe["\'][^>]*src=["\']([^"\']+)',
webpage, 'iframe', default=None, fatal=True)
if iframe.startswith('/'):
iframe = f'https://www.nfb.ca{iframe}'
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
self._html_search_regex(r'source:\s*\'([^\']+)', player, 'm3u8 url'),
video_id, 'mp4', m3u8_id='hls')
player = self._download_webpage(iframe, video_id)
if dv_source := self._html_search_regex(r'dvSource:\s*\'([^\']+)', player, 'dv', default=None):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
dv_source, video_id, 'mp4', m3u8_id='dv', preference=-2, fatal=False)
for fmt in fmts:
fmt['format_note'] = 'described video'
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
source = self._html_search_regex(
r'source:\s*\'([^\']+)',
player, 'source', default=None, fatal=True)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(source, video_id, ext='mp4')
return {
info = {
'id': video_id,
'title': self._html_search_regex(
r'<[^>]+\bid=["\']titleHeader["\'][^>]*>\s*<h1[^>]*>\s*([^<]+?)\s*</h1>',
@ -45,14 +252,49 @@ def _real_extract(self, url):
r'<[^>]+\bid=["\']tabSynopsis["\'][^>]*>\s*<p[^>]*>\s*([^<]+)',
webpage, 'description', default=None),
'thumbnail': self._html_search_regex(
r'poster:\s*\'([^\']+)',
player, 'thumbnail', default=None),
r'poster:\s*\'([^\']+)', player, 'thumbnail', default=None),
'uploader': self._html_search_regex(
r'<[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)',
webpage, 'uploader', default=None),
r'<[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', webpage, 'uploader', default=None),
'release_year': int_or_none(self._html_search_regex(
r'<[^>]+\bitemprop=["\']datePublished["\'][^>]*>([^<]+)',
webpage, 'release_year', default=None)),
} if type_ == 'film' else self._extract_ep_info(self._extract_ep_data(webpage, video_id, slug), video_id)
return merge_dicts({
'formats': formats,
'subtitles': subtitles,
}
}, info, self._search_json_ld(webpage, video_id, default={}))
class NFBSeriesIE(NFBBaseIE):
IE_NAME = 'nfb:series'
IE_DESC = 'nfb.ca and onf.ca series'
_VALID_URL = rf'{NFBBaseIE._VALID_URL_BASE}/(?P<type>series?)/(?P<id>[^/?#&]+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.nfb.ca/series/true-north-inside-the-rise-of-toronto-basketball/',
'playlist_mincount': 9,
'info_dict': {
'id': 'true-north-inside-the-rise-of-toronto-basketball',
},
}, {
'url': 'https://www.onf.ca/serie/la-liste-des-choses-qui-existent-serie/',
'playlist_mincount': 26,
'info_dict': {
'id': 'la-liste-des-choses-qui-existent-serie',
},
}]
def _entries(self, episodes):
for episode in traverse_obj(episodes, lambda _, v: NFBIE.suitable(v['embed_url'])):
mobj = NFBIE._match_valid_url(episode['embed_url'])
yield self.url_result(
mobj[0], NFBIE, **self._extract_ep_info([episode], mobj.group('id')))
def _real_extract(self, url):
site, type_, series_id = self._match_valid_url(url).group('site', 'type', 'id')
season_path = 'saison' if type_ == 'serie' else 'season'
webpage = self._download_webpage(
f'https://www.{site}.ca/{type_}/{series_id}/{season_path}1/episode1', series_id)
episodes = self._extract_ep_data(webpage, series_id, fatal=True)
return self.playlist_result(self._entries(episodes), series_id)

225
yt_dlp/extractor/ninaprotocol.py Normal file
View file

@ -0,0 +1,225 @@
from .common import InfoExtractor
from ..utils import int_or_none, mimetype2ext, parse_iso8601, url_or_none
from ..utils.traversal import traverse_obj
class NinaProtocolIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ninaprotocol\.com/releases/(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'https://www.ninaprotocol.com/releases/3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ',
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ',
'title': 'The Spatulas - March Chant',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'channel': 'ppm',
'description': 'md5:bb9f9d39d8f786449cd5d0ff7c5772db',
'album': 'The Spatulas - March Chant',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'timestamp': 1701417610,
'uploader': 'ppmrecs',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'display_id': 'the-spatulas-march-chant',
'upload_date': '20231201',
'album_artist': 'Post Present Medium ',
},
'playlist': [{
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_1',
'title': 'March Chant In April',
'track': 'March Chant In April',
'ext': 'mp3',
'duration': 152,
'track_number': 1,
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'uploader': 'ppmrecs',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'timestamp': 1701417610,
'channel': 'ppm',
'album': 'The Spatulas - March Chant',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'upload_date': '20231201',
'album_artist': 'Post Present Medium ',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_2',
'title': 'Rescue Mission',
'track': 'Rescue Mission',
'ext': 'mp3',
'duration': 212,
'track_number': 2,
'album_artist': 'Post Present Medium ',
'uploader': 'ppmrecs',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'channel': 'ppm',
'upload_date': '20231201',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'timestamp': 1701417610,
'album': 'The Spatulas - March Chant',
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_3',
'title': 'Slinger Style',
'track': 'Slinger Style',
'ext': 'mp3',
'duration': 179,
'track_number': 3,
'timestamp': 1701417610,
'upload_date': '20231201',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'album_artist': 'Post Present Medium ',
'album': 'The Spatulas - March Chant',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'uploader': 'ppmrecs',
'channel': 'ppm',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_4',
'title': 'Psychic Signal',
'track': 'Psychic Signal',
'ext': 'mp3',
'duration': 220,
'track_number': 4,
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'upload_date': '20231201',
'album': 'The Spatulas - March Chant',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'timestamp': 1701417610,
'album_artist': 'Post Present Medium ',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'channel': 'ppm',
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'uploader': 'ppmrecs',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_5',
'title': 'Curvy Color',
'track': 'Curvy Color',
'ext': 'mp3',
'duration': 148,
'track_number': 5,
'timestamp': 1701417610,
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'album': 'The Spatulas - March Chant',
'album_artist': 'Post Present Medium ',
'channel': 'ppm',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'uploader': 'ppmrecs',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'upload_date': '20231201',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_6',
'title': 'Caveman Star',
'track': 'Caveman Star',
'ext': 'mp3',
'duration': 121,
'track_number': 6,
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'album_artist': 'Post Present Medium ',
'uploader': 'ppmrecs',
'timestamp': 1701417610,
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'album': 'The Spatulas - March Chant',
'channel': 'ppm',
'upload_date': '20231201',
},
}],
}, {
'url': 'https://www.ninaprotocol.com/releases/f-g-s-american-shield',
'info_dict': {
'id': '76PZnJwaMgViQHYfA4NYJXds7CmW6vHQKAtQUxGene6J',
'description': 'md5:63f08d5db558b4b36e1896f317062721',
'title': 'F.G.S. - American Shield',
'uploader_id': 'Ej3rozs11wYqFk1Gs6oggGCkGLz8GzBhmJfnUxf6gPci',
'channel_id': '6JuksCZPXuP16wJ1BUfwuukJzh42C7guhLrFPPkVJfyE',
'channel': 'tinkscough',
'tags': [],
'album_artist': 'F.G.S.',
'album': 'F.G.S. - American Shield',
'thumbnail': 'https://www.arweave.net/YJpgImkXLT9SbpFb576KuZ5pm6bdvs452LMs3Rx6lm8',
'display_id': 'f-g-s-american-shield',
'uploader': 'flannerysilva',
'timestamp': 1702395858,
'upload_date': '20231212',
},
'playlist_count': 1,
}, {
'url': 'https://www.ninaprotocol.com/releases/time-to-figure-things-out',
'info_dict': {
'id': '6Zi1nC5hj6b13NkpxVYwRhFy6mYA7oLBbe9DMrgGDcYh',
'display_id': 'time-to-figure-things-out',
'description': 'md5:960202ed01c3134bb8958f1008527e35',
'timestamp': 1706283607,
'title': 'DJ STEPDAD - time to figure things out',
'album_artist': 'DJ STEPDAD',
'uploader': 'tddvsss',
'upload_date': '20240126',
'album': 'time to figure things out',
'uploader_id': 'AXQNRgTyYsySyAMFDwxzumuGjfmoXshorCesjpquwCBi',
'thumbnail': 'https://www.arweave.net/O4i8bcKVqJVZvNeHHFp6r8knpFGh9ZwEgbeYacr4nss',
'tags': [],
},
'playlist_count': 4,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
release = self._download_json(
f'https://api.ninaprotocol.com/v1/releases/{video_id}', video_id)['release']
video_id = release.get('publicKey') or video_id
common_info = traverse_obj(release, {
'album': ('metadata', 'properties', 'title', {str}),
'album_artist': ((('hub', 'data'), 'publisherAccount'), 'displayName', {str}),
'timestamp': ('datetime', {parse_iso8601}),
'thumbnail': ('metadata', 'image', {url_or_none}),
'uploader': ('publisherAccount', 'handle', {str}),
'uploader_id': ('publisherAccount', 'publicKey', {str}),
'channel': ('hub', 'handle', {str}),
'channel_id': ('hub', 'publicKey', {str}),
}, get_all=False)
common_info['tags'] = traverse_obj(release, ('metadata', 'properties', 'tags', ..., {str}))
entries = []
for track_num, track in enumerate(traverse_obj(release, (
'metadata', 'properties', 'files', lambda _, v: url_or_none(v['uri']))), 1):
entries.append({
'id': f'{video_id}_{track_num}',
'url': track['uri'],
**traverse_obj(track, {
'title': ('track_title', {str}),
'track': ('track_title', {str}),
'ext': ('type', {mimetype2ext}),
'track_number': ('track', {int_or_none}),
'duration': ('duration', {int_or_none}),
}),
'vcodec': 'none',
**common_info,
})
return {
'_type': 'playlist',
'id': video_id,
'entries': entries,
**traverse_obj(release, {
'display_id': ('slug', {str}),
'title': ('metadata', 'name', {str}),
'description': ('metadata', 'description', {str}),
}),
**common_info,
}

199
yt_dlp/extractor/nuum.py Normal file
View file

@ -0,0 +1,199 @@
import functools
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
UserNotLive,
filter_dict,
int_or_none,
parse_iso8601,
str_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class NuumBaseIE(InfoExtractor):
def _call_api(self, path, video_id, description, query={}):
response = self._download_json(
f'https://nuum.ru/api/v2/{path}', video_id, query=query,
note=f'Downloading {description} metadata',
errnote=f'Unable to download {description} metadata')
if error := response.get('error'):
raise ExtractorError(f'API returned error: {error!r}')
return response['result']
def _get_channel_info(self, channel_name):
return self._call_api(
'broadcasts/public', video_id=channel_name, description='channel',
query={
'with_extra': 'true',
'channel_name': channel_name,
'with_deleted': 'true',
})
def _parse_video_data(self, container, extract_formats=True):
stream = traverse_obj(container, ('media_container_streams', 0, {dict})) or {}
media = traverse_obj(stream, ('stream_media', 0, {dict})) or {}
media_url = traverse_obj(media, (
'media_meta', ('media_archive_url', 'media_url'), {url_or_none}), get_all=False)
video_id = str(container['media_container_id'])
is_live = media.get('media_status') == 'RUNNING'
formats, subtitles = None, None
if extract_formats:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
media_url, video_id, 'mp4', live=is_live)
return filter_dict({
'id': video_id,
'is_live': is_live,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(container, {
'title': ('media_container_name', {str}),
'description': ('media_container_description', {str}),
'timestamp': ('created_at', {parse_iso8601}),
'channel': ('media_container_channel', 'channel_name', {str}),
'channel_id': ('media_container_channel', 'channel_id', {str_or_none}),
}),
**traverse_obj(stream, {
'view_count': ('stream_total_viewers', {int_or_none}),
'concurrent_view_count': ('stream_current_viewers', {int_or_none}),
}),
**traverse_obj(media, {
'duration': ('media_duration', {int_or_none}),
'thumbnail': ('media_meta', ('media_preview_archive_url', 'media_preview_url'), {url_or_none}),
}, get_all=False),
})
class NuumMediaIE(NuumBaseIE):
IE_NAME = 'nuum:media'
_VALID_URL = r'https?://nuum\.ru/(?:streams|videos|clips)/(?P<id>[\d]+)'
_TESTS = [{
'url': 'https://nuum.ru/streams/1592713-7-days-to-die',
'only_matching': True,
}, {
'url': 'https://nuum.ru/videos/1567547-toxi-hurtz',
'md5': 'f1d9118a30403e32b702a204eb03aca3',
'info_dict': {
'id': '1567547',
'ext': 'mp4',
'title': 'Toxi$ - Hurtz',
'description': '',
'timestamp': 1702631651,
'upload_date': '20231215',
'thumbnail': r're:^https?://.+\.jpg',
'view_count': int,
'concurrent_view_count': int,
'channel_id': '6911',
'channel': 'toxis',
'duration': 116,
},
}, {
'url': 'https://nuum.ru/clips/1552564-pro-misu',
'md5': 'b248ae1565b1e55433188f11beeb0ca1',
'info_dict': {
'id': '1552564',
'ext': 'mp4',
'title': 'Про Мису 🙃',
'timestamp': 1701971828,
'upload_date': '20231207',
'thumbnail': r're:^https?://.+\.jpg',
'view_count': int,
'concurrent_view_count': int,
'channel_id': '3320',
'channel': 'Misalelik',
'duration': 41,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._call_api(f'media-containers/{video_id}', video_id, 'media')
return self._parse_video_data(video_data)
class NuumLiveIE(NuumBaseIE):
IE_NAME = 'nuum:live'
_VALID_URL = r'https?://nuum\.ru/channel/(?P<id>[^/#?]+)/?(?:$|[#?])'
_TESTS = [{
'url': 'https://nuum.ru/channel/mts_live',
'only_matching': True,
}]
def _real_extract(self, url):
channel = self._match_id(url)
channel_info = self._get_channel_info(channel)
if traverse_obj(channel_info, ('channel', 'channel_is_live')) is False:
raise UserNotLive(video_id=channel)
info = self._parse_video_data(channel_info['media_container'])
return {
'webpage_url': f'https://nuum.ru/streams/{info["id"]}',
'extractor_key': NuumMediaIE.ie_key(),
'extractor': NuumMediaIE.IE_NAME,
**info,
}
class NuumTabIE(NuumBaseIE):
IE_NAME = 'nuum:tab'
_VALID_URL = r'https?://nuum\.ru/channel/(?P<id>[^/#?]+)/(?P<type>streams|videos|clips)'
_TESTS = [{
'url': 'https://nuum.ru/channel/dankon_/clips',
'info_dict': {
'id': 'dankon__clips',
'title': 'Dankon_',
},
'playlist_mincount': 29,
}, {
'url': 'https://nuum.ru/channel/dankon_/videos',
'info_dict': {
'id': 'dankon__videos',
'title': 'Dankon_',
},
'playlist_mincount': 2,
}, {
'url': 'https://nuum.ru/channel/dankon_/streams',
'info_dict': {
'id': 'dankon__streams',
'title': 'Dankon_',
},
'playlist_mincount': 1,
}]
_PAGE_SIZE = 50
def _fetch_page(self, channel_id, tab_type, tab_id, page):
CONTAINER_TYPES = {
'clips': ['SHORT_VIDEO', 'REVIEW_VIDEO'],
'videos': ['LONG_VIDEO'],
'streams': ['SINGLE'],
}
media_containers = self._call_api(
'media-containers', video_id=tab_id, description=f'{tab_type} tab page {page + 1}',
query={
'limit': self._PAGE_SIZE,
'offset': page * self._PAGE_SIZE,
'channel_id': channel_id,
'media_container_status': 'STOPPED',
'media_container_type': CONTAINER_TYPES[tab_type],
})
for container in traverse_obj(media_containers, (..., {dict})):
metadata = self._parse_video_data(container, extract_formats=False)
yield self.url_result(f'https://nuum.ru/videos/{metadata["id"]}', NuumMediaIE, **metadata)
def _real_extract(self, url):
channel_name, tab_type = self._match_valid_url(url).group('id', 'type')
tab_id = f'{channel_name}_{tab_type}'
channel_data = self._get_channel_info(channel_name)['channel']
return self.playlist_result(OnDemandPagedList(functools.partial(
self._fetch_page, channel_data['channel_id'], tab_type, tab_id), self._PAGE_SIZE),
playlist_id=tab_id, playlist_title=channel_data.get('channel_name'))

452
yt_dlp/extractor/nytimes.py
View file

@ -1,50 +1,93 @@
import hmac
import hashlib
import base64
import json
import uuid
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
determine_ext,
extract_attributes,
float_or_none,
get_elements_html_by_class,
int_or_none,
js_to_json,
merge_dicts,
mimetype2ext,
parse_iso8601,
remove_end,
remove_start,
str_or_none,
traverse_obj,
url_or_none,
)
class NYTimesBaseIE(InfoExtractor):
_SECRET = b'pX(2MbU2);4N{7J8)>YwKRJ+/pQ3JkiU2Q^V>mFYv6g6gYvt6v'
_DNS_NAMESPACE = uuid.UUID('36dd619a-56dc-595b-9e09-37f4152c7b5d')
_TOKEN = 'MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAuNIzKBOFB77aT/jN/FQ+/QVKWq5V1ka1AYmCR9hstz1pGNPH5ajOU9gAqta0T89iPnhjwla+3oec/Z3kGjxbpv6miQXufHFq3u2RC6HyU458cLat5kVPSOQCe3VVB5NRpOlRuwKHqn0txfxnwSSj8mqzstR997d3gKB//RO9zE16y3PoWlDQXkASngNJEWvL19iob/xwAkfEWCjyRILWFY0JYX3AvLMSbq7wsqOCE5srJpo7rRU32zsByhsp1D5W9OYqqwDmflsgCEQy2vqTsJjrJohuNg+urMXNNZ7Y3naMoqttsGDrWVxtPBafKMI8pM2ReNZBbGQsQXRzQNo7+QIDAQAB'
_GRAPHQL_API = 'https://samizdat-graphql.nytimes.com/graphql/v2'
_GRAPHQL_QUERY = '''query VideoQuery($id: String!) {
video(id: $id) {
... on Video {
bylines {
renderedRepresentation
}
duration
firstPublished
promotionalHeadline
promotionalMedia {
... on Image {
crops {
name
renditions {
name
width
height
url
}
}
}
}
renditions {
type
width
height
url
bitrate
}
summary
}
}
}'''
def _extract_video_from_id(self, video_id):
# Authorization generation algorithm is reverse engineered from `signer` in
# http://graphics8.nytimes.com/video/vhs/vhs-2.x.min.js
path = '/svc/video/api/v3/video/' + video_id
hm = hmac.new(self._SECRET, (path + ':vhs').encode(), hashlib.sha512).hexdigest()
video_data = self._download_json('http://www.nytimes.com' + path, video_id, 'Downloading video JSON', headers={
'Authorization': 'NYTV ' + base64.b64encode(hm.encode()).decode(),
'X-NYTV': 'vhs',
}, fatal=False)
if not video_data:
video_data = self._download_json(
'http://www.nytimes.com/svc/video/api/v2/video/' + video_id,
video_id, 'Downloading video JSON')
def _call_api(self, media_id):
# reference: `id-to-uri.js`
video_uuid = uuid.uuid5(self._DNS_NAMESPACE, 'video')
media_uuid = uuid.uuid5(video_uuid, media_id)
title = video_data['headline']
return traverse_obj(self._download_json(
self._GRAPHQL_API, media_id, 'Downloading JSON from GraphQL API', data=json.dumps({
'query': self._GRAPHQL_QUERY,
'variables': {'id': f'nyt://video/{media_uuid}'},
}, separators=(',', ':')).encode(), headers={
'Content-Type': 'application/json',
'Nyt-App-Type': 'vhs',
'Nyt-App-Version': 'v3.52.21',
'Nyt-Token': self._TOKEN,
'Origin': 'https://nytimes.com',
}, fatal=False), ('data', 'video', {dict})) or {}
def get_file_size(file_size):
if isinstance(file_size, int):
return file_size
elif isinstance(file_size, dict):
return int(file_size.get('value', 0))
else:
return None
def _extract_thumbnails(self, thumbs):
return traverse_obj(thumbs, (lambda _, v: url_or_none(v['url']), {
'url': 'url',
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
}), default=None)
def _extract_formats_and_subtitles(self, video_id, content_media_json):
urls = []
formats = []
subtitles = {}
for video in video_data.get('renditions', []):
for video in traverse_obj(content_media_json, ('renditions', ..., {dict})):
video_url = video.get('url')
format_id = video.get('type')
if not video_url or format_id == 'thumbs' or video_url in urls:
@ -56,11 +99,9 @@ def get_file_size(file_size):
video_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id or 'hls', fatal=False)
formats.extend(m3u8_fmts)
subtitles = self._merge_subtitles(subtitles, m3u8_subs)
self._merge_subtitles(m3u8_subs, target=subtitles)
elif ext == 'mpd':
continue
# formats.extend(self._extract_mpd_formats(
# video_url, video_id, format_id or 'dash', fatal=False))
continue # all mpd urls give 404 errors
else:
formats.append({
'url': video_url,
@ -68,55 +109,50 @@ def get_file_size(file_size):
'vcodec': video.get('videoencoding') or video.get('video_codec'),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
'filesize': traverse_obj(video, (
('file_size', 'fileSize'), (None, ('value')), {int_or_none}), get_all=False),
'tbr': int_or_none(video.get('bitrate'), 1000) or None,
'ext': ext,
})
thumbnails = []
for image in video_data.get('images', []):
image_url = image.get('url')
if not image_url:
continue
thumbnails.append({
'url': 'http://www.nytimes.com/' + image_url,
'width': int_or_none(image.get('width')),
'height': int_or_none(image.get('height')),
})
return formats, subtitles
publication_date = video_data.get('publication_date')
timestamp = parse_iso8601(publication_date[:-8]) if publication_date else None
def _extract_video(self, media_id):
data = self._call_api(media_id)
formats, subtitles = self._extract_formats_and_subtitles(media_id, data)
return {
'id': video_id,
'title': title,
'description': video_data.get('summary'),
'timestamp': timestamp,
'uploader': video_data.get('byline'),
'duration': float_or_none(video_data.get('duration'), 1000),
'id': media_id,
'title': data.get('promotionalHeadline'),
'description': data.get('summary'),
'timestamp': parse_iso8601(data.get('firstPublished')),
'duration': float_or_none(data.get('duration'), scale=1000),
'creator': ', '.join(traverse_obj(data, ( # TODO: change to 'creators'
'bylines', ..., 'renderedRepresentation', {lambda x: remove_start(x, 'By ')}))),
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
'thumbnails': self._extract_thumbnails(
traverse_obj(data, ('promotionalMedia', 'crops', ..., 'renditions', ...))),
}
class NYTimesIE(NYTimesBaseIE):
_VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>']
_TESTS = [{
'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
'md5': 'd665342765db043f7e225cff19df0f2d',
'md5': 'a553aa344014e3723d33893d89d4defc',
'info_dict': {
'id': '100000002847155',
'ext': 'mov',
'ext': 'mp4',
'title': 'Verbatim: What Is a Photocopier?',
'description': 'md5:93603dada88ddbda9395632fdc5da260',
'timestamp': 1398631707,
'upload_date': '20140427',
'uploader': 'Brett Weiner',
'timestamp': 1398646132,
'upload_date': '20140428',
'creator': 'Brett Weiner',
'thumbnail': r're:https?://\w+\.nyt.com/images/.+\.jpg',
'duration': 419,
}
},
}, {
'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
'only_matching': True,
@ -125,138 +161,260 @@ class NYTimesIE(NYTimesBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video_from_id(video_id)
return self._extract_video(video_id)
class NYTimesArticleIE(NYTimesBaseIE):
_VALID_URL = r'https?://(?:www\.)?nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
_VALID_URL = r'https?://(?:www\.)?nytimes\.com/\d{4}/\d{2}/\d{2}/(?!books|podcasts)[^/?#]+/(?:\w+/)?(?P<id>[^./?#]+)(?:\.html)?'
_TESTS = [{
'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
'md5': 'e2076d58b4da18e6a001d53fd56db3c9',
'md5': '3eb5ddb1d6f86254fe4f233826778737',
'info_dict': {
'id': '100000003628438',
'ext': 'mov',
'title': 'New Minimum Wage: $70,000 a Year',
'description': 'Dan Price, C.E.O. of Gravity Payments, surprised his 120-person staff by announcing that he planned over the next three years to raise the salary of every employee to $70,000 a year.',
'timestamp': 1429033037,
'ext': 'mp4',
'title': 'One Company’s New Minimum Wage: $70,000 a Year',
'description': 'md5:89ba9ab67ca767bb92bf823d1f138433',
'timestamp': 1429047468,
'upload_date': '20150414',
'uploader': 'Matthew Williams',
}
'creator': 'Patricia Cohen',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
'duration': 119.0,
},
}, {
'url': 'http://www.nytimes.com/2016/10/14/podcasts/revelations-from-the-final-weeks.html',
'md5': 'e0d52040cafb07662acf3c9132db3575',
# article with audio and no video
'url': 'https://www.nytimes.com/2023/09/29/health/mosquitoes-genetic-engineering.html',
'md5': '2365b3555c8aa7f4dd34ca735ad02e6a',
'info_dict': {
'id': '100000004709062',
'title': 'The Run-Up: ‘He Was Like an Octopus’',
'id': '100000009110381',
'ext': 'mp3',
'description': 'md5:fb5c6b93b12efc51649b4847fe066ee4',
'series': 'The Run-Up',
'episode': '‘He Was Like an Octopus’',
'episode_number': 20,
'duration': 2130,
}
'title': 'The Gamble: Can Genetically Modified Mosquitoes End Disease?',
'description': 'md5:9ff8b47acbaf7f3ca8c732f5c815be2e',
'timestamp': 1695960700,
'upload_date': '20230929',
'creator': 'Stephanie Nolen, Natalija Gormalova',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
'duration': 1322,
},
}, {
'url': 'http://www.nytimes.com/2016/10/16/books/review/inside-the-new-york-times-book-review-the-rise-of-hitler.html',
'url': 'https://www.nytimes.com/2023/11/29/business/dealbook/kamala-harris-biden-voters.html',
'md5': '3eb5ddb1d6f86254fe4f233826778737',
'info_dict': {
'id': '100000004709479',
'title': 'The Rise of Hitler',
'ext': 'mp3',
'description': 'md5:bce877fd9e3444990cb141875fab0028',
'creator': 'Pamela Paul',
'duration': 3475,
'id': '100000009202270',
'ext': 'mp4',
'title': 'Kamala Harris Defends Biden Policies, but Says ‘More Work’ Needed to Reach Voters',
'description': 'md5:de4212a7e19bb89e4fb14210ca915f1f',
'timestamp': 1701290997,
'upload_date': '20231129',
'uploader': 'By The New York Times',
'creator': 'Katie Rogers',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
'duration': 97.631,
},
'params': {
'skip_download': True,
'skip_download': 'm3u8',
},
}, {
'url': 'http://www.nytimes.com/news/minute/2014/03/17/times-minute-whats-next-in-crimea/?_php=true&_type=blogs&_php=true&_type=blogs&_r=1',
# multiple videos in the same article
'url': 'https://www.nytimes.com/2023/12/02/business/air-traffic-controllers-safety.html',
'info_dict': {
'id': 'air-traffic-controllers-safety',
'title': 'Drunk and Asleep on the Job: Air Traffic Controllers Pushed to the Brink',
'description': 'md5:549e5a5e935bf7d048be53ba3d2c863d',
'upload_date': '20231202',
'creator': 'Emily Steel, Sydney Ember',
'timestamp': 1701511264,
},
'playlist_count': 3,
}, {
'url': 'https://www.nytimes.com/2023/12/02/business/media/netflix-squid-game-challenge.html',
'only_matching': True,
}]
def _extract_podcast_from_json(self, json, page_id, webpage):
podcast_audio = self._parse_json(
json, page_id, transform_source=js_to_json)
def _extract_content_from_block(self, block):
details = traverse_obj(block, {
'id': ('sourceId', {str}),
'uploader': ('bylines', ..., 'renderedRepresentation', {str}),
'duration': (None, (('duration', {lambda x: float_or_none(x, scale=1000)}), ('length', {int_or_none}))),
'timestamp': ('firstPublished', {parse_iso8601}),
'series': ('podcastSeries', {str}),
}, get_all=False)
audio_data = podcast_audio['data']
track = audio_data['track']
episode_title = track['title']
video_url = track['source']
description = track.get('description') or self._html_search_meta(
['og:description', 'twitter:description'], webpage)
podcast_title = audio_data.get('podcast', {}).get('title')
title = ('%s: %s' % (podcast_title, episode_title)
if podcast_title else episode_title)
episode = audio_data.get('podcast', {}).get('episode') or ''
episode_number = int_or_none(self._search_regex(
r'[Ee]pisode\s+(\d+)', episode, 'episode number', default=None))
formats, subtitles = self._extract_formats_and_subtitles(details.get('id'), block)
# audio articles will have an url and no formats
url = traverse_obj(block, ('fileUrl', {url_or_none}))
if not formats and url:
formats.append({'url': url, 'vcodec': 'none'})
return {
'id': remove_start(podcast_audio.get('target'), 'FT') or page_id,
'url': video_url,
'title': title,
'description': description,
'creator': track.get('credit'),
'series': podcast_title,
'episode': episode_title,
'episode_number': episode_number,
'duration': int_or_none(track.get('duration')),
**details,
'thumbnails': self._extract_thumbnails(traverse_obj(
block, ('promotionalMedia', 'crops', ..., 'renditions', ...))),
'formats': formats,
'subtitles': subtitles
}
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
art_json = self._search_json(
r'window\.__preloadedData\s*=', webpage, 'media details', page_id,
transform_source=lambda x: x.replace('undefined', 'null'))['initialData']['data']['article']
video_id = self._search_regex(
r'data-videoid=["\'](\d+)', webpage, 'video id',
default=None, fatal=False)
if video_id is not None:
return self._extract_video_from_id(video_id)
blocks = traverse_obj(art_json, (
'sprinkledBody', 'content', ..., ('ledeMedia', None),
lambda _, v: v['__typename'] in ('Video', 'Audio')))
if not blocks:
raise ExtractorError('Unable to extract any media blocks from webpage')
podcast_data = self._search_regex(
(r'NYTD\.FlexTypes\.push\s*\(\s*({.+?})\s*\)\s*;\s*</script',
r'NYTD\.FlexTypes\.push\s*\(\s*({.+})\s*\)\s*;'),
webpage, 'podcast data')
return self._extract_podcast_from_json(podcast_data, page_id, webpage)
common_info = {
'title': remove_end(self._html_extract_title(webpage), ' - The New York Times'),
'description': traverse_obj(art_json, (
'sprinkledBody', 'content', ..., 'summary', 'content', ..., 'text', {str}),
get_all=False) or self._html_search_meta(['og:description', 'twitter:description'], webpage),
'timestamp': traverse_obj(art_json, ('firstPublished', {parse_iso8601})),
'creator': ', '.join(
traverse_obj(art_json, ('bylines', ..., 'creators', ..., 'displayName'))), # TODO: change to 'creators' (list)
'thumbnails': self._extract_thumbnails(traverse_obj(
art_json, ('promotionalMedia', 'assetCrops', ..., 'renditions', ...))),
}
entries = []
for block in blocks:
entries.append(merge_dicts(self._extract_content_from_block(block), common_info))
if len(entries) > 1:
return self.playlist_result(entries, page_id, **common_info)
return {
'id': page_id,
**entries[0],
}
class NYTimesCookingIE(NYTimesBaseIE):
_VALID_URL = r'https?://cooking\.nytimes\.com/(?:guid|recip)es/(?P<id>\d+)'
IE_NAME = 'NYTimesCookingGuide'
_VALID_URL = r'https?://cooking\.nytimes\.com/guides/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://cooking.nytimes.com/recipes/1017817-cranberry-curd-tart',
'md5': 'dab81fa2eaeb3f9ed47498bdcfcdc1d3',
'url': 'https://cooking.nytimes.com/guides/13-how-to-cook-a-turkey',
'info_dict': {
'id': '100000004756089',
'ext': 'mov',
'timestamp': 1479383008,
'uploader': 'By SHAW LASH, ADAM SAEWITZ and JAMES HERRON',
'title': 'Cranberry Tart',
'upload_date': '20161117',
'description': 'If you are a fan of lemon curd or the classic French tarte au citron, you will love this cranberry version.',
'id': '13-how-to-cook-a-turkey',
'title': 'How to Cook a Turkey',
'description': 'md5:726cfd3f9b161bdf5c279879e8050ca0',
},
'playlist_count': 2,
}, {
# single video example
'url': 'https://cooking.nytimes.com/guides/50-how-to-make-mac-and-cheese',
'md5': '64415805fe0b8640fce6b0b9def5989a',
'info_dict': {
'id': '100000005835845',
'ext': 'mp4',
'title': 'How to Make Mac and Cheese',
'description': 'md5:b8f2f33ec1fb7523b21367147c9594f1',
'timestamp': 1522950315,
'upload_date': '20180405',
'duration': 9.51,
'creator': 'Alison Roman',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
},
}, {
'url': 'https://cooking.nytimes.com/guides/13-how-to-cook-a-turkey',
'md5': '4b2e8c70530a89b8d905a2b572316eb8',
'url': 'https://cooking.nytimes.com/guides/20-how-to-frost-a-cake',
'md5': '64415805fe0b8640fce6b0b9def5989a',
'info_dict': {
'id': '100000003951728',
'ext': 'mov',
'timestamp': 1445509539,
'description': 'Turkey guide',
'upload_date': '20151022',
'title': 'Turkey',
}
'id': '20-how-to-frost-a-cake',
'title': 'How to Frost a Cake',
'description': 'md5:a31fe3b98a8ce7b98aae097730c269cd',
},
'playlist_count': 8,
}]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
description = self._html_search_meta(['og:description', 'twitter:description'], webpage)
video_id = self._search_regex(
r'data-video-id=["\'](\d+)', webpage, 'video id')
lead_video_id = self._search_regex(
r'data-video-player-id="(\d+)"></div>', webpage, 'lead video')
media_ids = traverse_obj(
get_elements_html_by_class('video-item', webpage), (..., {extract_attributes}, 'data-video-id'))
return self._extract_video_from_id(video_id)
if media_ids:
media_ids.append(lead_video_id)
return self.playlist_result(
[self._extract_video(media_id) for media_id in media_ids], page_id, title, description)
return {
**self._extract_video(lead_video_id),
'title': title,
'description': description,
'creator': self._search_regex( # TODO: change to 'creators'
r'<span itemprop="author">([^<]+)</span></p>', webpage, 'author', default=None),
}
class NYTimesCookingRecipeIE(InfoExtractor):
_VALID_URL = r'https?://cooking\.nytimes\.com/recipes/(?P<id>\d+)'
_TESTS = [{
'url': 'https://cooking.nytimes.com/recipes/1017817-cranberry-curd-tart',
'md5': '579e83bbe8e61e9de67f80edba8a78a8',
'info_dict': {
'id': '1017817',
'ext': 'mp4',
'title': 'Cranberry Curd Tart',
'description': 'md5:ad77a3fc321db636256d4343c5742152',
'timestamp': 1447804800,
'upload_date': '20151118',
'creator': 'David Tanis',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
},
}, {
'url': 'https://cooking.nytimes.com/recipes/1024781-neapolitan-checkerboard-cookies',
'md5': '58df35998241dcf0620e99e646331b42',
'info_dict': {
'id': '1024781',
'ext': 'mp4',
'title': 'Neapolitan Checkerboard Cookies',
'description': 'md5:ba12394c585ababea951cb6d2fcc6631',
'timestamp': 1701302400,
'upload_date': '20231130',
'creator': 'Sue Li',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
},
}, {
'url': 'https://cooking.nytimes.com/recipes/1019516-overnight-oats',
'md5': '2fe7965a3adc899913b8e25ada360823',
'info_dict': {
'id': '1019516',
'ext': 'mp4',
'timestamp': 1546387200,
'description': 'md5:8856ce10239161bd2596ac335b9f9bfb',
'upload_date': '20190102',
'title': 'Overnight Oats',
'creator': 'Genevieve Ko',
'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
},
}]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
recipe_data = self._search_nextjs_data(webpage, page_id)['props']['pageProps']['recipe']
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
recipe_data['videoSrc'], page_id, 'mp4', m3u8_id='hls')
return {
**traverse_obj(recipe_data, {
'id': ('id', {str_or_none}),
'title': ('title', {str}),
'description': ('topnote', {clean_html}),
'timestamp': ('publishedAt', {int_or_none}),
'creator': ('contentAttribution', 'cardByline', {str}),
}),
'formats': formats,
'subtitles': subtitles,
'thumbnails': [{'url': thumb_url} for thumb_url in traverse_obj(
recipe_data, ('image', 'crops', 'recipe', ..., {url_or_none}))],
}

64
yt_dlp/extractor/orf.py
View file

@ -1,3 +1,4 @@
import base64
import functools
import re
@ -565,3 +566,66 @@ def _real_extract(self, url):
})
return self.playlist_result(entries)
class ORFONIE(InfoExtractor):
IE_NAME = 'orf:on'
_VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d{8})/(?P<slug>[\w-]+)'
_TESTS = [{
'url': 'https://on.orf.at/video/14210000/school-of-champions-48',
'info_dict': {
'id': '14210000',
'ext': 'mp4',
'duration': 2651.08,
'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0167/98/thumb_16697671_segments_highlight_teaser.jpeg',
'title': 'School of Champions (4/8)',
'description': 'md5:d09ad279fc2e8502611e7648484b6afd',
'media_type': 'episode',
'timestamp': 1706472362,
'upload_date': '20240128',
}
}]
def _extract_video(self, video_id, display_id):
encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode()
api_json = self._download_json(
f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', display_id)
formats, subtitles = [], {}
for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)):
for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})):
if manifest_type == 'hls':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
manifest_url, display_id, fatal=False, m3u8_id='hls')
elif manifest_type == 'dash':
fmts, subs = self._extract_mpd_formats_and_subtitles(
manifest_url, display_id, fatal=False, mpd_id='dash')
else:
continue
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(api_json, {
'duration': ('duration_second', {float_or_none}),
'title': (('title', 'headline'), {str}),
'description': (('description', 'teaser_text'), {str}),
'media_type': ('video_type', {str}),
}, get_all=False),
}
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'slug')
webpage = self._download_webpage(url, display_id)
return {
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
'description': self._html_search_meta(
['description', 'og:description', 'twitter:description'], webpage, default=None),
**self._search_json_ld(webpage, display_id, fatal=False),
**self._extract_video(video_id, display_id),
}

972
yt_dlp/extractor/peertube.py
View file

File diff suppressed because it is too large Load diff

73
yt_dlp/extractor/prankcast.py
View file

@ -1,5 +1,8 @@
import json
from .common import InfoExtractor
from ..utils import parse_iso8601, traverse_obj, try_call
from ..utils import float_or_none, parse_iso8601, str_or_none, try_call
from ..utils.traversal import traverse_obj
class PrankCastIE(InfoExtractor):
@ -64,3 +67,71 @@ def _real_extract(self, url):
'categories': [json_info.get('broadcast_category')],
'tags': try_call(lambda: json_info['broadcast_tags'].split(','))
}
class PrankCastPostIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?prankcast\.com/[^/?#]+/posts/(?P<id>\d+)-(?P<display_id>[^/?#]+)'
_TESTS = [{
'url': 'https://prankcast.com/devonanustart/posts/6214-happy-national-rachel-day-',
'info_dict': {
'id': '6214',
'ext': 'mp3',
'title': 'Happy National Rachel Day!',
'display_id': 'happy-national-rachel-day-',
'timestamp': 1704333938,
'uploader': 'Devonanustart',
'channel_id': '4',
'duration': 13175,
'cast': ['Devonanustart'],
'description': '',
'categories': ['prank call'],
'upload_date': '20240104'
}
}, {
'url': 'https://prankcast.com/despicabledogs/posts/6217-jake-the-work-crow-',
'info_dict': {
'id': '6217',
'ext': 'mp3',
'title': 'Jake the Work Crow!',
'display_id': 'jake-the-work-crow-',
'timestamp': 1704346592,
'uploader': 'despicabledogs',
'channel_id': '957',
'duration': 263.287,
'cast': ['despicabledogs'],
'description': 'https://imgur.com/a/vtxLvKU',
'categories': [],
'upload_date': '20240104'
}
}]
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
webpage = self._download_webpage(url, video_id)
post = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['ssr_data_posts']
content = self._parse_json(post['post_contents_json'], video_id)[0]
uploader = post.get('user_name')
guests_json = traverse_obj(content, ('guests_json', {json.loads}, {dict})) or {}
return {
'id': video_id,
'title': post.get('post_title') or self._og_search_title(webpage),
'display_id': display_id,
'url': content.get('url'),
'timestamp': parse_iso8601(content.get('start_date') or content.get('crdate'), ' '),
'uploader': uploader,
'channel_id': str_or_none(post.get('user_id')),
'duration': float_or_none(content.get('duration')),
'cast': list(filter(None, [uploader] + traverse_obj(guests_json, (..., 'name')))),
'description': post.get('post_body'),
'categories': list(filter(None, [content.get('category')])),
'tags': try_call(lambda: list(filter('', post['post_tags'].split(',')))),
'subtitles': {
'live_chat': [{
'url': f'https://prankcast.com/api/private/chat/select-broadcast?id={post["content_id"]}&cache=',
'ext': 'json',
}],
} if post.get('content_id') else None
}

11
yt_dlp/extractor/radiko.py
View file

@ -1,5 +1,6 @@
import base64
import random
import re
import urllib.parse
from .common import InfoExtractor
@ -11,6 +12,7 @@
unified_timestamp,
update_url_query,
)
from ..utils.traversal import traverse_obj
class RadikoBaseIE(InfoExtractor):
@ -159,6 +161,12 @@ def _extract_formats(self, video_id, station, is_onair, ft, cursor, auth_token,
return formats
def _extract_performers(self, prog):
performers = traverse_obj(prog, (
'pfm/text()', ..., {lambda x: re.split(r'[/／、　,，]', x)}, ..., {str.strip}))
# TODO: change 'artist' fields to 'artists' and return traversal list instead of str
return ', '.join(performers) or None
class RadikoIE(RadikoBaseIE):
_VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P<station>[A-Z0-9-]+)/(?P<id>\d+)'
@ -186,10 +194,12 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': try_call(lambda: prog.find('title').text),
'artist': self._extract_performers(prog),
'description': clean_html(try_call(lambda: prog.find('info').text)),
'uploader': try_call(lambda: station_program.find('.//name').text),
'uploader_id': station,
'timestamp': vid_int,
'duration': try_call(lambda: unified_timestamp(radio_end, False) - unified_timestamp(radio_begin, False)),
'is_live': True,
'formats': self._extract_formats(
video_id=video_id, station=station, is_onair=False,
@ -243,6 +253,7 @@ def _real_extract(self, url):
return {
'id': station,
'title': title,
'artist': self._extract_performers(prog),
'description': description,
'uploader': station_name,
'uploader_id': station,

5
yt_dlp/extractor/redtube.py
View file

@ -12,7 +12,7 @@
class RedTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com(?:\.br)?/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)']
_TESTS = [{
'url': 'https://www.redtube.com/38864951',
@ -35,6 +35,9 @@ class RedTubeIE(InfoExtractor):
}, {
'url': 'http://it.redtube.com/66418',
'only_matching': True,
}, {
'url': 'https://www.redtube.com.br/103224331',
'only_matching': True,
}]
def _real_extract(self, url):

21
yt_dlp/extractor/tvp.py
View file

@ -21,7 +21,7 @@
class TVPIE(InfoExtractor):
IE_NAME = 'tvp'
IE_DESC = 'Telewizja Polska'
_VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|tvpworld\.com|swipeto\.pl)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)'
_VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|tvpworld\.com|swipeto\.pl)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)(?:[/?#]|$)'
_TESTS = [{
# TVPlayer 2 in js wrapper
@ -514,7 +514,7 @@ def _parse_video(self, video, with_url=True):
class TVPVODVideoIE(TVPVODBaseIE):
IE_NAME = 'tvp:vod'
_VALID_URL = r'https?://vod\.tvp\.pl/[a-z\d-]+,\d+/[a-z\d-]+(?<!-odcinki)(?:-odcinki,\d+/odcinek-\d+,S\d+E\d+)?,(?P<id>\d+)(?:\?[^#]+)?(?:#.+)?$'
_VALID_URL = r'https?://vod\.tvp\.pl/(?P<category>[a-z\d-]+,\d+)/[a-z\d-]+(?<!-odcinki)(?:-odcinki,\d+/odcinek-\d+,S\d+E\d+)?,(?P<id>\d+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://vod.tvp.pl/dla-dzieci,24/laboratorium-alchemika-odcinki,309338/odcinek-24,S01E24,311357',
@ -560,12 +560,23 @@ class TVPVODVideoIE(TVPVODBaseIE):
'thumbnail': 're:https?://.+',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://vod.tvp.pl/live,1/tvp-world,399731',
'info_dict': {
'id': '399731',
'ext': 'mp4',
'title': r're:TVP WORLD \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'live_status': 'is_live',
'thumbnail': 're:https?://.+',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
category, video_id = self._match_valid_url(url).group('category', 'id')
info_dict = self._parse_video(self._call_api(f'vods/{video_id}', video_id), with_url=False)
is_live = category == 'live,1'
entity = 'lives' if is_live else 'vods'
info_dict = self._parse_video(self._call_api(f'{entity}/{video_id}', video_id), with_url=False)
playlist = self._call_api(f'{video_id}/videos/playlist', video_id, query={'videoType': 'MOVIE'})
@ -582,6 +593,8 @@ def _real_extract(self, url):
'ext': 'ttml',
})
info_dict['is_live'] = is_live
return info_dict

9
yt_dlp/extractor/vimeo.py
View file

@ -269,7 +269,7 @@ def _extract_original_format(self, url, video_id, unlisted_hash=None):
'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
if not jwt_response.get('jwt'):
return
headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
headers = {'Authorization': 'jwt %s' % jwt_response['jwt'], 'Accept': 'application/json'}
original_response = self._download_json(
f'https://api.vimeo.com/videos/{video_id}', video_id,
headers=headers, fatal=False, expected_status=(403, 404)) or {}
@ -751,6 +751,7 @@ def _extract_from_api(self, video_id, unlisted_hash=None):
video = self._download_json(
api_url, video_id, headers={
'Authorization': 'jwt ' + token,
'Accept': 'application/json',
}, query={
'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
})
@ -785,7 +786,7 @@ def _try_album_password(self, url):
jwt = viewer['jwt']
album = self._download_json(
'https://api.vimeo.com/albums/' + album_id,
album_id, headers={'Authorization': 'jwt ' + jwt},
album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
query={'fields': 'description,name,privacy'})
if try_get(album, lambda x: x['privacy']['view']) == 'password':
password = self.get_param('videopassword')
@ -1147,10 +1148,12 @@ def _fetch_page(self, album_id, authorization, hashed_pass, page):
'https://api.vimeo.com/albums/%s/videos' % album_id,
album_id, 'Downloading page %d' % api_page, query=query, headers={
'Authorization': 'jwt ' + authorization,
'Accept': 'application/json',
})['data']
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
return
raise
for video in videos:
link = video.get('link')
if not link:
@ -1171,7 +1174,7 @@ def _real_extract(self, url):
jwt = viewer['jwt']
album = self._download_json(
'https://api.vimeo.com/albums/' + album_id,
album_id, headers={'Authorization': 'jwt ' + jwt},
album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
query={'fields': 'description,name,privacy'})
hashed_pass = None
if try_get(album, lambda x: x['privacy']['view']) == 'password':

159
yt_dlp/extractor/wasdtv.py
View file

@ -1,159 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
traverse_obj,
try_get,
)
class WASDTVBaseIE(InfoExtractor):
def _fetch(self, path, video_id, description, query={}):
response = self._download_json(
f'https://wasd.tv/api/{path}', video_id, query=query,
note=f'Downloading {description} metadata',
errnote=f'Unable to download {description} metadata')
error = response.get('error')
if error:
raise ExtractorError(f'{self.IE_NAME} returned error: {error}', expected=True)
return response.get('result')
def _extract_thumbnails(self, thumbnails_dict):
return [{
'url': url,
'preference': index,
} for index, url in enumerate(
traverse_obj(thumbnails_dict, (('small', 'medium', 'large'),))) if url]
def _real_extract(self, url):
container = self._get_container(url)
stream = traverse_obj(container, ('media_container_streams', 0))
media = try_get(stream, lambda x: x['stream_media'][0])
if not media:
raise ExtractorError('Can not extract media data.', expected=True)
media_meta = media.get('media_meta')
media_url, is_live = self._get_media_url(media_meta)
video_id = media.get('media_id') or container.get('media_container_id')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(media_url, video_id, 'mp4')
return {
'id': str(video_id),
'title': container.get('media_container_name') or self._og_search_title(self._download_webpage(url, video_id)),
'description': container.get('media_container_description'),
'thumbnails': self._extract_thumbnails(media_meta.get('media_preview_images')),
'timestamp': parse_iso8601(container.get('created_at')),
'view_count': int_or_none(stream.get('stream_current_viewers' if is_live else 'stream_total_viewers')),
'is_live': is_live,
'formats': formats,
'subtitles': subtitles,
}
def _get_container(self, url):
raise NotImplementedError('Subclass for get media container')
def _get_media_url(self, media_meta):
raise NotImplementedError('Subclass for get media url')
class WASDTVStreamIE(WASDTVBaseIE):
IE_NAME = 'wasdtv:stream'
_VALID_URL = r'https?://wasd\.tv/(?P<id>[^/#?]+)$'
_TESTS = [{
'url': 'https://wasd.tv/24_7',
'info_dict': {
'id': '559738',
'ext': 'mp4',
'title': 'Live 24/7 Music',
'description': '24&#x2F;7 Music',
'timestamp': int,
'upload_date': r're:^\d{8}$',
'is_live': True,
'view_count': int,
},
}]
def _get_container(self, url):
nickname = self._match_id(url)
channel = self._fetch(f'channels/nicknames/{nickname}', video_id=nickname, description='channel')
channel_id = channel.get('channel_id')
containers = self._fetch(
'v2/media-containers', channel_id, 'running media containers',
query={
'channel_id': channel_id,
'media_container_type': 'SINGLE',
'media_container_status': 'RUNNING',
})
if not containers:
raise ExtractorError(f'{nickname} is offline', expected=True)
return containers[0]
def _get_media_url(self, media_meta):
return media_meta['media_url'], True
class WASDTVRecordIE(WASDTVBaseIE):
IE_NAME = 'wasdtv:record'
_VALID_URL = r'https?://wasd\.tv/[^/#?]+(?:/videos)?\?record=(?P<id>\d+)$'
_TESTS = [{
'url': 'https://wasd.tv/spacemita/videos?record=907755',
'md5': 'c9899dd85be4cc997816ff9f9ca516ce',
'info_dict': {
'id': '906825',
'ext': 'mp4',
'title': 'Музыкальный',
'description': 'md5:f510388d929ff60ae61d4c3cab3137cc',
'timestamp': 1645812079,
'upload_date': '20220225',
'thumbnail': r're:^https?://.+\.jpg',
'is_live': False,
'view_count': int,
},
}, {
'url': 'https://wasd.tv/spacemita?record=907755',
'only_matching': True,
}]
def _get_container(self, url):
container_id = self._match_id(url)
return self._fetch(
f'v2/media-containers/{container_id}', container_id, 'media container')
def _get_media_url(self, media_meta):
media_archive_url = media_meta.get('media_archive_url')
if media_archive_url:
return media_archive_url, False
return media_meta['media_url'], True
class WASDTVClipIE(WASDTVBaseIE):
IE_NAME = 'wasdtv:clip'
_VALID_URL = r'https?://wasd\.tv/[^/#?]+/clips\?clip=(?P<id>\d+)$'
_TESTS = [{
'url': 'https://wasd.tv/spacemita/clips?clip=26804',
'md5': '818885e720143d7a4e776ff66fcff148',
'info_dict': {
'id': '26804',
'ext': 'mp4',
'title': 'Пуш флексит на голове стримера',
'timestamp': 1646682908,
'upload_date': '20220307',
'thumbnail': r're:^https?://.+\.jpg',
'view_count': int,
},
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._fetch(f'v2/clips/{clip_id}', video_id=clip_id, description='clip')
clip_data = clip.get('clip_data')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(clip_data.get('url'), video_id=clip_id, ext='mp4')
return {
'id': clip_id,
'title': clip.get('clip_title') or self._og_search_title(self._download_webpage(url, clip_id, fatal=False)),
'thumbnails': self._extract_thumbnails(clip_data.get('preview')),
'timestamp': parse_iso8601(clip.get('created_at')),
'view_count': int_or_none(clip.get('clip_views_count')),
'formats': formats,
'subtitles': subtitles,
}

71
yt_dlp/extractor/zetland.py Normal file
View file

@ -0,0 +1,71 @@
from .common import InfoExtractor
from ..utils import merge_dicts, unified_timestamp, url_or_none
from ..utils.traversal import traverse_obj
class ZetlandDKArticleIE(InfoExtractor):
_VALID_URL = r'https?://www\.zetland\.dk/\w+/(?P<id>(?P<story_id>\w{8})-(?P<uploader_id>\w{8})-(?:\w{5}))'
_TESTS = [{
'url': 'https://www.zetland.dk/historie/sO9aq2MY-a81VP3BY-66e69?utm_source=instagram&utm_medium=linkibio&utm_campaign=artikel',
'info_dict': {
'id': 'sO9aq2MY-a81VP3BY-66e69',
'ext': 'mp3',
'modified_date': '20240118',
'title': 'Afsnit 1: “Det føltes som en kidnapning.” ',
'upload_date': '20240116',
'uploader_id': 'a81VP3BY',
'modified_timestamp': 1705568739,
'release_timestamp': 1705377592,
'uploader_url': 'https://www.zetland.dk/skribent/a81VP3BY',
'uploader': 'Helle Fuusager',
'release_date': '20240116',
'thumbnail': r're:https://zetland\.imgix\.net/2aafe500-b14e-11ee-bf83-65d5e1283a57/Zetland_Image_1\.jpg',
'description': 'md5:9619d426772c133f5abb26db27f26a01',
'timestamp': 1705377592,
'series_id': '62d54630-e87b-4ab1-a255-8de58dbe1b14',
}
}]
def _real_extract(self, url):
display_id, uploader_id = self._match_valid_url(url).group('id', 'uploader_id')
webpage = self._download_webpage(url, display_id)
next_js_data = self._search_nextjs_data(webpage, display_id)['props']['pageProps']
story_data = traverse_obj(next_js_data, ('initialState', 'consume', 'story', 'story'))
formats = []
for audio_url in traverse_obj(story_data, ('story_content', 'meta', 'audioFiles', ..., {url_or_none})):
formats.append({
'url': audio_url,
'vcodec': 'none',
})
return merge_dicts({
'id': display_id,
'formats': formats,
'uploader_id': uploader_id
}, traverse_obj(story_data, {
'title': ((('story_content', 'content', 'title'), 'title'), {str}),
'uploader': ('sharer', 'name'),
'uploader_id': ('sharer', 'sharer_id'),
'description': ('story_content', 'content', 'socialDescription'),
'series_id': ('story_content', 'meta', 'seriesId'),
'release_timestamp': ('published_at', {unified_timestamp}),
'modified_timestamp': ('revised_at', {unified_timestamp}),
}, get_all=False), traverse_obj(next_js_data, ('metaInfo', {
'title': ((('meta', 'title'), ('ld', 'headline'), ('og', 'og:title'), ('og', 'twitter:title')), {str}),
'description': ((('meta', 'description'), ('ld', 'description'), ('og', 'og:description'), ('og', 'twitter:description')), {str}),
'uploader': ((('meta', 'author'), ('ld', 'author', 'name')), {str}),
'uploader_url': ('ld', 'author', 'url', {url_or_none}),
'thumbnail': ((('ld', 'image'), ('og', 'og:image'), ('og', 'twitter:image')), {url_or_none}),
'modified_timestamp': ('ld', 'dateModified', {unified_timestamp}),
'release_timestamp': ('ld', 'datePublished', {unified_timestamp}),
'timestamp': ('ld', 'dateCreated', {unified_timestamp}),
}), get_all=False), {
'title': self._html_search_meta(['title', 'og:title', 'twitter:title'], webpage),
'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
'uploader': self._html_search_meta(['author'], webpage),
'release_timestamp': unified_timestamp(self._html_search_meta(['article:published_time'], webpage)),
}, self._search_json_ld(webpage, display_id, fatal=False))