Compare commits

...

5 Commits

Author SHA1 Message Date
Mozi
bac95e2239
Merge 0743fbd6e9 into b83ca24eb7 2024-11-10 09:28:09 +05:30
sepro
b83ca24eb7
[core] Catch broken Cryptodome installations (#11486)
Authored by: seproDev
2024-11-10 00:53:49 +01:00
bashonly
240a7d43c8
[build] Pin websockets version to >=13.0,<14 (#11488)
websockets 14.0 causes CI test failures (a lot more of them)

Authored by: bashonly
2024-11-09 23:46:47 +00:00
bashonly
f13df591d4
[build] Enable attestations for trusted publishing (#11420)
Reverts 428ffb75aa

Authored by: bashonly
2024-11-09 23:26:02 +00:00
Mozi
0743fbd6e9 [ie/espn] Add subtitles extraction; fix clip regex in articles
No video is extractable from any "only_matching" url in "ESPNArticleIE".
2024-09-05 16:50:54 +00:00
7 changed files with 77 additions and 19 deletions

View File

@ -504,7 +504,8 @@ jobs:
- windows32 - windows32
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/download-artifact@v4 - name: Download artifacts
uses: actions/download-artifact@v4
with: with:
path: artifact path: artifact
pattern: build-bin-* pattern: build-bin-*

View File

@ -28,3 +28,20 @@ jobs:
actions: write # For cleaning up cache actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing id-token: write # mandatory for trusted publishing
secrets: inherit secrets: inherit
publish_pypi:
needs: [release]
if: vars.MASTER_PYPI_PROJECT != ''
runs-on: ubuntu-latest
permissions:
id-token: write # mandatory for trusted publishing
steps:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist
name: build-pypi
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true

View File

@ -41,3 +41,20 @@ jobs:
actions: write # For cleaning up cache actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing id-token: write # mandatory for trusted publishing
secrets: inherit secrets: inherit
publish_pypi:
needs: [release]
if: vars.NIGHTLY_PYPI_PROJECT != ''
runs-on: ubuntu-latest
permissions:
id-token: write # mandatory for trusted publishing
steps:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist
name: build-pypi
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true

View File

@ -2,10 +2,6 @@ name: Release
on: on:
workflow_call: workflow_call:
inputs: inputs:
prerelease:
required: false
default: true
type: boolean
source: source:
required: false required: false
default: '' default: ''
@ -18,6 +14,10 @@ on:
required: false required: false
default: '' default: ''
type: string type: string
prerelease:
required: false
default: true
type: boolean
workflow_dispatch: workflow_dispatch:
inputs: inputs:
source: source:
@ -278,11 +278,20 @@ jobs:
make clean-cache make clean-cache
python -m build --no-isolation . python -m build --no-isolation .
- name: Upload artifacts
if: github.event_name != 'workflow_dispatch'
uses: actions/upload-artifact@v4
with:
name: build-pypi
path: |
dist/*
compression-level: 0
- name: Publish to PyPI - name: Publish to PyPI
if: github.event_name == 'workflow_dispatch'
uses: pypa/gh-action-pypi-publish@release/v1 uses: pypa/gh-action-pypi-publish@release/v1
with: with:
verbose: true verbose: true
attestations: false # Currently doesn't work w/ reusable workflows (breaks nightly)
publish: publish:
needs: [prepare, build] needs: [prepare, build]

View File

@ -52,7 +52,7 @@ default = [
"pycryptodomex", "pycryptodomex",
"requests>=2.32.2,<3", "requests>=2.32.2,<3",
"urllib3>=1.26.17,<3", "urllib3>=1.26.17,<3",
"websockets>=13.0", "websockets>=13.0,<14",
] ]
curl-cffi = [ curl-cffi = [
"curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'", "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",

View File

@ -24,7 +24,7 @@ try:
from Crypto.Cipher import AES, PKCS1_OAEP, Blowfish, PKCS1_v1_5 # noqa: F401 from Crypto.Cipher import AES, PKCS1_OAEP, Blowfish, PKCS1_v1_5 # noqa: F401
from Crypto.Hash import CMAC, SHA1 # noqa: F401 from Crypto.Hash import CMAC, SHA1 # noqa: F401
from Crypto.PublicKey import RSA # noqa: F401 from Crypto.PublicKey import RSA # noqa: F401
except ImportError: except (ImportError, OSError):
__version__ = f'broken {__version__}'.strip() __version__ = f'broken {__version__}'.strip()

View File

@ -113,6 +113,7 @@ class ESPNIE(OnceIE):
format_urls = set() format_urls = set()
formats = [] formats = []
subtitles = {}
def traverse_source(source, base_source_id=None): def traverse_source(source, base_source_id=None):
for src_id, src_item in source.items(): for src_id, src_item in source.items():
@ -140,9 +141,11 @@ class ESPNIE(OnceIE):
formats.extend(self._extract_f4m_formats( formats.extend(self._extract_f4m_formats(
source_url, video_id, f4m_id=source_id, fatal=False)) source_url, video_id, f4m_id=source_id, fatal=False))
elif ext == 'm3u8': elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats( m3u8_frmts, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
source_url, video_id, 'mp4', entry_protocol='m3u8_native', source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=source_id, fatal=False)) m3u8_id=source_id, fatal=False)
formats.extend(m3u8_frmts)
self._merge_subtitles(m3u8_subs, target=subtitles)
else: else:
f = { f = {
'url': source_url, 'url': source_url,
@ -176,12 +179,26 @@ class ESPNIE(OnceIE):
'timestamp': timestamp, 'timestamp': timestamp,
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
'subtitles': subtitles,
} }
class ESPNArticleIE(InfoExtractor): class ESPNArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)' _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.espn.com/college-football/game/_/gameId/401520427',
'info_dict': {
'id': '401520427',
'title': 'Alabama 27-24 Auburn (Nov 25, 2023) Final Score - ESPN',
'description': 'Game summary of the Alabama Crimson Tide vs. Auburn Tigers NCAAF game, final score 27-24, from November 25, 2023 on ESPN.',
'entries': [{
'id': '38979520',
}, {
'id': '38981707',
}],
},
'playlist_count': 2,
}, {
'url': 'http://espn.go.com/nba/recap?gameId=400793786', 'url': 'http://espn.go.com/nba/recap?gameId=400793786',
'only_matching': True, 'only_matching': True,
}, { }, {
@ -200,16 +217,13 @@ class ESPNArticleIE(InfoExtractor):
return False if (ESPNIE.suitable(url) or WatchESPNIE.suitable(url)) else super().suitable(url) return False if (ESPNIE.suitable(url) or WatchESPNIE.suitable(url)) else super().suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
webpage = self._download_webpage(url, video_id) return self.playlist_result(traverse_obj(re.finditer(
r'class=(["\']).*?Media.*?\1[^>]+data-videoid=["\'](?P<id>\d+)', webpage), (..., 'id', {
video_id = self._search_regex( lambda x: self.url_result(f'http://espn.go.com/video/clip?id={x}', ESPNIE.ie_key(), x),
r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)', })), playlist_id, self._html_extract_title(webpage), self._html_search_meta('description', webpage))
webpage, 'video id', group='id')
return self.url_result(
f'http://espn.go.com/video/clip?id={video_id}', ESPNIE.ie_key())
class FiveThirtyEightIE(InfoExtractor): class FiveThirtyEightIE(InfoExtractor):