mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'yt-dlp:master' into biliSearchPageIE
N/Ame
8 months ago
committed by
GitHub
commit
a9ac7d7f99
@ -0,0 +1,32 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import update_url, url_or_none
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class GraspopIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://vod\.graspop\.be/[a-z]{2}/(?P<id>\d+)/'
|
||||
_TESTS = [{
|
||||
'url': 'https://vod.graspop.be/fr/101556/thy-art-is-murder-concert/',
|
||||
'info_dict': {
|
||||
'id': '101556',
|
||||
'ext': 'mp4',
|
||||
'title': 'Thy Art Is Murder',
|
||||
'thumbnail': r're:https://cdn-mds\.pickx\.be/festivals/v3/global/original/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
metadata = self._download_json(
|
||||
f'https://tv.proximus.be/MWC/videocenter/festivals/{video_id}/stream', video_id)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': self._extract_m3u8_formats(
|
||||
# Downgrade manifest request to avoid incomplete certificate chain error
|
||||
update_url(metadata['source']['assetUri'], scheme='http'), video_id, 'mp4'),
|
||||
**traverse_obj(metadata, {
|
||||
'title': ('name', {str}),
|
||||
'thumbnail': ('source', 'poster', {url_or_none}),
|
||||
}),
|
||||
}
|
||||
@ -0,0 +1,114 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .vimeo import VimeoIE
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
get_element_html_by_id,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
str_or_none,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
urljoin,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class LaracastsBaseIE(InfoExtractor):
|
||||
def _get_prop_data(self, url, display_id):
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
return traverse_obj(
|
||||
get_element_html_by_id('app', webpage),
|
||||
({extract_attributes}, 'data-page', {json.loads}, 'props'))
|
||||
|
||||
def _parse_episode(self, episode):
|
||||
if not traverse_obj(episode, 'vimeoId'):
|
||||
self.raise_login_required('This video is only available for subscribers.')
|
||||
return self.url_result(
|
||||
VimeoIE._smuggle_referrer(
|
||||
f'https://player.vimeo.com/video/{episode["vimeoId"]}', 'https://laracasts.com/'),
|
||||
VimeoIE, url_transparent=True,
|
||||
**traverse_obj(episode, {
|
||||
'id': ('id', {int}, {str_or_none}),
|
||||
'webpage_url': ('path', {lambda x: urljoin('https://laracasts.com', x)}),
|
||||
'title': ('title', {clean_html}),
|
||||
'season_number': ('chapter', {int_or_none}),
|
||||
'episode_number': ('position', {int_or_none}),
|
||||
'description': ('body', {clean_html}),
|
||||
'thumbnail': ('largeThumbnail', {url_or_none}),
|
||||
'duration': ('length', {int_or_none}),
|
||||
'date': ('dateSegments', 'published', {unified_strdate}),
|
||||
}))
|
||||
|
||||
|
||||
class LaracastsIE(LaracastsBaseIE):
|
||||
IE_NAME = 'laracasts'
|
||||
_VALID_URL = r'https?://(?:www\.)?laracasts\.com/series/(?P<id>[\w-]+/episodes/\d+)/?(?:[?#]|$)'
|
||||
_TESTS = [{
|
||||
'url': 'https://laracasts.com/series/30-days-to-learn-laravel-11/episodes/1',
|
||||
'md5': 'c8f5e7b02ad0e438ef9280a08c8493dc',
|
||||
'info_dict': {
|
||||
'id': '922040563',
|
||||
'title': 'Hello, Laravel',
|
||||
'ext': 'mp4',
|
||||
'duration': 519,
|
||||
'date': '20240312',
|
||||
'thumbnail': 'https://laracasts.s3.amazonaws.com/videos/thumbnails/youtube/30-days-to-learn-laravel-11-1.png',
|
||||
'description': 'md5:ddd658bb241975871d236555657e1dd1',
|
||||
'season_number': 1,
|
||||
'season': 'Season 1',
|
||||
'episode_number': 1,
|
||||
'episode': 'Episode 1',
|
||||
'uploader': 'Laracasts',
|
||||
'uploader_id': 'user20182673',
|
||||
'uploader_url': 'https://vimeo.com/user20182673',
|
||||
},
|
||||
'expected_warnings': ['Failed to parse XML'], # TODO: Remove when vimeo extractor is fixed
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
return self._parse_episode(self._get_prop_data(url, display_id)['lesson'])
|
||||
|
||||
|
||||
class LaracastsPlaylistIE(LaracastsBaseIE):
|
||||
IE_NAME = 'laracasts:series'
|
||||
_VALID_URL = r'https?://(?:www\.)?laracasts\.com/series/(?P<id>[\w-]+)/?(?:[?#]|$)'
|
||||
_TESTS = [{
|
||||
'url': 'https://laracasts.com/series/30-days-to-learn-laravel-11',
|
||||
'info_dict': {
|
||||
'title': '30 Days to Learn Laravel',
|
||||
'id': '210',
|
||||
'thumbnail': 'https://laracasts.s3.amazonaws.com/series/thumbnails/social-cards/30-days-to-learn-laravel-11.png?v=2',
|
||||
'duration': 30600.0,
|
||||
'modified_date': '20240511',
|
||||
'description': 'md5:27c260a1668a450984e8f901579912dd',
|
||||
'categories': ['Frameworks'],
|
||||
'tags': ['Laravel'],
|
||||
'display_id': '30-days-to-learn-laravel-11',
|
||||
},
|
||||
'playlist_count': 30,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
series = self._get_prop_data(url, display_id)['series']
|
||||
|
||||
metadata = {
|
||||
'display_id': display_id,
|
||||
**traverse_obj(series, {
|
||||
'title': ('title', {str}),
|
||||
'id': ('id', {int}, {str_or_none}),
|
||||
'description': ('body', {clean_html}),
|
||||
'thumbnail': (('large_thumbnail', 'thumbnail'), {url_or_none}, any),
|
||||
'duration': ('runTime', {parse_duration}),
|
||||
'categories': ('taxonomy', 'name', {str}, {lambda x: x and [x]}),
|
||||
'tags': ('topics', ..., 'name', {str}),
|
||||
'modified_date': ('lastUpdated', {unified_strdate}),
|
||||
}),
|
||||
}
|
||||
|
||||
return self.playlist_result(traverse_obj(
|
||||
series, ('chapters', ..., 'episodes', lambda _, v: v['vimeoId'], {self._parse_episode})), **metadata)
|
||||
@ -1,188 +0,0 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
smuggle_url,
|
||||
unsmuggle_url,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
||||
class MicrosoftVirtualAcademyBaseIE(InfoExtractor):
|
||||
def _extract_base_url(self, course_id, display_id):
|
||||
return self._download_json(
|
||||
f'https://api-mlxprod.microsoft.com/services/products/anonymous/{course_id}',
|
||||
display_id, 'Downloading course base URL')
|
||||
|
||||
def _extract_chapter_and_title(self, title):
|
||||
if not title:
|
||||
return None, None
|
||||
m = re.search(r'(?P<chapter>\d+)\s*\|\s*(?P<title>.+)', title)
|
||||
return (int(m.group('chapter')), m.group('title')) if m else (None, title)
|
||||
|
||||
|
||||
class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
|
||||
IE_NAME = 'mva'
|
||||
IE_DESC = 'Microsoft Virtual Academy videos'
|
||||
_VALID_URL = rf'(?:{IE_NAME}:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/[^/?#&]+-)(?P<course_id>\d+)(?::|\?l=)(?P<id>[\da-zA-Z]+_\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788?l=gfVXISmEB_6804984382',
|
||||
'md5': '7826c44fc31678b12ad8db11f6b5abb9',
|
||||
'info_dict': {
|
||||
'id': 'gfVXISmEB_6804984382',
|
||||
'ext': 'mp4',
|
||||
'title': 'Course Introduction',
|
||||
'formats': 'mincount:3',
|
||||
'subtitles': {
|
||||
'en': [{
|
||||
'ext': 'ttml',
|
||||
}],
|
||||
},
|
||||
},
|
||||
}, {
|
||||
'url': 'mva:11788:gfVXISmEB_6804984382',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
|
||||
mobj = self._match_valid_url(url)
|
||||
course_id = mobj.group('course_id')
|
||||
video_id = mobj.group('id')
|
||||
|
||||
base_url = smuggled_data.get('base_url') or self._extract_base_url(course_id, video_id)
|
||||
|
||||
settings = self._download_xml(
|
||||
f'{base_url}/content/content_{video_id}/videosettings.xml?v=1',
|
||||
video_id, 'Downloading video settings XML')
|
||||
|
||||
_, title = self._extract_chapter_and_title(xpath_text(
|
||||
settings, './/Title', 'title', fatal=True))
|
||||
|
||||
formats = []
|
||||
|
||||
for sources in settings.findall('.//MediaSources'):
|
||||
sources_type = sources.get('videoType')
|
||||
for source in sources.findall('./MediaSource'):
|
||||
video_url = source.text
|
||||
if not video_url or not video_url.startswith('http'):
|
||||
continue
|
||||
if sources_type == 'smoothstreaming':
|
||||
formats.extend(self._extract_ism_formats(
|
||||
video_url, video_id, 'mss', fatal=False))
|
||||
continue
|
||||
video_mode = source.get('videoMode')
|
||||
height = int_or_none(self._search_regex(
|
||||
r'^(\d+)[pP]$', video_mode or '', 'height', default=None))
|
||||
codec = source.get('codec')
|
||||
acodec, vcodec = [None] * 2
|
||||
if codec:
|
||||
codecs = codec.split(',')
|
||||
if len(codecs) == 2:
|
||||
acodec, vcodec = codecs
|
||||
elif len(codecs) == 1:
|
||||
vcodec = codecs[0]
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': video_mode,
|
||||
'height': height,
|
||||
'acodec': acodec,
|
||||
'vcodec': vcodec,
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
for source in settings.findall('.//MarkerResourceSource'):
|
||||
subtitle_url = source.text
|
||||
if not subtitle_url:
|
||||
continue
|
||||
subtitles.setdefault('en', []).append({
|
||||
'url': f'{base_url}/{subtitle_url}',
|
||||
'ext': source.get('type'),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class MicrosoftVirtualAcademyCourseIE(MicrosoftVirtualAcademyBaseIE):
|
||||
IE_NAME = 'mva:course'
|
||||
IE_DESC = 'Microsoft Virtual Academy courses'
|
||||
_VALID_URL = rf'(?:{IE_NAME}:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/(?P<display_id>[^/?#&]+)-)(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
|
||||
'info_dict': {
|
||||
'id': '11788',
|
||||
'title': 'Microsoft Azure Fundamentals: Virtual Machines',
|
||||
},
|
||||
'playlist_count': 36,
|
||||
}, {
|
||||
# with emphasized chapters
|
||||
'url': 'https://mva.microsoft.com/en-US/training-courses/developing-windows-10-games-with-construct-2-16335',
|
||||
'info_dict': {
|
||||
'id': '16335',
|
||||
'title': 'Developing Windows 10 Games with Construct 2',
|
||||
},
|
||||
'playlist_count': 10,
|
||||
}, {
|
||||
'url': 'https://www.microsoftvirtualacademy.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'mva:course:11788',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if MicrosoftVirtualAcademyIE.suitable(url) else super().suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
course_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id')
|
||||
|
||||
base_url = self._extract_base_url(course_id, display_id)
|
||||
|
||||
manifest = self._download_json(
|
||||
f'{base_url}/imsmanifestlite.json',
|
||||
display_id, 'Downloading course manifest JSON')['manifest']
|
||||
|
||||
organization = manifest['organizations']['organization'][0]
|
||||
|
||||
entries = []
|
||||
for chapter in organization['item']:
|
||||
chapter_number, chapter_title = self._extract_chapter_and_title(chapter.get('title'))
|
||||
chapter_id = chapter.get('@identifier')
|
||||
for item in chapter.get('item', []):
|
||||
item_id = item.get('@identifier')
|
||||
if not item_id:
|
||||
continue
|
||||
metadata = item.get('resource', {}).get('metadata') or {}
|
||||
if metadata.get('learningresourcetype') != 'Video':
|
||||
continue
|
||||
_, title = self._extract_chapter_and_title(item.get('title'))
|
||||
duration = parse_duration(metadata.get('duration'))
|
||||
description = metadata.get('description')
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'url': smuggle_url(
|
||||
f'mva:{course_id}:{item_id}', {'base_url': base_url}),
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'chapter': chapter_title,
|
||||
'chapter_number': chapter_number,
|
||||
'chapter_id': chapter_id,
|
||||
})
|
||||
|
||||
title = organization.get('title') or manifest.get('metadata', {}).get('title')
|
||||
|
||||
return self.playlist_result(entries, course_id, title)
|
||||
Loading…
Reference in New Issue