mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 08:58:30 +00:00
Code Issues Projects Releases Wiki Activity

Merge e0c568675f into eff0759705

Browse Source
This commit is contained in:
garret1317 2025-06-26 06:44:10 -03:00 committed by GitHub
commit 809b1ba359
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 69 additions and 68 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

137
yt_dlp/extractor/tbsjp.py
View File

@ -1,104 +1,105 @@
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from .streaks import StreaksBaseIE
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
str_or_none,
unified_timestamp,
urljoin,
url_or_none,
)
from ..utils.traversal import find_element, traverse_obj
from ..utils.traversal import traverse_obj
class TBSJPEpisodeIE(InfoExtractor):
class TBSJPBaseIE(StreaksBaseIE):
def _window_app(self, webpage, name, item_id, fatal=True):
return self._search_json(r'window\.app\s*=', webpage, f'{name} info', item_id, fatal=fatal, default={})
class TBSJPEpisodeIE(TBSJPBaseIE):
_VALID_URL = r'https?://cu\.tbs\.co\.jp/episode/(?P<id>[\d_]+)'
_GEO_BYPASS = False
_TESTS = [{
'url': 'https://cu.tbs.co.jp/episode/23613_2044134_1000049010',
'skip': 'streams geo-restricted, Japan only. Also, will likely expire eventually',
'url': 'https://cu.tbs.co.jp/episode/14694_2090934_1000117476',
'skip': 'geo-blocked to japan + 7-day expiry',
'info_dict': {
'title': 'VIVANT 第三話 誤送金完結へ!絶体絶命の反撃開始',
'id': '23613_2044134_1000049010',
'title': '次世代リアクション王発掘トーナメント',
'id': '14694_2090934_1000117476',
'ext': 'mp4',
'upload_date': '20230728',
'duration': 3517,
'release_timestamp': 1691118230,
'episode': '第三話 誤送金完結へ!絶体絶命の反撃開始',
'release_date': '20230804',
'categories': 'count:11',
'episode_number': 3,
'timestamp': 1690522538,
'description': 'md5:2b796341af1ef772034133174ba4a895',
'series': 'VIVANT',
'display_id': 'ref:14694_2090934_1000117476',
'description': 'md5:0f57448221519627dce7802432729159',
'uploader': 'TBS',
'uploader_id': 'tbs',
'duration': 2761,
'thumbnail': 'md5:76882f287053dfec6a5adffad70ff1e3',
'categories': ['エンタメ', '水曜日のダウンタウン', 'ダウンタウン', '浜田雅功', '松本人志', '水ダウ', 'バラエティ', '動画'],
'cast': ['浜田\u3000雅功', '千原\u3000ジュニア', 'くっきー！（野性爆弾）', '田中\u3000卓志', '菊地\u3000亜美', '池田\u3000美優', '服部\u3000潤'],
'genres': ['variety'],
'series': '水曜日のダウンタウン',
'series_id': '14694',
'episode': '次世代リアクション王発掘トーナメント',
'episode_number': 335,
'episode_id': '14694_2090934_1000117476',
'timestamp': 1749547434,
'upload_date': '20250610',
'release_timestamp': 1749646802,
'release_date': '20250611',
'modified_timestamp': 1749647146,
'modified_date': '20250611',
'live_status': 'not_live',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
meta = self._search_json(r'window\.app\s*=', webpage, 'episode info', video_id, fatal=False)
meta = self._window_app(webpage, 'episode', video_id, fatal=False)
episode = traverse_obj(meta, ('falcorCache', 'catalog', 'episode', video_id, 'value'))
tf_path = self._search_regex(
r'<script[^>]+src=["\'](/assets/tf\.[^"\']+\.js)["\']', webpage, 'stream API config')
tf_js = self._download_webpage(urljoin(url, tf_path), video_id, note='Downloading stream API config')
video_url = self._search_regex(r'videoPlaybackUrl:\s*[\'"]([^\'"]+)[\'"]', tf_js, 'stream API url')
api_key = self._search_regex(r'api_key:\s*[\'"]([^\'"]+)[\'"]', tf_js, 'stream API key')
try:
source_meta = self._download_json(f'{video_url}ref:{video_id}', video_id,
headers={'X-Streaks-Api-Key': api_key},
note='Downloading stream metadata')
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
self.raise_geo_restricted(countries=['JP'])
raise
formats, subtitles = [], {}
for src in traverse_obj(source_meta, ('sources', ..., 'src')):
fmts, subs = self._extract_m3u8_formats_and_subtitles(src, video_id, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'title': traverse_obj(webpage, ({find_element(tag='h3')}, {clean_html})),
'id': video_id,
**self._extract_from_streaks_api(
'tbs', f'ref:{video_id}', headers={'Referer': 'https://cu.tbs.co.jp/'}),
**traverse_obj(episode, {
'categories': ('keywords', {list}),
'id': ('content_id', {str}),
'description': ('description', 0, 'value'),
'timestamp': ('created_at', {unified_timestamp}),
'release_timestamp': ('pub_date', {unified_timestamp}),
'title': ('title', ..., 'value', {str}, any),
'cast': ('credit', ..., 'name', ..., 'value', {clean_html}, any, {lambda x: x.split(',')}, ..., {str.strip}, filter, all, filter),
'categories': ('keywords', ..., {str}, filter, all, filter),
'description': ('description', ..., 'value', {clean_html}, any),
'duration': ('tv_episode_info', 'duration', {int_or_none}),
'episode': ('title', lambda _, v: not v.get('is_phonetic'), 'value', {str}, any),
'episode_id': ('content_id', {str}),
'episode_number': ('tv_episode_info', 'episode_number', {int_or_none}),
'episode': ('title', lambda _, v: not v.get('is_phonetic'), 'value'),
'series': ('custom_data', 'program_name'),
}, get_all=False),
'formats': formats,
'subtitles': subtitles,
'genres': ('genre', ..., {str}, filter, all, filter),
'release_timestamp': ('pub_date', {unified_timestamp}),
'series': ('custom_data', 'program_name', {str}),
'tags': ('tags', ..., {str}, filter, all, filter),
'thumbnail': ('artwork', ..., 'url', {url_or_none}, any),
'timestamp': ('created_at', {unified_timestamp}),
'uploader': ('tv_show_info', 'networks', ..., {str}, any),
}),
**traverse_obj(episode, ('tv_episode_info', {
'duration': ('duration', {int_or_none}),
'episode_number': ('episode_number', {int_or_none}),
'series_id': ('show_content_id', {str}),
})),
'id': video_id,
}
class TBSJPProgramIE(InfoExtractor):
class TBSJPProgramIE(TBSJPBaseIE):
_VALID_URL = r'https?://cu\.tbs\.co\.jp/program/(?P<id>\d+)'
_TESTS = [{
'url': 'https://cu.tbs.co.jp/program/23601',
'playlist_mincount': 4,
'url': 'https://cu.tbs.co.jp/program/14694',
'playlist_mincount': 1,
'info_dict': {
'id': '23601',
'categories': ['エンタメ', 'ミライカプセル', '会社', '働く', 'バラエティ', '動画'],
'description': '幼少期の夢は大人になって、どう成長したのだろうか？\nそしてその夢は今後、どのように広がっていくのか？\nいま話題の会社で働く人の「夢の成長」を描く',
'series': 'ミライカプセル　-I have a dream-',
'title': 'ミライカプセル　-I have a dream-',
'id': '14694',
'title': '水曜日のダウンタウン',
'description': 'md5:cf1d46c76c2755d7f87512498718b837',
'categories': ['エンタメ', '水曜日のダウンタウン', 'ダウンタウン', '浜田雅功', '松本人志', '水ダウ', 'バラエティ', '動画'],
'series': '水曜日のダウンタウン',
},
}]
def _real_extract(self, url):
programme_id = self._match_id(url)
webpage = self._download_webpage(url, programme_id)
meta = self._search_json(r'window\.app\s*=', webpage, 'programme info', programme_id)
meta = self._window_app(webpage, 'programme', programme_id)
programme = traverse_obj(meta, ('falcorCache', 'catalog', 'program', programme_id, 'false', 'value'))
return {
@ -116,7 +117,7 @@ def _real_extract(self, url):
}
class TBSJPPlaylistIE(InfoExtractor):
class TBSJPPlaylistIE(TBSJPBaseIE):
_VALID_URL = r'https?://cu\.tbs\.co\.jp/playlist/(?P<id>[\da-f]+)'
_TESTS = [{
'url': 'https://cu.tbs.co.jp/playlist/184f9970e7ba48e4915f1b252c55015e',
@ -129,8 +130,8 @@ class TBSJPPlaylistIE(InfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
page = self._download_webpage(url, playlist_id)
meta = self._search_json(r'window\.app\s*=', page, 'playlist info', playlist_id)
webpage = self._download_webpage(url, playlist_id)
meta = self._window_app(webpage, 'playlist', playlist_id)
playlist = traverse_obj(meta, ('falcorCache', 'playList', playlist_id))
def entries():