mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-22 16:31:41 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[ie/TVer] Support series URLs (#9507)
Some checks failed
Download Tests / Quick Download Tests (push) Waiting to run
Details
Download Tests / Full Download Tests (ubuntu-latest, 3.10) (push) Waiting to run
Details
Download Tests / Full Download Tests (ubuntu-latest, 3.11) (push) Waiting to run
Details
Download Tests / Full Download Tests (ubuntu-latest, 3.12) (push) Waiting to run
Details
Download Tests / Full Download Tests (ubuntu-latest, pypy-3.10) (push) Waiting to run
Details
Download Tests / Full Download Tests (ubuntu-latest, pypy-3.8) (push) Waiting to run
Details
Download Tests / Full Download Tests (windows-latest, 3.8) (push) Waiting to run
Details
Download Tests / Full Download Tests (windows-latest, pypy-3.9) (push) Waiting to run
Details
Quick Test / Core Test (push) Waiting to run
Details
Quick Test / Code check (push) Waiting to run
Details
Release (master) / release (push) Waiting to run
Details
CodeQL / Analyze (python) (push) Has been cancelled
Details

Browse Source 
Also improve thumbnails extraction

Authored by: vvto33, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
This commit is contained in:
vvto33 2024-10-11 06:42:34 +09:00 committed by GitHub
parent 5310fa87f6
commit ceaea731b6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 101 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

148
yt_dlp/extractor/tver.py
View File

@ -6,11 +6,12 @@
str_or_none,
strip_or_none,
traverse_obj,
update_url_query,
)
class TVerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video|olympic/paris2024/video)/)+(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature)/)+(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'skip': 'videos are only available for 7 days',
'url': 'https://tver.jp/episodes/ep83nf3w4p',
@ -21,80 +22,115 @@ class TVerIE(InfoExtractor):
'episode': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
'alt_title': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
'channel': 'テレビ朝日',
'id': 'ep83nf3w4p',
'ext': 'mp4',
'onair_label': '5月3日(火)放送分',
'ext_title': '家事ヤロウ!!! 売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！ テレビ朝日 5月3日(火)放送分',
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'https://tver.jp/olympic/paris2024/video/6359578055112/',
'info_dict': {
'id': '6359578055112',
'ext': 'mp4',
'title': '堀米雄斗 金メダルで五輪連覇！「みんなの応援が最後に乗れたカギ」',
'timestamp': 1722279928,
'upload_date': '20240729',
'tags': ['20240729', 'japanese', 'japanmedal', 'paris'],
'uploader_id': '4774017240001',
'thumbnail': r're:https?://[^/?#]+boltdns\.net/[^?#]+/1920x1080/match/image\.jpg',
'duration': 670.571,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://tver.jp/corner/f0103888',
'only_matching': True,
}, {
'url': 'https://tver.jp/lp/f0033031',
'only_matching': True,
}, {
'url': 'https://tver.jp/series/srtxft431v',
'info_dict': {
'id': 'srtxft431v',
'title': '名探偵コナン',
},
'playlist': [
{
'md5': '779ffd97493ed59b0a6277ea726b389e',
'info_dict': {
'id': 'ref:conan-1137-241005',
'ext': 'mp4',
'title': '名探偵コナン #1137「行列店、味変の秘密」',
'uploader_id': '5330942432001',
'tags': [],
'channel': '読売テレビ',
'series': '名探偵コナン',
'description': 'md5:601fccc1d2430d942a2c8068c4b33eb5',
'episode': '#1137「行列店、味変の秘密」',
'duration': 1469.077,
'timestamp': 1728030405,
'upload_date': '20241004',
'alt_title': '名探偵コナン #1137「行列店、味変の秘密」 読売テレビ 10月5日(土)放送分',
'thumbnail': r're:https://.+\.jpg',
},
}],
}, {
'url': 'https://tver.jp/series/sru35hwdd2',
'info_dict': {
'id': 'sru35hwdd2',
'title': '神回だけ見せます！',
},
'playlist_count': 11,
}, {
'url': 'https://tver.jp/series/srkq2shp9d',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
_PLATFORM_UID = None
_PLATFORM_TOKEN = None
_HEADERS = {'x-tver-platform-type': 'web'}
_PLATFORM_QUERY = {}
def _real_initialize(self):
create_response = self._download_json(
'https://platform-api.tver.jp/v2/api/platform_users/browser/create', None,
note='Creating session', data=b'device_type=pc', headers={
'Origin': 'https://s.tver.jp',
'Referer': 'https://s.tver.jp/',
'Content-Type': 'application/x-www-form-urlencoded',
session_info = self._download_json(
'https://platform-api.tver.jp/v2/api/platform_users/browser/create',
None, 'Creating session', data=b'device_type=pc')
self._PLATFORM_QUERY = traverse_obj(session_info, ('result', {
'platform_uid': 'platform_uid',
'platform_token': 'platform_token',
}))
def _call_platform_api(self, path, video_id, note=None, fatal=True, query=None):
return self._download_json(
f'https://platform-api.tver.jp/service/api/{path}', video_id, note,
fatal=fatal, headers=self._HEADERS, query={
**self._PLATFORM_QUERY,
**(query or {}),
})
self._PLATFORM_UID = traverse_obj(create_response, ('result', 'platform_uid'))
self._PLATFORM_TOKEN = traverse_obj(create_response, ('result', 'platform_token'))
def _yield_episode_ids_for_series(self, series_id):
seasons_info = self._download_json(
f'https://service-api.tver.jp/api/v1/callSeriesSeasons/{series_id}',
series_id, 'Downloading seasons info', headers=self._HEADERS)
for season_id in traverse_obj(
seasons_info, ('result', 'contents', lambda _, v: v['type'] == 'season', 'content', 'id', {str})):
episodes_info = self._call_platform_api(
f'v1/callSeasonEpisodes/{season_id}', series_id, f'Downloading season {season_id} episodes info')
yield from traverse_obj(episodes_info, (
'result', 'contents', lambda _, v: v['type'] == 'episode', 'content', 'id', {str}))
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
if video_type == 'olympic/paris2024/video':
# Player ID is taken from .content.brightcove.E200.pro.pc.account_id:
# https://tver.jp/olympic/paris2024/req/api/hook?q=https%3A%2F%2Folympic-assets.tver.jp%2Fweb-static%2Fjson%2Fconfig.json&d=
return self.url_result(smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % ('4774017240001', video_id),
{'geo_countries': ['JP']}), 'BrightcoveNew')
if video_type == 'series':
series_info = self._call_platform_api(
f'v2/callSeries/{video_id}', video_id, 'Downloading series info')
return self.playlist_from_matches(
self._yield_episode_ids_for_series(video_id), video_id,
traverse_obj(series_info, ('result', 'content', 'content', 'title', {str})),
ie=TVerIE, getter=lambda x: f'https://tver.jp/episodes/{x}')
elif video_type not in {'series', 'episodes'}:
if video_type != 'episodes':
webpage = self._download_webpage(url, video_id, note='Resolving to new URL')
video_id = self._match_id(self._search_regex(
(r'canonical"\s*href="(https?://tver\.jp/[^"]+)"', r'&link=(https?://tver\.jp/[^?&]+)[?&]'),
webpage, 'url regex'))
episode_info = self._download_json(
f'https://platform-api.tver.jp/service/api/v1/callEpisode/{video_id}?require_data=mylist,later[epefy106ur],good[epefy106ur],resume[epefy106ur]',
video_id, fatal=False,
query={
'platform_uid': self._PLATFORM_UID,
'platform_token': self._PLATFORM_TOKEN,
}, headers={
'x-tver-platform-type': 'web',
episode_info = self._call_platform_api(
f'v1/callEpisode/{video_id}', video_id, 'Downloading episode info', fatal=False, query={
'require_data': 'mylist,later[epefy106ur],good[epefy106ur],resume[epefy106ur]',
})
episode_content = traverse_obj(
episode_info, ('result', 'episode', 'content')) or {}
version = traverse_obj(episode_content, ('version', {str_or_none}), default='5')
video_info = self._download_json(
f'https://statics.tver.jp/content/episode/{video_id}.json', video_id,
query={
'v': str_or_none(episode_content.get('version')) or '5',
}, headers={
'Origin': 'https://tver.jp',
'Referer': 'https://tver.jp/',
})
f'https://statics.tver.jp/content/episode/{video_id}.json', video_id, 'Downloading video info',
query={'v': version}, headers={'Referer': 'https://tver.jp/'})
p_id = video_info['video']['accountID']
r_id = traverse_obj(video_info, ('video', ('videoRefID', 'videoID')), get_all=False)
if not r_id:
@ -110,6 +146,23 @@ def _real_extract(self, url):
provider = str_or_none(episode_content.get('productionProviderName'))
onair_label = str_or_none(episode_content.get('broadcastDateLabel'))
thumbnails = [
{
'id': quality,
'url': update_url_query(
f'https://statics.tver.jp/images/content/thumbnail/episode/{quality}/{video_id}.jpg',
{'v': version}),
'width': width,
'height': height,
}
for quality, width, height in [
('small', 480, 270),
('medium', 640, 360),
('large', 960, 540),
('xlarge', 1280, 720),
]
]
return {
'_type': 'url_transparent',
'title': title,
@ -119,6 +172,7 @@ def _real_extract(self, url):
'alt_title': join_nonempty(title, provider, onair_label, delim=' '),
'channel': provider,
'description': str_or_none(video_info.get('description')),
'thumbnails': thumbnails,
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id), {'geo_countries': ['JP']}),
'ie_key': 'BrightcoveNew',