Compare commits

...

9 Commits

Author SHA1 Message Date
Mevious
0bd3b18167
Merge 74c3ddbfef19f8d4aaf6ebb452f1b57c0127000f into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 10:24:54 +02:00
dirkf
3eb8d22ddb
[JSInterp] Temporary fix for #33102 2025-03-31 04:21:09 +01:00
dirkf
4e714f9df1 [Misc] Correct [_]IE_DESC/NAME in a few IEs
* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`
2025-03-26 12:47:19 +00:00
dirkf
c1ea7f5a24 [ITV] Mark ITVX not working
* update old shim
* correct [_]IE_DESC
2025-03-26 12:17:49 +00:00
Nasir
74c3ddbfef Prevent playlist from matching individual episode URL 2021-05-20 18:55:28 -07:00
Mevious
ebf8db6c43 Merge branch 'ytdl-org:master' into mevious/funimation-playlist 2021-05-07 09:23:04 -07:00
Nasir
e2a4c61afc Add UK site URL only_matching test 2021-05-04 14:45:02 -07:00
Nasir
bc85e70db0 Make lang code optional and add a only_matching test 2021-05-04 14:35:53 -07:00
Nasir
b91377b6d7 Added funimation show playlist extractor 2021-05-03 00:04:43 -07:00
8 changed files with 73 additions and 17 deletions

View File

@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
IE_DESC = 'CC视频'
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{

View File

@ -9,7 +9,7 @@ from ..utils import (
class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec'
IE_DESC = 'cloudy.ec'
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac',

View File

@ -422,6 +422,8 @@ class InfoExtractor(object):
_GEO_COUNTRIES = None
_GEO_IP_BLOCKS = None
_WORKING = True
# supply this in public subclasses: used in supported sites list, etc
# IE_DESC = 'short description of IE'
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""

View File

@ -434,7 +434,10 @@ from .frontendmasters import (
FrontendMastersCourseIE
)
from .fujitv import FujiTVFODPlus7IE
from .funimation import FunimationIE
from .funimation import (
FunimationIE,
FunimationShowPlaylistIE
)
from .funk import FunkIE
from .fusion import FusionIE
from .gaia import GaiaIE

View File

@ -11,7 +11,8 @@ from ..utils import (
int_or_none,
js_to_json,
ExtractorError,
urlencode_postdata
urlencode_postdata,
urljoin
)
@ -156,3 +157,58 @@ class FunimationIE(InfoExtractor):
'season_id': title_data.get('seriesId'),
'formats': formats,
}
class FunimationShowPlaylistIE(FunimationIE):
IE_NAME = 'funimation:playlist'
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:[^/]+/)?shows/(?P<id>[^/?#&]+)/?$'
_TESTS = [{
'url': 'https://www.funimation.com/shows/hacksign/',
'info_dict': {
'id': 90646,
'title': '.hack//SIGN'
},
'playlist_count': 28,
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/',
'only_matching': True,
}, {
# with lang code
'url': 'https://www.funimation.com/en/shows/hacksign/',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title_data = self._parse_json(self._search_regex(
r'TITLE_DATA\s*=\s*({[^}]+})',
webpage, 'title data', default=''),
display_id, js_to_json, fatal=False) or {}
items = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id=%s'
% title_data.get('id'), display_id).get('items')
vod_items = list(map(lambda k:
(k.get('mostRecentSvod') or k.get('mostRecentAvod'))
.get('item'), items))
vod_items = sorted(vod_items, key=lambda k: k.get('episodeOrder'))
entries = []
for vod_item in vod_items:
entries.append(
self.url_result(urljoin(url, vod_item.get('episodeSlug')),
'Funimation', vod_item.get('episodeId'),
vod_item.get('episodeSlug')))
return {
'_type': 'playlist',
'id': title_data.get('id'),
'title': title_data.get('title'),
'entries': entries,
}

View File

@ -35,15 +35,6 @@ from ..utils import (
class ITVBaseIE(InfoExtractor):
def _search_nextjs_data(self, webpage, video_id, **kw):
transform_source = kw.pop('transform_source', None)
fatal = kw.pop('fatal', True)
return self._parse_json(
self._search_regex(
r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
webpage, 'next.js data', group='js', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False:
return False
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
_IE_DESC = 'ITVX'
IE_DESC = 'ITVX'
_WORKING = False
_TESTS = [{
'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'ext': determine_ext(href, 'vtt'),
})
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
_IE_DESC = 'ITV articles: News, British Touring Car Championship'
IE_DESC = 'ITV articles: News, British Touring Car Championship'
_TESTS = [{
'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

View File

@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
['arch', '', 'http://ussenate-f.akamaihd.net/']
]
_IE_NAME = 'senate.gov'
IE_NAME = 'senate.gov'
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

View File

@ -686,6 +686,8 @@ class JSInterpreter(object):
raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
def _dump(self, obj, namespace):
if obj is JS_Undefined:
return 'undefined'
try:
return json.dumps(obj)
except TypeError: