Compare commits

...

7 Commits

Author SHA1 Message Date
Pierre
f5c6506de6
Merge b91bbb8084ca39edebcfbc472e15a43ce584fdd0 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 08:00:02 +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
Pierre Mesure
b91bbb8084 Edit tests 2024-03-29 14:24:37 +01:00
Pierre
3f45e4c128
Apply suggestions from code review
Co-authored-by: dirkf <fieldhouse@gmx.net>
2024-03-29 13:25:42 +01:00
Pierre Mesure
2594f3c2bd Add support for shows.acast.com 2024-03-17 07:49:19 +01:00
7 changed files with 30 additions and 19 deletions

View File

@ -48,9 +48,9 @@ class ACastIE(ACastBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?: (?:
(?:(?:embed|www)\.)?acast\.com/| (?:(?:(?P<embed>embed)|www|shows)\.)?acast\.com|
play\.acast\.com/s/ play\.acast\.com/s
) )/(?(embed)(?:$/)?)
(?P<channel>[^/]+)/(?P<id>[^/#?]+) (?P<channel>[^/]+)/(?P<id>[^/#?]+)
''' '''
_TESTS = [{ _TESTS = [{
@ -77,6 +77,9 @@ class ACastIE(ACastBaseIE):
}, { }, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9', 'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://shows.acast.com/611233d8767fdf0012f22cb6/episodes/611233e4988b6a001394b5cf',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -93,7 +96,7 @@ class ACastChannelIE(ACastBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?: (?:
(?:www\.)?acast\.com/| (?:(?:www|shows)\.)?acast\.com/|
play\.acast\.com/s/ play\.acast\.com/s/
) )
(?P<id>[^/#?]+) (?P<id>[^/#?]+)
@ -104,11 +107,22 @@ class ACastChannelIE(ACastBaseIE):
'id': '4efc5294-5385-4847-98bd-519799ce5786', 'id': '4efc5294-5385-4847-98bd-519799ce5786',
'title': 'Today in Focus', 'title': 'Today in Focus',
'description': 'md5:c09ce28c91002ce4ffce71d6504abaae', 'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
'skip': 'Error 404'
}, },
'playlist_mincount': 200, 'playlist_mincount': 200,
}, { }, {
'url': 'http://play.acast.com/s/ft-banking-weekly', 'url': 'http://play.acast.com/s/ft-banking-weekly',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://shows.acast.com/611233d8767fdf0012f22cb6',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/getthebeltpod',
'info_dict': {
'id': '4caac858-3cda-44e6-b684-50d88b909c18',
'title': 'Get The Belt'
},
'playlist_mincount': 138,
}] }]
@classmethod @classmethod

View File

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

View File

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

View File

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

View File

@ -35,15 +35,6 @@ from ..utils import (
class ITVBaseIE(InfoExtractor): 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): def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False: if errnote is False:
return False return False
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE): class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)' _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 = [{ _TESTS = [{
'note': 'Hub URLs redirect to ITVX', 'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012', 'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'ext': determine_ext(href, 'vtt'), '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 {}) video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle') title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title) info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE): class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)' _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 = [{ _TESTS = [{
'note': 'British Touring Car Championship', 'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch', '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'], ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
['arch', '', 'http://ussenate-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>.+)' _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{ _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', '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) raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
def _dump(self, obj, namespace): def _dump(self, obj, namespace):
if obj is JS_Undefined:
return 'undefined'
try: try:
return json.dumps(obj) return json.dumps(obj)
except TypeError: except TypeError: