Compare commits

...

8 Commits

Author SHA1 Message Date
Aly Smith
b321e23116
Merge 819a5f30a6d977d7a3e2476e2b5db3f798d262e0 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 08:54:45 +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
alyssadev
819a5f30a6 [nbl] added support for ott urls 2022-04-01 10:32:17 +10:00
alyssadev
0ae2a8f320 [nbl] addressed comments, added more test cases 2022-04-01 10:11:08 +10:00
alyssadev
0d1bb1ce25 [nbl] re-enable display_id match for testing 2022-03-29 18:29:04 +10:00
alyssadev
2b8eac2d3a [nbl] Add new extractor 2022-03-29 18:17:31 +10:00
8 changed files with 112 additions and 15 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

@ -768,6 +768,7 @@ from .nbc import (
NBCSportsStreamIE,
NBCSportsVPlayerIE,
)
from .nbl import NBLIE
from .ndr import (
NDRIE,
NJoyIE,

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

@ -0,0 +1,99 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import unified_strdate
class NBLIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|ott\.)?nbl\.com\.au/(?:tv|en(?:-int)?)/(?P<section>game-replays|highlights|condensed-games|embed)?/?(?P<id>[0-9]+)/?(?P<display_id>.*)'
_TESTS = [
{
'url': 'https://nbl.com.au/tv/highlights/1310086/Perth-Wildcats-vs.-Sydney-Kings---Game-Highlights',
'md5': '684a1126879371c3137850b8474ae3c8',
'info_dict': {
'id': '1310086',
'ext': 'mp4',
'title': 'Perth Wildcats vs. Sydney Kings - Game Highlights',
'description': 'Watch the Game Highlights from Perth Wildcats vs. Sydney Kings, 03/26/2022',
'display_id': 'Perth-Wildcats-vs.-Sydney-Kings---Game-Highlights',
'upload_date': '20220326'
}
},
{
'url': 'https://nbl.com.au/tv/condensed-games/1310087/Perth-Wildcats-vs.-Sydney-Kings---Condensed-Game',
'md5': '1f9ac9ea04dc4024e50b27593860a782',
'info_dict': {
'id': '1310087',
'ext': 'mp4',
'title': 'Perth Wildcats vs. Sydney Kings - Condensed Game',
'description': 'Watch the Condensed Game from Perth Wildcats vs. Sydney Kings, 03/26/2022',
'display_id': 'Perth-Wildcats-vs.-Sydney-Kings---Condensed-Game',
'upload_date': '20220326'
}
},
{
'url': 'https://nbl.com.au/tv/game-replays/1303323/NBL22-Round-17-Replay---Perth-Wildcats-vs-Sydney-Kings',
'md5': '8505f02156f756e865a1aa80050eb768',
'info_dict': {
'id': '1303323',
'ext': 'mp4',
'title': 'NBL22 Round 17 Replay - Perth Wildcats vs Sydney Kings',
'display_id': 'NBL22-Round-17-Replay---Perth-Wildcats-vs-Sydney-Kings',
'upload_date': '20220326'
}
},
{
'url': 'https://nbl.com.au/tv/game-replays/1303323',
'md5': '8505f02156f756e865a1aa80050eb768',
'info_dict': {
'id': '1303323',
'ext': 'mp4',
'title': 'NBL22 Round 17 Replay - Perth Wildcats vs Sydney Kings',
'display_id': 'NBL22-Round-17-Replay---Perth-Wildcats-vs-Sydney-Kings',
'upload_date': '20220326'
}
},
{
'url': 'https://ott.nbl.com.au/en-int/embed/1303323',
'md5': '8505f02156f756e865a1aa80050eb768',
'info_dict': {
'id': '1303323',
'ext': 'mp4',
'title': 'NBL22 Round 17 Replay - Perth Wildcats vs Sydney Kings',
'display_id': 'NBL22-Round-17-Replay---Perth-Wildcats-vs-Sydney-Kings'
}
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
if mobj.groupdict().get("section") not in ['game-replays', 'highlights', 'condensed-games']:
webpage = self._download_webpage('https://ott.nbl.com.au/en-int/embed/' + video_id, video_id)
else:
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title\b[^>]*>\s*(.+?)\s*</title>', webpage, 'title')
stream_url = self._download_json(
'https://ott.nbl.com.au/api/v2/content/' + video_id + '/access/hls',
video_id,
data=b'',
headers={
'Referer': 'https://ott.nbl.com.au/en-int/embed/' + video_id,
'Origin': 'https://ott.nbl.com.au',
'Content-Length': '0'
}
)['data']['stream']
formats = self._extract_m3u8_formats(stream_url, video_id, ext='mp4')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage, default=None),
'display_id': mobj.groupdict().get('display_id') or title.replace(" ", "-"),
'upload_date': unified_strdate(self._og_search_property('video:release_date', webpage, 'upload_date', fatal=False, default=None)),
'formats': formats
}

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: