Compare commits

...

11 Commits

Author SHA1 Message Date
changren-wcr
d2daa0b82d
Merge 0afddd0b9ae23e32d809e2f4edd5574e28d28487 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 08:43:27 +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
wangchangren
0afddd0b9a fix: refactor two extractors into one 2022-06-18 08:56:44 +08:00
wangchangren
9ff181a1ab fix: add new extractor for QingTing 2022-06-16 20:44:05 +08:00
changren-wcr
16e7b15f76
use youtube-dl match function instead of native python re
Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:14:08 +08:00
changren-wcr
9a421b4e7e
fix regular search pattern for title
_html_search_regex() has default fatal=True: add a default to fall back to _og_search_title()

allow line break in .*

Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:12:26 +08:00
changren-wcr
87706c5ec8
Use _search_regex() to get proper error reports in youtube-dl
Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:08:09 +08:00
changren-wcr
60783025df
remove capture of patterns that aren't used
Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:02:30 +08:00
wangchangren
174624aef8 [QingTing] Add new extractor 2022-06-12 10:58:44 +08:00
8 changed files with 66 additions and 15 deletions

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

@ -993,6 +993,7 @@ from .presstv import PressTVIE
from .prosiebensat1 import ProSiebenSat1IE from .prosiebensat1 import ProSiebenSat1IE
from .puls4 import Puls4IE from .puls4 import Puls4IE
from .pyvideo import PyvideoIE from .pyvideo import PyvideoIE
from .qingting import QingTingIE
from .qqmusic import ( from .qqmusic import (
QQMusicIE, QQMusicIE,
QQMusicSingerIE, QQMusicSingerIE,

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

@ -0,0 +1,53 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from youtube_dl import utils
class QingTingIE(InfoExtractor):
IE_NAME = 'QingTing'
_VALID_URL = r'''(?x)
(?:https?://)?(?:www\.)?
(?P<m>m\.)?(?:qingting\.fm|qtfm\.cn)/(?(m)v|)
channels/\d+/programs/(?P<id>\d+)'''
_TEST = {
'url': 'https://www.qingting.fm/channels/378005/programs/22257411/',
'md5': '47e6a94f4e621ed832c316fd1888fb3c',
'info_dict': {
'id': '22257411',
'ext': 'mp3',
'title': '用了十年才修改,谁在乎教科书?-睡前消息-蜻蜓FM听头条',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'(?s)<title\b[^>]*>(.*)</title>', webpage, 'title',
default=None) or self._og_search_title(webpage)
urlType = self._search_regex(
self._VALID_URL,
url, 'audio URL', group="m")
if urlType == 'm.':
url = self._search_regex(
r'''("|')audioUrl\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
webpage, 'audio URL', group="url")
test_url = utils.url_or_none(url)
if not test_url:
raise utils.ExtractorError('Invalid audio URL %s' % (url,))
return {
'id': video_id,
'title': title,
'ext': 'mp3',
'url': test_url,
}
else:
url = self._search_regex(
r'''("|')alternate\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
webpage, 'alternate URL', group="url")
test_url = utils.url_or_none(url)
if not test_url:
raise utils.ExtractorError('Invalid audio URL %s' % (url,))
return self.url_result(url=test_url, video_id=video_id, video_title=title)

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: