mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-09 12:42:28 +01:00
86e5f3ed2e
Using https://github.com/asottile/pyupgrade 1. `__future__` imports and `coding: utf-8` were removed 2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format` 3. f-strings were cherry-picked from `pyupgrade --py36-plus` Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
44 lines
1.8 KiB
Python
44 lines
1.8 KiB
Python
from .common import InfoExtractor
|
||
|
||
|
||
class GazetaIE(InfoExtractor):
|
||
_VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:main/)*(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
|
||
_TESTS = [{
|
||
'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',
|
||
'md5': 'd49c9bdc6e5a7888f27475dc215ee789',
|
||
'info_dict': {
|
||
'id': '205566',
|
||
'ext': 'mp4',
|
||
'title': '«70–80 процентов гражданских в Донецке на грани голода»',
|
||
'description': 'md5:38617526050bd17b234728e7f9620a71',
|
||
'thumbnail': r're:^https?://.*\.jpg',
|
||
},
|
||
'skip': 'video not found',
|
||
}, {
|
||
'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml',
|
||
'only_matching': True,
|
||
}, {
|
||
'url': 'http://www.gazeta.ru/video/main/main/2015/06/22/platit_ili_ne_platit_po_isku_yukosa.shtml',
|
||
'md5': '37f19f78355eb2f4256ee1688359f24c',
|
||
'info_dict': {
|
||
'id': '252048',
|
||
'ext': 'mp4',
|
||
'title': '"Если по иску ЮКОСа придется платить, это будет большой удар по бюджету"',
|
||
},
|
||
'add_ie': ['EaglePlatform'],
|
||
}]
|
||
|
||
def _real_extract(self, url):
|
||
mobj = self._match_valid_url(url)
|
||
|
||
display_id = mobj.group('id')
|
||
embed_url = '%s?p=embed' % mobj.group('url')
|
||
embed_page = self._download_webpage(
|
||
embed_url, display_id, 'Downloading embed page')
|
||
|
||
video_id = self._search_regex(
|
||
r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id')
|
||
|
||
return self.url_result(
|
||
'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform')
|