depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 19:52:11 +00:00
Code Issues Releases Wiki Activity

[dbtv] fix extraction

Browse source
This commit is contained in:
Remita Amine 2019-07-12 23:26:46 +01:00
parent 57227618fe
commit 272355c172
1 changed files with 26 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
youtube_dl/extractor/dbtv.py
View file

@ -7,50 +7,51 @@ from .common import InfoExtractor
class DBTVIE(InfoExtractor): class DBTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?' _VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P<display_id>[^/]+))/)?(?P<id>[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})'
_TESTS = [{ _TESTS = [{
'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', 'url': 'https://www.dagbladet.no/video/PynxJnNWChE/',
'md5': '2e24f67936517b143a234b4cadf792ec', 'md5': 'b8f850ba1860adbda668d367f9b77699',
'info_dict': { 'info_dict': {
'id': '3649835190001', 'id': 'PynxJnNWChE',
'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0', 'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
'thumbnail': r're:https?://.*\.jpg', 'thumbnail': r're:https?://.*\.jpg',
'timestamp': 1404039863, 'upload_date': '20160916',
'upload_date': '20140629', 'duration': 69,
'duration': 69.544, 'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
'uploader_id': '1027729757001', 'uploader': 'Dagbladet',
}, },
'add_ie': ['BrightcoveNew'] 'add_ie': ['Youtube']
}, { }, {
'url': 'http://dbtv.no/3649835190001', 'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://www.dbtv.no/lazyplayer/4631135248001', 'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
'only_matching': True,
}, {
'url': 'http://dbtv.no/vice/5000634109001',
'only_matching': True,
}, {
'url': 'http://dbtv.no/filmtrailer/3359293614001',
'only_matching': True, 'only_matching': True,
}] }]
@staticmethod @staticmethod
def _extract_urls(webpage): def _extract_urls(webpage):
return [url for _, url in re.findall( return [url for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dbtv\.no/(?:lazy)?player/\d+.*?)\1', r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1',
webpage)] webpage)]
def _real_extract(self, url): def _real_extract(self, url):
video_id, display_id = re.match(self._VALID_URL, url).groups() display_id, video_id = re.match(self._VALID_URL, url).groups()
info = {
return {
'_type': 'url_transparent', '_type': 'url_transparent',
'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id,
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'ie_key': 'BrightcoveNew',
} }
if len(video_id) == 11:
info.update({
'url': video_id,
'ie_key': 'Youtube',
})
else:
info.update({
'url': 'jwplatform:' + video_id,
'ie_key': 'JWPlatform',
})
return info