is_html,
js_to_json,
KNOWN_EXTENSIONS,
+ merge_dicts,
mimetype2ext,
orderedSet,
sanitized_Request,
from .tnaflix import TNAFlixNetworkEmbedIE
from .drtuber import DrTuberIE
from .redtube import RedTubeIE
+from .tube8 import Tube8IE
from .vimeo import VimeoIE
from .dailymotion import DailymotionIE
from .dailymail import DailyMailIE
'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
}
},
+ # RSS feed with enclosures and unsupported link URLs
+ {
+ 'url': 'http://www.hellointernet.fm/podcast?format=rss',
+ 'info_dict': {
+ 'id': 'http://www.hellointernet.fm/podcast?format=rss',
+ 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
+ 'title': 'Hello Internet',
+ },
+ 'playlist_mincount': 100,
+ },
# SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
{
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
'title': '35871',
'timestamp': 1355743100,
'upload_date': '20121217',
- 'uploader_id': 'batchUser',
+ 'uploader_id': 'cplapp@learn360.com',
},
'add_ie': ['Kaltura'],
},
},
'add_ie': ['Kaltura'],
},
- # EaglePlatform embed (generic URL)
{
- 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
- # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
+ # meta twitter:player
+ 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
'info_dict': {
- 'id': '227304',
+ 'id': '0_01b42zps',
'ext': 'mp4',
- 'title': 'Навальный вышел на свободу',
- 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'duration': 87,
- 'view_count': int,
- 'age_limit': 0,
+ 'title': 'Main Twerk (Video)',
+ 'upload_date': '20171208',
+ 'uploader_id': 'sebastian.salinas@thechive.com',
+ 'timestamp': 1512713057,
},
'params': {
'skip_download': True,
},
+ 'add_ie': ['Kaltura'],
},
# referrer protected EaglePlatform embed
{
'params': {
'skip_download': True,
},
- }
+ },
+ {
+ 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
+ 'md5': 'b68d276de422ab07ee1d49388103f457',
+ 'info_dict': {
+ 'id': '83645793',
+ 'title': 'Lock up and get excited',
+ 'ext': 'mp4'
+ },
+ 'skip': 'TODO: fix nested playlists processing in tests',
+ },
# {
# # TODO: find another test
# # http://schema.org/VideoObject
entries = []
for it in doc.findall('./channel/item'):
- next_url = xpath_text(it, 'link', fatal=False)
+ next_url = None
+ enclosure_nodes = it.findall('./enclosure')
+ for e in enclosure_nodes:
+ next_url = e.attrib.get('url')
+ if next_url:
+ break
+
if not next_url:
- enclosure_nodes = it.findall('./enclosure')
- for e in enclosure_nodes:
- next_url = e.attrib.get('url')
- if next_url:
- break
+ next_url = xpath_text(it, 'link', fatal=False)
if not next_url:
continue
self._sort_formats(smil['formats'])
return smil
elif doc.tag == '{http://xspf.org/ns/0/}playlist':
- return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
+ return self.playlist_result(
+ self._parse_xspf(
+ doc, video_id, xspf_url=url,
+ xspf_base_url=compat_str(full_response.geturl())),
+ video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc,
if redtube_urls:
return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
+ # Look for embedded Tube8 player
+ tube8_urls = Tube8IE._extract_urls(webpage)
+ if tube8_urls:
+ return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
+
# Look for embedded Tvigle player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
return self.playlist_from_matches(
xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
- def merge_dicts(dict1, dict2):
- merged = {}
- for k, v in dict1.items():
- if v is not None:
- merged[k] = v
- for k, v in dict2.items():
- if v is None:
- continue
- if (k not in merged or
- (isinstance(v, compat_str) and v and
- isinstance(merged[k], compat_str) and
- not merged[k])):
- merged[k] = v
- return merged
+ sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
+ r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
+ webpage)]
+ if sharevideos_urls:
+ return self.playlist_from_matches(
+ sharevideos_urls, video_id, video_title)
# Look for HTML5 media
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')