1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
|
import re
import json
from .common import InfoExtractor
from ..utils import compat_urllib_parse_urlparse, compat_urlparse
class LivestreamIE(InfoExtractor):
_VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_TEST = {
u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
u'file': u'4719370.mp4',
u'md5': u'0d2186e3187d185a04b3cdd02b828836',
u'info_dict': {
u'title': u'Live from Webster Hall NYC',
u'upload_date': u'20121012',
}
}
def _extract_video_info(self, video_data):
video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
return {'id': video_data['id'],
'url': video_url,
'ext': 'mp4',
'title': video_data['caption'],
'thumbnail': video_data['thumbnail_url'],
'upload_date': video_data['updated_at'].replace('-','')[:8],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
event_name = mobj.group('event_name')
webpage = self._download_webpage(url, video_id or event_name)
if video_id is None:
# This is an event page:
api_url = self._search_regex(r'event_design_eventId: \'(.+?)\'',
webpage, 'api url')
info = json.loads(self._download_webpage(api_url, event_name,
u'Downloading event info'))
videos = [self._extract_video_info(video_data['data'])
for video_data in info['feed']['data'] if video_data['type'] == u'video']
return self.playlist_result(videos, info['id'], info['full_name'])
else:
og_video = self._og_search_video_url(webpage, name=u'player url')
query_str = compat_urllib_parse_urlparse(og_video).query
query = compat_urlparse.parse_qs(query_str)
api_url = query['play_url'][0].replace('.smil', '')
info = json.loads(self._download_webpage(api_url, video_id,
u'Downloading video info'))
return self._extract_video_info(info)
|
