]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/breakcom.py
Merge tag 'upstream/2014.11.21'
[youtubedl] / youtube_dl / extractor / breakcom.py
1 from __future__ import unicode_literals
2
3 import re
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import (
8 int_or_none,
9 parse_age_limit,
10 )
11
12
13 class BreakIE(InfoExtractor):
14 _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
15 _TESTS = [{
16 'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
17 'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
18 'info_dict': {
19 'id': '2468056',
20 'ext': 'mp4',
21 'title': 'When Girls Act Like D-Bags',
22 }
23 }, {
24 'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
25 'only_matching': True,
26 }]
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30 webpage = self._download_webpage(
31 'http://www.break.com/embed/%s' % video_id, video_id)
32 info = json.loads(self._search_regex(
33 r'var embedVars = ({.*})\s*?</script>',
34 webpage, 'info json', flags=re.DOTALL))
35
36 youtube_id = info.get('youtubeId')
37 if youtube_id:
38 return self.url_result(youtube_id, 'Youtube')
39
40 formats = [{
41 'url': media['uri'] + '?' + info['AuthToken'],
42 'tbr': media['bitRate'],
43 'width': media['width'],
44 'height': media['height'],
45 } for media in info['media']]
46
47 if not formats:
48 formats.append({
49 'url': info['videoUri']
50 })
51
52 self._sort_formats(formats)
53
54 duration = int_or_none(info.get('videoLengthInSeconds'))
55 age_limit = parse_age_limit(info.get('audienceRating'))
56
57 return {
58 'id': video_id,
59 'title': info['contentName'],
60 'thumbnail': info['thumbUri'],
61 'duration': duration,
62 'age_limit': age_limit,
63 'formats': formats,
64 }