]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/breakcom.py
4bcc897c95229ea0ee509fe53443d355309a66aa
[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 'info_dict': {
18 'id': '2468056',
19 'ext': 'mp4',
20 'title': 'When Girls Act Like D-Bags',
21 }
22 }, {
23 'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
24 'only_matching': True,
25 }]
26
27 def _real_extract(self, url):
28 video_id = self._match_id(url)
29 webpage = self._download_webpage(
30 'http://www.break.com/embed/%s' % video_id, video_id)
31 info = json.loads(self._search_regex(
32 r'var embedVars = ({.*})\s*?</script>',
33 webpage, 'info json', flags=re.DOTALL))
34
35 youtube_id = info.get('youtubeId')
36 if youtube_id:
37 return self.url_result(youtube_id, 'Youtube')
38
39 formats = [{
40 'url': media['uri'] + '?' + info['AuthToken'],
41 'tbr': media['bitRate'],
42 'width': media['width'],
43 'height': media['height'],
44 } for media in info['media']]
45
46 if not formats:
47 formats.append({
48 'url': info['videoUri']
49 })
50
51 self._sort_formats(formats)
52
53 duration = int_or_none(info.get('videoLengthInSeconds'))
54 age_limit = parse_age_limit(info.get('audienceRating'))
55
56 return {
57 'id': video_id,
58 'title': info['contentName'],
59 'thumbnail': info['thumbUri'],
60 'duration': duration,
61 'age_limit': age_limit,
62 'formats': formats,
63 }