1 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import ExtractorError
10 class FunnyOrDieIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|articles|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
13 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
14 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
18 'title': 'Heart-Shaped Box: Literal Video Version',
19 'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338',
20 'thumbnail': 're:^http:.*\.jpg$',
23 'url': 'http://www.funnyordie.com/embed/e402820827',
24 'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad',
28 'title': 'Please Use This Song (Jon Lajoie)',
29 'description': 'Please use this to sell something. www.jonlajoie.com',
30 'thumbnail': 're:^http:.*\.jpg$',
33 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
34 'only_matching': True,
37 def _real_extract(self, url):
38 mobj = re.match(self._VALID_URL, url)
40 video_id = mobj.group('id')
41 webpage = self._download_webpage(url, video_id)
43 links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage)
45 raise ExtractorError('No media links available for %s' % video_id)
47 links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
49 bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
50 bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
55 for bitrate in bitrates:
58 'url': '%s%d.%s' % (link[0], bitrate, link[1]),
59 'format_id': '%s-%d' % (link[1], bitrate),
63 post_json = self._search_regex(
64 r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
65 post = json.loads(post_json)
69 'title': post['name'],
70 'description': post.get('description'),
71 'thumbnail': post.get('picture'),