]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/funnyordie.py
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',
27 'title': 'Please Use This Song (Jon Lajoie)',
28 'description': 'Please use this to sell something. www.jonlajoie.com',
29 'thumbnail': 're:^http:.*\.jpg$',
32 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
33 'only_matching': True,
36 def _real_extract(self
, url
):
37 mobj
= re
.match(self
._VALID
_URL
, url
)
39 video_id
= mobj
.group('id')
40 webpage
= self
._download
_webpage
(url
, video_id
)
42 links
= re
.findall(r
'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video
', webpage)
44 raise ExtractorError('No media links available
for %s' % video_id)
46 links.sort(key=lambda link: 1 if link[1] == 'mp4
' else 0)
48 bitrates = self._html_search_regex(r'<source src
="[^"]+/v
,((?
:\d
+,)+)\
.mp4\
.csmil
', webpage, 'video bitrates
')
49 bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
53 for bitrate in bitrates:
56 'url
': '%s%d.%s' % (link[0], bitrate, link[1]),
57 'format_id
': '%s-%d' % (link[1], bitrate),
62 for src, src_lang in re.findall(r'<track kind
="captions" src
="([^"]+)" srclang="([^
"]+)"', webpage):
63 subtitles[src_lang] = [{
64 'ext
': src.split('/')[-1],
65 'url
': 'http
://www
.funnyordie
.com
%s' % src,
68 post_json = self._search_regex(
69 r'fb_post\s
*=\s
*(\{.*?\}
);', webpage, 'post details
')
70 post = json.loads(post_json)
74 'title
': post['name
'],
75 'description
': post.get('description
'),
76 'thumbnail
': post.get('picture
'),
78 'subtitles
': subtitles,