]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/cracked.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
12 class CrackedIE(InfoExtractor
):
13 _VALID_URL
= r
'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
15 'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
16 'md5': '4b29a5eeec292cd5eca6388c7558db9e',
20 'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
21 'description': 'md5:3b909e752661db86007d10e5ec2df769',
22 'timestamp': 1405659600,
23 'upload_date': '20140718',
27 def _real_extract(self
, url
):
28 mobj
= re
.match(self
._VALID
_URL
, url
)
29 video_id
= mobj
.group('id')
31 webpage
= self
._download
_webpage
(url
, video_id
)
33 youtube_url
= self
._search
_regex
(
34 r
'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
35 webpage
, 'youtube url', default
=None)
37 return self
.url_result(youtube_url
)
39 video_url
= self
._html
_search
_regex
(
40 [r
'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r
'<video\s+src="([^"]+)"'],
43 title
= self
._search
_regex
(
44 [r
'property="?og:title"?\s+content="([^"]+)"', r
'class="?title"?>([^<]+)'],
47 description
= self
._search
_regex
(
48 r
'name="?(?:og:)?description"?\s+content="([^"]+)"',
49 webpage
, 'description', default
=None)
51 timestamp
= self
._html
_search
_regex
(
52 r
'"date"\s*:\s*"([^"]+)"', webpage
, 'upload date', fatal
=False)
54 timestamp
= parse_iso8601(timestamp
[:-6])
56 view_count
= str_to_int(self
._html
_search
_regex
(
57 r
'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
58 webpage
, 'view count', fatal
=False))
59 comment_count
= str_to_int(self
._html
_search
_regex
(
60 r
'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
61 webpage
, 'comment count', fatal
=False))
63 m
= re
.search(r
'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url
)
65 width
= int(m
.group('width'))
66 height
= int(m
.group('height'))
74 'description': description
,
75 'timestamp': timestamp
,
76 'view_count': view_count
,
77 'comment_count': comment_count
,