]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cracked.py
74b880ffce9b0a8dbf7ab273063253a2743dbbdb
[youtubedl] / youtube_dl / extractor / cracked.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 parse_iso8601,
8 str_to_int,
9 )
10
11
12 class CrackedIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
14 _TEST = {
15 'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
16 'md5': '4b29a5eeec292cd5eca6388c7558db9e',
17 'info_dict': {
18 'id': '19006',
19 'ext': 'mp4',
20 'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
21 'description': 'md5:3b909e752661db86007d10e5ec2df769',
22 'timestamp': 1405659600,
23 'upload_date': '20140718',
24 }
25 }
26
27 def _real_extract(self, url):
28 mobj = re.match(self._VALID_URL, url)
29 video_id = mobj.group('id')
30
31 webpage = self._download_webpage(url, video_id)
32
33 video_url = self._html_search_regex(
34 [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
35
36 title = self._og_search_title(webpage)
37 description = self._og_search_description(webpage)
38
39 timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False)
40 if timestamp:
41 timestamp = parse_iso8601(timestamp[:-6])
42
43 view_count = str_to_int(self._html_search_regex(
44 r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False))
45 comment_count = str_to_int(self._html_search_regex(
46 r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False))
47
48 m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
49 if m:
50 width = int(m.group('width'))
51 height = int(m.group('height'))
52 else:
53 width = height = None
54
55 return {
56 'id': video_id,
57 'url':video_url,
58 'title': title,
59 'description': description,
60 'timestamp': timestamp,
61 'view_count': view_count,
62 'comment_count': comment_count,
63 'height': height,
64 'width': width,
65 }