]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tmz.py
debian/copyright: Fix lintian's dep5-copyright-license-name-not-unique.
[youtubedl] / youtube_dl / extractor / tmz.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5
6
7 class TMZIE(InfoExtractor):
8 _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/]+)/?'
9 _TEST = {
10 'url': 'http://www.tmz.com/videos/0_okj015ty/',
11 'md5': '791204e3bf790b1426cb2db0706184c0',
12 'info_dict': {
13 'id': '0_okj015ty',
14 'url': 'http://tmz.vo.llnwd.net/o28/2014-03/13/0_okj015ty_0_rt8ro3si_2.mp4',
15 'ext': 'mp4',
16 'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
17 'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie??? Or is she just showing off her amazing boobs?',
18 'thumbnail': r're:http://cdnbakmi\.kaltura\.com/.*thumbnail.*',
19 }
20 }
21
22 def _real_extract(self, url):
23 video_id = self._match_id(url)
24 webpage = self._download_webpage(url, video_id)
25
26 return {
27 'id': video_id,
28 'url': self._html_search_meta('VideoURL', webpage, fatal=True),
29 'title': self._og_search_title(webpage),
30 'description': self._og_search_description(webpage),
31 'thumbnail': self._html_search_meta('ThumbURL', webpage),
32 }
33
34
35 class TMZArticleIE(InfoExtractor):
36 _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
37 _TEST = {
38 'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
39 'md5': 'e482a414a38db73087450e3a6ce69d00',
40 'info_dict': {
41 'id': '0_6snoelag',
42 'ext': 'mp4',
43 'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
44 'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."',
45 }
46 }
47
48 def _real_extract(self, url):
49 video_id = self._match_id(url)
50
51 webpage = self._download_webpage(url, video_id)
52 embedded_video_info_str = self._html_search_regex(
53 r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
54
55 embedded_video_info = self._parse_json(
56 embedded_video_info_str, video_id,
57 transform_source=lambda s: s.replace('\\', ''))
58
59 return self.url_result(
60 'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])