]> jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/bet.py
Fix `--windows-filenames` removing `/` from UNIX paths
[yt-dlp.git] / youtube_dlc / extractor / bet.py
1 from __future__ import unicode_literals
2
3 from .mtv import MTVServicesInfoExtractor
4 from ..utils import unified_strdate
5
6 # TODO Remove - Reason: Outdated Site
7
8
9 class BetIE(MTVServicesInfoExtractor):
10 _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
11 _TESTS = [
12 {
13 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
14 'info_dict': {
15 'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
16 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
17 'ext': 'flv',
18 'title': 'A Conversation With President Obama',
19 'description': 'President Obama urges persistence in confronting racism and bias.',
20 'duration': 1534,
21 'upload_date': '20141208',
22 'thumbnail': r're:(?i)^https?://.*\.jpg$',
23 'subtitles': {
24 'en': 'mincount:2',
25 }
26 },
27 'params': {
28 # rtmp download
29 'skip_download': True,
30 },
31 },
32 {
33 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
34 'info_dict': {
35 'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
36 'display_id': 'justice-for-ferguson-a-community-reacts',
37 'ext': 'flv',
38 'title': 'Justice for Ferguson: A Community Reacts',
39 'description': 'A BET News special.',
40 'duration': 1696,
41 'upload_date': '20141125',
42 'thumbnail': r're:(?i)^https?://.*\.jpg$',
43 'subtitles': {
44 'en': 'mincount:2',
45 }
46 },
47 'params': {
48 # rtmp download
49 'skip_download': True,
50 },
51 }
52 ]
53
54 _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
55
56 def _get_feed_query(self, uri):
57 return {
58 'uuid': uri,
59 }
60
61 def _extract_mgid(self, webpage):
62 return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
63
64 def _real_extract(self, url):
65 display_id = self._match_id(url)
66
67 webpage = self._download_webpage(url, display_id)
68 mgid = self._extract_mgid(webpage)
69 videos_info = self._get_videos_info(mgid)
70
71 info_dict = videos_info['entries'][0]
72
73 upload_date = unified_strdate(self._html_search_meta('date', webpage))
74 description = self._html_search_meta('description', webpage)
75
76 info_dict.update({
77 'display_id': display_id,
78 'description': description,
79 'upload_date': upload_date,
80 })
81
82 return info_dict