]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/bet.py
[bilibili] Mark as broken
[yt-dlp.git] / youtube_dl / extractor / bet.py
CommitLineData
b89a9386
S
1from __future__ import unicode_literals
2
c878e635
YCH
3from .mtv import MTVServicesInfoExtractor
4from ..utils import unified_strdate
5from ..compat import compat_urllib_parse_urlencode
b89a9386
S
6
7
c878e635 8class BetIE(MTVServicesInfoExtractor):
b89a9386
S
9 _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
10 _TESTS = [
11 {
12 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
13 'info_dict': {
c878e635 14 'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
b89a9386
S
15 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
16 'ext': 'flv',
249962ff 17 'title': 'A Conversation With President Obama',
c878e635 18 'description': 'President Obama urges persistence in confronting racism and bias.',
b89a9386 19 'duration': 1534,
b89a9386 20 'upload_date': '20141208',
b89a9386 21 'thumbnail': 're:(?i)^https?://.*\.jpg$',
c878e635
YCH
22 'subtitles': {
23 'en': 'mincount:2',
24 }
b89a9386
S
25 },
26 'params': {
27 # rtmp download
28 'skip_download': True,
29 },
30 },
31 {
32 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
33 'info_dict': {
c878e635 34 'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
b89a9386
S
35 'display_id': 'justice-for-ferguson-a-community-reacts',
36 'ext': 'flv',
37 'title': 'Justice for Ferguson: A Community Reacts',
38 'description': 'A BET News special.',
39 'duration': 1696,
b89a9386 40 'upload_date': '20141125',
b89a9386 41 'thumbnail': 're:(?i)^https?://.*\.jpg$',
c878e635
YCH
42 'subtitles': {
43 'en': 'mincount:2',
44 }
b89a9386
S
45 },
46 'params': {
47 # rtmp download
48 'skip_download': True,
49 },
50 }
51 ]
52
c878e635 53 _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
b89a9386 54
c878e635
YCH
55 def _get_feed_query(self, uri):
56 return compat_urllib_parse_urlencode({
57 'uuid': uri,
58 })
249962ff 59
c878e635
YCH
60 def _extract_mgid(self, webpage):
61 return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
b89a9386 62
c878e635
YCH
63 def _real_extract(self, url):
64 display_id = self._match_id(url)
b89a9386 65
c878e635
YCH
66 webpage = self._download_webpage(url, display_id)
67 mgid = self._extract_mgid(webpage)
68 videos_info = self._get_videos_info(mgid)
b89a9386 69
c878e635 70 info_dict = videos_info['entries'][0]
b89a9386 71
c878e635
YCH
72 upload_date = unified_strdate(self._html_search_meta('date', webpage))
73 description = self._html_search_meta('description', webpage)
b89a9386 74
c878e635 75 info_dict.update({
b89a9386 76 'display_id': display_id,
b89a9386 77 'description': description,
c878e635
YCH
78 'upload_date': upload_date,
79 })
80
81 return info_dict