bet.py (2783B)
1 from __future__ import unicode_literals 2 3 from .mtv import MTVServicesInfoExtractor 4 from ..utils import unified_strdate 5 6 7 class BetIE(MTVServicesInfoExtractor): 8 _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' 9 _TESTS = [ 10 { 11 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html', 12 'info_dict': { 13 'id': '07e96bd3-8850-3051-b856-271b457f0ab8', 14 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism', 15 'ext': 'flv', 16 'title': 'A Conversation With President Obama', 17 'description': 'President Obama urges persistence in confronting racism and bias.', 18 'duration': 1534, 19 'upload_date': '20141208', 20 'thumbnail': r're:(?i)^https?://.*\.jpg$', 21 'subtitles': { 22 'en': 'mincount:2', 23 } 24 }, 25 'params': { 26 # rtmp download 27 'skip_download': True, 28 }, 29 }, 30 { 31 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', 32 'info_dict': { 33 'id': '9f516bf1-7543-39c4-8076-dd441b459ba9', 34 'display_id': 'justice-for-ferguson-a-community-reacts', 35 'ext': 'flv', 36 'title': 'Justice for Ferguson: A Community Reacts', 37 'description': 'A BET News special.', 38 'duration': 1696, 39 'upload_date': '20141125', 40 'thumbnail': r're:(?i)^https?://.*\.jpg$', 41 'subtitles': { 42 'en': 'mincount:2', 43 } 44 }, 45 'params': { 46 # rtmp download 47 'skip_download': True, 48 }, 49 } 50 ] 51 52 _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player" 53 54 def _get_feed_query(self, uri): 55 return { 56 'uuid': uri, 57 } 58 59 def _extract_mgid(self, webpage): 60 return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid') 61 62 def _real_extract(self, url): 63 display_id = self._match_id(url) 64 65 webpage = self._download_webpage(url, display_id) 66 mgid = self._extract_mgid(webpage) 67 videos_info = self._get_videos_info(mgid) 68 69 info_dict = videos_info['entries'][0] 70 71 upload_date = unified_strdate(self._html_search_meta('date', webpage)) 72 description = self._html_search_meta('description', webpage) 73 74 info_dict.update({ 75 'display_id': display_id, 76 'description': description, 77 'upload_date': upload_date, 78 }) 79 80 return info_dict