thestar.py (1404B)
1 # coding: utf-8 2 from __future__ import unicode_literals 3 4 from .common import InfoExtractor 5 6 7 class TheStarIE(InfoExtractor): 8 _VALID_URL = r'https?://(?:www\.)?thestar\.com/(?:[^/]+/)*(?P<id>.+)\.html' 9 _TEST = { 10 'url': 'http://www.thestar.com/life/2016/02/01/mankind-why-this-woman-started-a-men-s-skincare-line.html', 11 'md5': '2c62dd4db2027e35579fefb97a8b6554', 12 'info_dict': { 13 'id': '4732393888001', 14 'ext': 'mp4', 15 'title': 'Mankind: Why this woman started a men\'s skin care line', 16 'description': 'Robert Cribb talks to Young Lee, the founder of Uncle Peter\'s MAN.', 17 'uploader_id': '794267642001', 18 'timestamp': 1454353482, 19 'upload_date': '20160201', 20 }, 21 'params': { 22 # m3u8 download 23 'skip_download': True, 24 } 25 } 26 BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/794267642001/default_default/index.html?videoId=%s' 27 28 def _real_extract(self, url): 29 display_id = self._match_id(url) 30 webpage = self._download_webpage(url, display_id) 31 brightcove_id = self._search_regex( 32 r'mainartBrightcoveVideoId["\']?\s*:\s*["\']?(\d+)', 33 webpage, 'brightcove id') 34 return self.url_result( 35 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 36 'BrightcoveNew', brightcove_id)