atttechchannel.py (1962B)
1 from __future__ import unicode_literals 2 3 from .common import InfoExtractor 4 from ..utils import unified_strdate 5 6 7 class ATTTechChannelIE(InfoExtractor): 8 _VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)' 9 _TEST = { 10 'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use', 11 'info_dict': { 12 'id': '11316', 13 'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use', 14 'ext': 'flv', 15 'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use', 16 'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.', 17 'thumbnail': r're:^https?://.*\.jpg$', 18 'upload_date': '20140127', 19 }, 20 'params': { 21 # rtmp download 22 'skip_download': True, 23 }, 24 } 25 26 def _real_extract(self, url): 27 display_id = self._match_id(url) 28 29 webpage = self._download_webpage(url, display_id) 30 31 video_url = self._search_regex( 32 r"url\s*:\s*'(rtmp://[^']+)'", 33 webpage, 'video URL') 34 35 video_id = self._search_regex( 36 r'mediaid\s*=\s*(\d+)', 37 webpage, 'video id', fatal=False) 38 39 title = self._og_search_title(webpage) 40 description = self._og_search_description(webpage) 41 thumbnail = self._og_search_thumbnail(webpage) 42 upload_date = unified_strdate(self._search_regex( 43 r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})', 44 webpage, 'upload date', fatal=False), False) 45 46 return { 47 'id': video_id, 48 'display_id': display_id, 49 'url': video_url, 50 'ext': 'flv', 51 'title': title, 52 'description': description, 53 'thumbnail': thumbnail, 54 'upload_date': upload_date, 55 }