youtube_dl/extractor/aol.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class AolIE(InfoExtractor):
   7     IE_NAME = 'on.aol.com'
   8     _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
   9
  10     _TESTS = [{
  11         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  12         'md5': '18ef68f48740e86ae94b98da815eec42',
  13         'info_dict': {
  14             'id': '518167793',
  15             'ext': 'mp4',
  16             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  17         },
  18         'add_ie': ['FiveMin'],
  19     }]
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         return self.url_result('5min:%s' % video_id)
  24
  25
  26 class AolFeaturesIE(InfoExtractor):
  27     IE_NAME = 'features.aol.com'
  28     _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
  29
  30     _TESTS = [{
  31         'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
  32         'md5': '7db483bb0c09c85e241f84a34238cc75',
  33         'info_dict': {
  34             'id': '519507715',
  35             'ext': 'mp4',
  36             'title': 'What To Watch - February 17, 2016',
  37         },
  38         'add_ie': ['FiveMin'],
  39     }]
  40
  41     def _real_extract(self, url):
  42         display_id = self._match_id(url)
  43         webpage = self._download_webpage(url, display_id)
  44         return self.url_result(self._search_regex(
  45             r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
  46             webpage, '5min embed url'), 'FiveMin')