youtube_dl/extractor/seeker.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class SeekerIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P<display_id>.*)-(?P<article_id>\d+)\.html'
  11     _TESTS = [{
  12         # player.loadRevision3Item
  13         'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html',
  14         'md5': '30c1dc4030cc715cf05b423d0947ac18',
  15         'info_dict': {
  16             'id': '76243',
  17             'ext': 'webm',
  18             'title': 'Should Trump Be Required To Release His Tax Returns?',
  19             'description': 'Donald Trump has been secretive about his "big," "beautiful" tax returns. So what can we learn if he decides to release them?',
  20             'uploader': 'Seeker Daily',
  21             'uploader_id': 'seekerdaily',
  22         }
  23     }, {
  24         'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html',
  25         'playlist': [
  26             {
  27                 'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
  28                 'info_dict': {
  29                     'id': '67558',
  30                     'ext': 'mp4',
  31                     'title': 'The Pros & Cons Of Zoos',
  32                     'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
  33                     'uploader': 'DNews',
  34                     'uploader_id': 'dnews',
  35                 },
  36             }
  37         ],
  38         'info_dict': {
  39             'id': '1834116536',
  40             'title': 'After Gorilla Killing, Changes Ahead for Zoos',
  41             'description': 'The largest association of zoos and others are hoping to learn from recent incidents that led to the shooting deaths of a gorilla and two lions.',
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         display_id, article_id = re.match(self._VALID_URL, url).groups()
  47         webpage = self._download_webpage(url, display_id)
  48         mobj = re.search(r"player\.loadRevision3Item\('([^']+)'\s*,\s*(\d+)\);", webpage)
  49         if mobj:
  50             playlist_type, playlist_id = mobj.groups()
  51             return self.url_result(
  52                 'revision3:%s:%s' % (playlist_type, playlist_id), 'Revision3Embed', playlist_id)
  53         else:
  54             entries = [self.url_result('revision3:video_id:%s' % video_id, 'Revision3Embed', video_id) for video_id in re.findall(
  55                 r'<iframe[^>]+src=[\'"](?:https?:)?//api\.seekernetwork\.com/player/embed\?videoId=(\d+)', webpage)]
  56             return self.playlist_result(
  57                 entries, article_id, self._og_search_title(webpage), self._og_search_description(webpage))