_ Git - youtube-dl/blob - youtube_dl/extractor/aol.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class AolIE(InfoExtractor):
   9     IE_NAME = 'on.aol.com'
  10     _VALID_URL = r'''(?x)
  11         (?:
  12             aol-video:|
  13             http://on\.aol\.com/
  14             (?:
  15                 video/.*-|
  16                 playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
  17             )
  18         )
  19         (?P<id>[0-9]+)
  20         (?:$|\?)
  21     '''
  22
  23     _TESTS = [{
  24         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  25         'md5': '18ef68f48740e86ae94b98da815eec42',
  26         'info_dict': {
  27             'id': '518167793',
  28             'ext': 'mp4',
  29             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  30         },
  31         'add_ie': ['FiveMin'],
  32     }, {
  33         'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
  34         'info_dict': {
  35             'id': '152147',
  36             'title': 'Brace Yourself - Today\'s Weirdest News',
  37         },
  38         'playlist_mincount': 10,
  39     }]
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         video_id = mobj.group('id')
  44         playlist_id = mobj.group('playlist_id')
  45         if not playlist_id or self._downloader.params.get('noplaylist'):
  46             return self.url_result('5min:%s' % video_id)
  47
  48         self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
  49
  50         webpage = self._download_webpage(url, playlist_id)
  51         title = self._html_search_regex(
  52             r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
  53         playlist_html = self._search_regex(
  54             r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
  55             'playlist HTML')
  56         entries = [{
  57             '_type': 'url',
  58             'url': 'aol-video:%s' % m.group('id'),
  59             'ie_key': 'Aol',
  60         } for m in re.finditer(
  61             r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
  62             playlist_html)]
  63
  64         return {
  65             '_type': 'playlist',
  66             'id': playlist_id,
  67             'display_id': mobj.group('playlist_display_id'),
  68             'title': title,
  69             'entries': entries,
  70         }