Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/aol.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .fivemin import FiveMinIE
   7
   8
   9 class AolIE(InfoExtractor):
  10     IE_NAME = 'on.aol.com'
  11     _VALID_URL = r'''(?x)
  12         (?:
  13             aol-video:|
  14             http://on\.aol\.com/
  15             (?:
  16                 video/.*-|
  17                 playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
  18             )
  19         )
  20         (?P<id>[0-9]+)
  21         (?:$|\?)
  22     '''
  23
  24     _TESTS = [{
  25         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  26         'md5': '18ef68f48740e86ae94b98da815eec42',
  27         'info_dict': {
  28             'id': '518167793',
  29             'ext': 'mp4',
  30             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  31         },
  32         'add_ie': ['FiveMin'],
  33     }, {
  34         'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
  35         'info_dict': {
  36             'id': '152147',
  37             'title': 'Brace Yourself - Today\'s Weirdest News',
  38         },
  39         'playlist_mincount': 10,
  40     }]
  41
  42     def _real_extract(self, url):
  43         mobj = re.match(self._VALID_URL, url)
  44         video_id = mobj.group('id')
  45
  46         playlist_id = mobj.group('playlist_id')
  47         if playlist_id and not self._downloader.params.get('noplaylist'):
  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             }
  71
  72         return FiveMinIE._build_result(video_id)