youtube_dl/extractor/ustream.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urlparse,
   7     get_meta_content,
   8 )
   9
  10
  11 class UstreamIE(InfoExtractor):
  12     _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
  13     IE_NAME = u'ustream'
  14     _TEST = {
  15         u'url': u'http://www.ustream.tv/recorded/20274954',
  16         u'file': u'20274954.flv',
  17         u'md5': u'088f151799e8f572f84eb62f17d73e5c',
  18         u'info_dict': {
  19             u"uploader": u"Young Americans for Liberty",
  20             u"title": u"Young Americans for Liberty February 7, 2012 2:28 AM"
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         m = re.match(self._VALID_URL, url)
  26         video_id = m.group('videoID')
  27
  28         video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
  29         webpage = self._download_webpage(url, video_id)
  30
  31         self.report_extraction(video_id)
  32
  33         video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
  34             webpage, u'title')
  35
  36         uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
  37             webpage, u'uploader', fatal=False, flags=re.DOTALL)
  38
  39         thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
  40             webpage, u'thumbnail', fatal=False)
  41
  42         info = {
  43                 'id': video_id,
  44                 'url': video_url,
  45                 'ext': 'flv',
  46                 'title': video_title,
  47                 'uploader': uploader,
  48                 'thumbnail': thumbnail,
  49                }
  50         return info
  51
  52 class UstreamChannelIE(InfoExtractor):
  53     _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
  54     IE_NAME = u'ustream:channel'
  55
  56     def _real_extract(self, url):
  57         m = re.match(self._VALID_URL, url)
  58         slug = m.group('slug')
  59         webpage = self._download_webpage(url, slug)
  60         channel_id = get_meta_content('ustream:channel_id', webpage)
  61
  62         BASE = 'http://www.ustream.tv'
  63         next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
  64         video_ids = []
  65         while next_url:
  66             reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
  67             video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
  68             next_url = reply['nextUrl']
  69
  70         urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids]
  71         url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls]
  72         return self.playlist_result(url_entries, channel_id)