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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class MiomioTvIE(InfoExtractor):
   8     IE_NAME = 'miomio.tv'
   9     _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'http://www.miomio.tv/watch/cc179734/',
  12         'md5': '48de02137d0739c15b440a224ad364b9',
  13         'info_dict': {
  14             'id': '179734',
  15             'title': u'\u624b\u7ed8\u52a8\u6f2b\u9b3c\u6ce3\u4f46\u4e01\u5168\u7a0b\u753b\u6cd5',
  16             'ext': 'flv'
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         title = self._html_search_regex(r'<meta\s+name="description"\s+content="\s*([^"]*)\s*"', webpage, 'title')
  25         ref_path = self._search_regex(r'src="(/mioplayer/.*?)"', webpage, 'ref_path')
  26         referer = 'http://www.miomio.tv{0}'.format(ref_path)
  27         xml_config = self._search_regex(r'flashvars="type=sina&amp;(.*?)&amp;cid=', webpage, 'xml config')
  28
  29         # skipping the following page causes lags and eventually connection drop-outs
  30         # id is normally a rotating three digit value but a fixed value always appears to work
  31         self._request_webpage("http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id={0}&r=cc{1}".format(id, 945), video_id)
  32
  33         # the following xml contains the actual configuration information on the video file(s)
  34         xml_url = 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config)
  35         vidconfig = self._download_xml(xml_url, video_id)
  36
  37         file_els = vidconfig.findall('.//durl')
  38
  39         entries = []
  40
  41         for file_el in file_els:
  42             segment_id = file_el.find('order').text.strip()
  43             segment_title = '_'.join([title, segment_id])
  44             segment_duration = file_el.find('length').text.strip()
  45             segment_url = file_el.find('url').text.strip()
  46
  47             entries.append({
  48                 'id': segment_id,
  49                 'title': segment_title,
  50                 'duration': segment_duration,
  51                 'url': segment_url
  52             })
  53
  54         http_headers = {
  55             'Referer': referer,
  56             'Accept-Encoding': 'gzip, deflate',
  57             'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
  58         }
  59
  60         if len(entries) == 1:
  61             return {
  62                 'id': video_id,
  63                 'title': title,
  64                 'url': entries[0]['url'],
  65                 'http_headers': http_headers
  66             }
  67
  68         return {
  69             '_type': 'multi_video',
  70             'id': video_id,
  71             'title': title,
  72             'entries': entries,
  73             'http_headers': http_headers
  74         }