youtube_dl/extractor/jukebox.py

   1 # coding: utf-8
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     unescapeHTML,
   8 )
   9
  10 class JukeboxIE(InfoExtractor):
  11     _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html'
  12     _IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
  13     _VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
  14     _TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
  15     _IS_YOUTUBE = r'config":{"file":"(?P<youtube_url>http:[\\][/][\\][/]www[.]youtube[.]com[\\][/]watch[?]v=[^"]+)"'
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19         video_id = mobj.group('video_id')
  20
  21         html = self._download_webpage(url, video_id)
  22
  23         mobj = re.search(self._IFRAME, html)
  24         if mobj is None:
  25             raise ExtractorError(u'Cannot extract iframe url')
  26         iframe_url = unescapeHTML(mobj.group('iframe'))
  27
  28         iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
  29         mobj = re.search(r'class="jkb_waiting"', iframe_html)
  30         if mobj is not None:
  31             raise ExtractorError(u'Video is not available(in your country?)!')
  32
  33         self.report_extraction(video_id)
  34
  35         mobj = re.search(self._VIDEO_URL, iframe_html)
  36         if mobj is None:
  37             mobj = re.search(self._IS_YOUTUBE, iframe_html)
  38             if mobj is None:
  39                 raise ExtractorError(u'Cannot extract video url')
  40             youtube_url = unescapeHTML(mobj.group('youtube_url')).replace('\/','/')
  41             self.to_screen(u'Youtube video detected')
  42             return self.url_result(youtube_url,ie='Youtube')
  43         video_url = unescapeHTML(mobj.group('video_url')).replace('\/','/')
  44         video_ext = unescapeHTML(mobj.group('video_ext'))
  45
  46         mobj = re.search(self._TITLE, html)
  47         if mobj is None:
  48             raise ExtractorError(u'Cannot extract title')
  49         title = unescapeHTML(mobj.group('title'))
  50         artist = unescapeHTML(mobj.group('artist'))
  51
  52         return [{'id': video_id,
  53                  'url': video_url,
  54                  'title': artist + '-' + title,
  55                  'ext': video_ext
  56                  }]