youtube_dl/extractor/jukebox.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     unescapeHTML,
   7 )
   8
   9 class JukeboxIE(InfoExtractor):
  10     _VALID_URL = r'^http://www\.jukebox\.es\/.+[,](?P<video_id>[a-z0-9]+).html'
  11     _IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
  12     _VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
  13     _TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
  14     _NOT_AVAILABLE = r'<span>Este video no está disponible por el momento [!]</span>'
  15     _IS_YOUTUBE = r'config":{"file":"(?P<youtube_url>http:[\\][/][\\][/]www[.]youtube[.]com[\\][/]watch[?]v=[^"]+)"'
  16     IE_NAME = u'jukebox'
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20         if mobj is None:
  21             raise ExtractorError(u'Invalid URL: %s' % url)
  22         video_id = mobj.group('video_id')
  23
  24         html = self._download_webpage(url, video_id)
  25
  26         mobj = re.search(self._IFRAME, html)
  27         if mobj is None:
  28             raise ExtractorError(u'Cannot extract iframe url')
  29         iframe_url = unescapeHTML(mobj.group('iframe'))
  30
  31         iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
  32         mobj = re.search(self._NOT_AVAILABLE, iframe_html)
  33         if mobj is not None:
  34             raise ExtractorError(u'Video is not available(in your country?)!')
  35
  36         self.report_extraction(video_id)
  37
  38         mobj = re.search(self._VIDEO_URL, iframe_html)
  39         if mobj is None:
  40             mobj = re.search(self._IS_YOUTUBE, iframe_html)
  41             if mobj is None:
  42                 raise ExtractorError(u'Cannot extract video url')
  43             youtube_url = unescapeHTML(mobj.group('youtube_url')).replace('\/','/')
  44             self.to_screen(u'Youtube video detected')
  45             return self.url_result(youtube_url,ie='Youtube')
  46         video_url = unescapeHTML(mobj.group('video_url')).replace('\/','/')
  47         video_ext = unescapeHTML(mobj.group('video_ext'))
  48
  49         mobj = re.search(self._TITLE, html)
  50         if mobj is None:
  51             raise ExtractorError(u'Cannot extract title')
  52         title = unescapeHTML(mobj.group('title'))
  53         artist = unescapeHTML(mobj.group('artist'))
  54
  55         return [{'id': video_id,
  56                  'url': video_url,
  57                  'title': artist + '-' + title,
  58                  'ext': video_ext
  59                  }]