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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     unescapeHTML,
   7 )
   8
   9 class ZDFIE(InfoExtractor):
  10     _VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek\/(.*beitrag\/video\/)(?P<video_id>[^/\?]+)(?:\?.*)?'
  11     _TITLE = r'<h1(?: class="beitragHeadline")?>(?P<title>.*)</h1>'
  12     _MEDIA_STREAM = r'<a href="(?P<video_url>.+(?P<media_type>.streaming).+/zdf/(?P<quality>[^\/]+)/[^"]*)".+class="play".+>'
  13     _MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
  14     _RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
  15
  16     def _real_extract(self, url):
  17         mobj = re.match(self._VALID_URL, url)
  18         if mobj is None:
  19             raise ExtractorError(u'Invalid URL: %s' % url)
  20         video_id = mobj.group('video_id')
  21
  22         html = self._download_webpage(url, video_id)
  23         streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
  24         if streams is None:
  25             raise ExtractorError(u'No media url found.')
  26
  27         # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url
  28         # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url
  29         # choose first/default media type and highest quality for now
  30         for s in streams:        #find 300 - dsl1000mbit
  31             if s['quality'] == '300' and s['media_type'] == 'wstreaming':
  32                 stream_=s
  33                 break
  34         for s in streams:        #find veryhigh - dsl2000mbit
  35             if s['quality'] == 'veryhigh' and s['media_type'] == 'wstreaming': # 'hstreaming' - rtsp is not working
  36                 stream_=s
  37                 break
  38         if stream_ is None:
  39             raise ExtractorError(u'No stream found.')
  40
  41         media_link = self._download_webpage(stream_['video_url'], video_id,'Get stream URL')
  42
  43         self.report_extraction(video_id)
  44         mobj = re.search(self._TITLE, html)
  45         if mobj is None:
  46             raise ExtractorError(u'Cannot extract title')
  47         title = unescapeHTML(mobj.group('title'))
  48
  49         mobj = re.search(self._MMS_STREAM, media_link)
  50         if mobj is None:
  51             mobj = re.search(self._RTSP_STREAM, media_link)
  52             if mobj is None:
  53                 raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL')
  54         mms_url = mobj.group('video_url')
  55
  56         mobj = re.search('(.*)[.](?P<ext>[^.]+)', mms_url)
  57         if mobj is None:
  58             raise ExtractorError(u'Cannot extract extention')
  59         ext = mobj.group('ext')
  60
  61         return [{'id': video_id,
  62                  'url': mms_url,
  63                  'title': title,
  64                  'ext': ext
  65                  }]