youtube_dl/extractor/spiegel.py

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5
   6
   7 class SpiegelIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
   9     _TEST = {
  10         u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
  11         u'file': u'1259285.mp4',
  12         u'md5': u'2c2754212136f35fb4b19767d242f66e',
  13         u'info_dict': {
  14             u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         m = re.match(self._VALID_URL, url)
  20         video_id = m.group('videoID')
  21
  22         webpage = self._download_webpage(url, video_id)
  23
  24         video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
  25             webpage, u'title')
  26
  27         xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
  28         xml_code = self._download_webpage(xml_url, video_id,
  29                     note=u'Downloading XML', errnote=u'Failed to download XML')
  30
  31         idoc = xml.etree.ElementTree.fromstring(xml_code)
  32         last_type = idoc[-1]
  33         filename = last_type.findall('./filename')[0].text
  34         duration = float(last_type.findall('./duration')[0].text)
  35
  36         video_url = 'http://video2.spiegel.de/flash/' + filename
  37         video_ext = filename.rpartition('.')[2]
  38         info = {
  39             'id': video_id,
  40             'url': video_url,
  41             'ext': video_ext,
  42             'title': video_title,
  43             'duration': duration,
  44         }
  45         return [info]