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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class SpiegelIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
  10     _TESTS = [{
  11         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
  12         'file': '1259285.mp4',
  13         'md5': '2c2754212136f35fb4b19767d242f66e',
  14         'info_dict': {
  15             'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
  16         },
  17     },
  18     {
  19         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
  20         'file': '1309159.mp4',
  21         'md5': 'f2cdf638d7aa47654e251e1aee360af1',
  22         'info_dict': {
  23             'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
  24         },
  25     }]
  26
  27     def _real_extract(self, url):
  28         m = re.match(self._VALID_URL, url)
  29         video_id = m.group('videoID')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         video_title = self._html_search_regex(
  34             r'<div class="module-title">(.*?)</div>', webpage, 'title')
  35
  36         xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml'
  37         idoc = self._download_xml(
  38             xml_url, video_id,
  39             note='Downloading XML', errnote='Failed to download XML')
  40
  41         formats = [
  42             {
  43                 'format_id': n.tag.rpartition('type')[2],
  44                 'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text,
  45                 'width': int(n.find('./width').text),
  46                 'height': int(n.find('./height').text),
  47                 'abr': int(n.find('./audiobitrate').text),
  48                 'vbr': int(n.find('./videobitrate').text),
  49                 'vcodec': n.find('./codec').text,
  50                 'acodec': 'MP4A',
  51             }
  52             for n in list(idoc)
  53             # Blacklist type 6, it's extremely LQ and not available on the same server
  54             if n.tag.startswith('type') and n.tag != 'type6'
  55         ]
  56         duration = float(idoc[0].findall('./duration')[0].text)
  57
  58         self._sort_formats(formats)
  59
  60         return {
  61             'id': video_id,
  62             'title': video_title,
  63             'duration': duration,
  64             'formats': formats,
  65         }