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

   1 import os.path
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse_urlparse,
   6
   7     ExtractorError,
   8 )
   9
  10
  11 class MySpassIE(InfoExtractor):
  12     _VALID_URL = r'http://www\.myspass\.de/.*'
  13     _TEST = {
  14         u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
  15         u'file': u'11741.mp4',
  16         u'md5': u'0b49f4844a068f8b33f4b7c88405862b',
  17         u'info_dict': {
  18             u"description": u"Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
  19             u"title": u"Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
  25
  26         # video id is the last path element of the URL
  27         # usually there is a trailing slash, so also try the second but last
  28         url_path = compat_urllib_parse_urlparse(url).path
  29         url_parent_path, video_id = os.path.split(url_path)
  30         if not video_id:
  31             _, video_id = os.path.split(url_parent_path)
  32
  33         # get metadata
  34         metadata_url = META_DATA_URL_TEMPLATE % video_id
  35         metadata = self._download_xml(metadata_url, video_id)
  36
  37         # extract values from metadata
  38         url_flv_el = metadata.find('url_flv')
  39         if url_flv_el is None:
  40             raise ExtractorError(u'Unable to extract download url')
  41         video_url = url_flv_el.text
  42         extension = os.path.splitext(video_url)[1][1:]
  43         title_el = metadata.find('title')
  44         if title_el is None:
  45             raise ExtractorError(u'Unable to extract title')
  46         title = title_el.text
  47         format_id_el = metadata.find('format_id')
  48         if format_id_el is None:
  49             format = 'mp4'
  50         else:
  51             format = format_id_el.text
  52         description_el = metadata.find('description')
  53         if description_el is not None:
  54             description = description_el.text
  55         else:
  56             description = None
  57         imagePreview_el = metadata.find('imagePreview')
  58         if imagePreview_el is not None:
  59             thumbnail = imagePreview_el.text
  60         else:
  61             thumbnail = None
  62         info = {
  63             'id': video_id,
  64             'url': video_url,
  65             'title': title,
  66             'ext': extension,
  67             'format': format,
  68             'thumbnail': thumbnail,
  69             'description': description
  70         }
  71         return [info]