_ Git - youtube-dl/blob - youtube_dl/extractor/openclassroom.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_parse_qs
   8 from ..utils import (
   9     ExtractorError,
  10     xpath_text,
  11     clean_html,
  12 )
  13
  14
  15 class OpenClassRoomIE(InfoExtractor):
  16     _VALID_URL = r'https?://openclassroom\.stanford\.edu/MainFolder/VideoPage\.php\?(?P<query>.*)'
  17     _TEST = {
  18         'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
  19         'md5': '544a9468546059d4e80d76265b0443b8',
  20         'info_dict': {
  21             'id': 'intro-environment',
  22             'ext': 'mp4',
  23             'title': 'Intro Environment',
  24             'description': 'md5:7d57306c8649f814ca00bb80dada600e',
  25         }
  26     }
  27     _URL_TEMPLATE = 'http://openclassroom.stanford.edu/MainFolder/courses/%s/videos/%s'
  28
  29     def _real_extract(self, url):
  30         qs = compat_parse_qs(re.match(self._VALID_URL, url).group('query'))
  31         if not qs.get('course') or not qs.get('video'):
  32             raise ExtractorError('Unsupported URL', expected=True)
  33         video_id = qs['video'][0]
  34         video_doc = self._download_xml(
  35             self._URL_TEMPLATE % (qs['course'][0], video_id + '.xml'), video_id)
  36         return {
  37             'id': video_id,
  38             'title': xpath_text(video_doc, 'title', 'title', True),
  39             'url': self._URL_TEMPLATE % (qs['course'][0], xpath_text(
  40                 video_doc, 'videoFile', 'video url', True)),
  41             'description': clean_html(xpath_text(video_doc, 'text')),
  42         }