youtube_dl/extractor/stanfordoc.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     orderedSet,
   9     unescapeHTML,
  10 )
  11
  12
  13 class StanfordOpenClassroomIE(InfoExtractor):
  14     IE_NAME = 'stanfordoc'
  15     IE_DESC = 'Stanford Open ClassRoom'
  16     _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
  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': 'PracticalUnix_intro-environment',
  22             'ext': 'mp4',
  23             'title': 'Intro Environment',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29
  30         if mobj.group('course') and mobj.group('video'):  # A specific video
  31             course = mobj.group('course')
  32             video = mobj.group('video')
  33             info = {
  34                 'id': course + '_' + video,
  35                 'uploader': None,
  36                 'upload_date': None,
  37             }
  38
  39             baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
  40             xmlUrl = baseUrl + video + '.xml'
  41             mdoc = self._download_xml(xmlUrl, info['id'])
  42             try:
  43                 info['title'] = mdoc.findall('./title')[0].text
  44                 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
  45             except IndexError:
  46                 raise ExtractorError('Invalid metadata XML file')
  47             return info
  48         elif mobj.group('course'):  # A course page
  49             course = mobj.group('course')
  50             info = {
  51                 'id': course,
  52                 '_type': 'playlist',
  53                 'uploader': None,
  54                 'upload_date': None,
  55             }
  56
  57             coursepage = self._download_webpage(
  58                 url, info['id'],
  59                 note='Downloading course info page',
  60                 errnote='Unable to download course info page')
  61
  62             info['title'] = self._html_search_regex(
  63                 r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
  64
  65             info['description'] = self._html_search_regex(
  66                 r'(?s)<description>([^<]+)</description>',
  67                 coursepage, 'description', fatal=False)
  68
  69             links = orderedSet(re.findall(r'<a href="(VideoPage.php\?[^"]+)">', coursepage))
  70             info['entries'] = [self.url_result(
  71                 'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
  72             ) for l in links]
  73             return info
  74         else:  # Root page
  75             info = {
  76                 'id': 'Stanford OpenClassroom',
  77                 '_type': 'playlist',
  78                 'uploader': None,
  79                 'upload_date': None,
  80             }
  81             info['title'] = info['id']
  82
  83             rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
  84             rootpage = self._download_webpage(rootURL, info['id'],
  85                                               errnote='Unable to download course info page')
  86
  87             links = orderedSet(re.findall(r'<a href="(CoursePage.php\?[^"]+)">', rootpage))
  88             info['entries'] = [self.url_result(
  89                 'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
  90             ) for l in links]
  91             return info