yt_dlp/extractor/stanfordoc.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     orderedSet,
   7     unescapeHTML,
   8 )
   9
  10
  11 class StanfordOpenClassroomIE(InfoExtractor):
  12     IE_NAME = 'stanfordoc'
  13     IE_DESC = 'Stanford Open ClassRoom'
  14     _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
  15     _TEST = {
  16         'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
  17         'md5': '544a9468546059d4e80d76265b0443b8',
  18         'info_dict': {
  19             'id': 'PracticalUnix_intro-environment',
  20             'ext': 'mp4',
  21             'title': 'Intro Environment',
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = self._match_valid_url(url)
  27
  28         if mobj.group('course') and mobj.group('video'):  # A specific video
  29             course = mobj.group('course')
  30             video = mobj.group('video')
  31             info = {
  32                 'id': course + '_' + video,
  33                 'uploader': None,
  34                 'upload_date': None,
  35             }
  36
  37             base_url = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
  38             xml_url = base_url + video + '.xml'
  39             mdoc = self._download_xml(xml_url, info['id'])
  40             try:
  41                 info['title'] = mdoc.findall('./title')[0].text
  42                 info['url'] = base_url + mdoc.findall('./videoFile')[0].text
  43             except IndexError:
  44                 raise ExtractorError('Invalid metadata XML file')
  45             return info
  46         elif mobj.group('course'):  # A course page
  47             course = mobj.group('course')
  48             info = {
  49                 'id': course,
  50                 '_type': 'playlist',
  51                 'uploader': None,
  52                 'upload_date': None,
  53             }
  54
  55             coursepage = self._download_webpage(
  56                 url, info['id'],
  57                 note='Downloading course info page',
  58                 errnote='Unable to download course info page')
  59
  60             info['title'] = self._html_search_regex(
  61                 r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
  62
  63             info['description'] = self._html_search_regex(
  64                 r'(?s)<description>([^<]+)</description>',
  65                 coursepage, 'description', fatal=False)
  66
  67             links = orderedSet(re.findall(r'<a href="(VideoPage\.php\?[^"]+)">', coursepage))
  68             info['entries'] = [self.url_result(
  69                 f'http://openclassroom.stanford.edu/MainFolder/{unescapeHTML(l)}',
  70             ) for l in links]
  71             return info
  72         else:  # Root page
  73             info = {
  74                 'id': 'Stanford OpenClassroom',
  75                 '_type': 'playlist',
  76                 'uploader': None,
  77                 'upload_date': None,
  78             }
  79             info['title'] = info['id']
  80
  81             root_url = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
  82             rootpage = self._download_webpage(root_url, info['id'],
  83                                               errnote='Unable to download course info page')
  84
  85             links = orderedSet(re.findall(r'<a href="(CoursePage\.php\?[^"]+)">', rootpage))
  86             info['entries'] = [self.url_result(
  87                 f'http://openclassroom.stanford.edu/MainFolder/{unescapeHTML(l)}',
  88             ) for l in links]
  89             return info