youtube_dl/extractor/academicearth.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class AcademicEarthCourseIE(InfoExtractor):
   7     _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
   8     IE_NAME = u'AcademicEarth:Course'
   9
  10     def _real_extract(self, url):
  11         m = re.match(self._VALID_URL, url)
  12         playlist_id = m.group('id')
  13
  14         webpage = self._download_webpage(url, playlist_id)
  15         title = self._html_search_regex(
  16             r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
  17         description = self._html_search_regex(
  18             r'<p class="excerpt">(.*?)</p>',
  19             webpage, u'description', fatal=False)
  20         urls = re.findall(
  21             r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
  22             webpage)
  23         entries = [self.url_result(u) for u in urls]
  24
  25         return {
  26             '_type': 'playlist',
  27             'id': playlist_id,
  28             'title': title,
  29             'description': description,
  30             'entries': entries,
  31         }