youtube_dl/extractor/academicearth.py

   1 from __future__ import unicode_literals
   2 import re
   3
   4 from .common import InfoExtractor
   5
   6
   7 class AcademicEarthCourseIE(InfoExtractor):
   8     _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
   9     IE_NAME = 'AcademicEarth:Course'
  10
  11     def _real_extract(self, url):
  12         m = re.match(self._VALID_URL, url)
  13         playlist_id = m.group('id')
  14
  15         webpage = self._download_webpage(url, playlist_id)
  16         title = self._html_search_regex(
  17             r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
  18         description = self._html_search_regex(
  19             r'<p class="excerpt"[^>]*?>(.*?)</p>',
  20             webpage, u'description', fatal=False)
  21         urls = re.findall(
  22             r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
  23             webpage)
  24         entries = [self.url_result(u) for u in urls]
  25
  26         return {
  27             '_type': 'playlist',
  28             'id': playlist_id,
  29             'title': title,
  30             'description': description,
  31             'entries': entries,
  32         }