from __future__ import unicode_literals import re from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P[^?#/]+)' IE_NAME = 'AcademicEarth:Course' def _real_extract(self, url): m = re.match(self._VALID_URL, url) playlist_id = m.group('id') webpage = self._download_webpage(url, playlist_id) title = self._html_search_regex( r'

]*?>(.*?)

', webpage, u'title') description = self._html_search_regex( r'

]*?>(.*?)

', webpage, u'description', fatal=False) print(description) urls = re.findall( r'
  • \s*?', webpage) entries = [self.url_result(u) for u in urls] return { '_type': 'playlist', 'id': playlist_id, 'title': title, 'description': description, 'entries': entries, }