yt_dlp/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/playlists/(?P<id>[^?#/]+)'
   8     IE_NAME = 'AcademicEarth:Course'
   9     _TEST = {
  10         'url': 'http://academicearth.org/playlists/laws-of-nature/',
  11         'info_dict': {
  12             'id': 'laws-of-nature',
  13             'title': 'Laws of Nature',
  14             'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
  15         },
  16         'playlist_count': 3,
  17     }
  18
  19     def _real_extract(self, url):
  20         playlist_id = self._match_id(url)
  21
  22         webpage = self._download_webpage(url, playlist_id)
  23         title = self._html_search_regex(
  24             r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
  25         description = self._html_search_regex(
  26             r'<p class="excerpt"[^>]*?>(.*?)</p>',
  27             webpage, 'description', fatal=False)
  28         urls = re.findall(
  29             r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
  30             webpage)
  31         entries = [self.url_result(u) for u in urls]
  32
  33         return {
  34             '_type': 'playlist',
  35             'id': playlist_id,
  36             'title': title,
  37             'description': description,
  38             'entries': entries,
  39         }