Raphaël G. Git Repositories - youtubedl/blob - 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     _TEST = {
  11         'url': 'http://academicearth.org/playlists/laws-of-nature/',
  12         'info_dict': {
  13             'id': 'laws-of-nature',
  14             'title': 'Laws of Nature',
  15             'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
  16         },
  17         'playlist_count': 4,
  18     }
  19
  20     def _real_extract(self, url):
  21         m = re.match(self._VALID_URL, url)
  22         playlist_id = m.group('id')
  23
  24         webpage = self._download_webpage(url, playlist_id)
  25         title = self._html_search_regex(
  26             r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
  27         description = self._html_search_regex(
  28             r'<p class="excerpt"[^>]*?>(.*?)</p>',
  29             webpage, u'description', fatal=False)
  30         urls = re.findall(
  31             r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
  32             webpage)
  33         entries = [self.url_result(u) for u in urls]
  34
  35         return {
  36             '_type': 'playlist',
  37             'id': playlist_id,
  38             'title': title,
  39             'description': description,
  40             'entries': entries,
  41         }