_ Git - youtube-dl/blob - youtube_dl/extractor/academicearth.py

   1 import datetime
   2 import json
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     remove_start,
   8 )
   9
  10
  11 class AcademicEarthCourseIE(InfoExtractor):
  12     _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/courses/(?P<id>[^?#/]+)'
  13     IE_NAME = u'AcademicEarth:Course'
  14
  15     def _real_extract(self, url):
  16         m = re.match(self._VALID_URL, url)
  17         playlist_id = m.group('id')
  18
  19         webpage = self._download_webpage(url, playlist_id)
  20         title = self._html_search_regex(
  21             r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
  22         description = self._html_search_regex(
  23             r'<p class="excerpt">(.*?)</p>',
  24             webpage, u'description', fatal=False)
  25         urls = re.findall(
  26             r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
  27             webpage)
  28         entries = [self.url_result(u) for u in urls]
  29
  30         return {
  31             '_type': 'playlist',
  32             'id': playlist_id,
  33             'title': title,
  34             'description': description,
  35             'entries': entries,
  36         }