X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Facademicearth.py;h=34095501cfa342e7ccb4afdb77e14b9514ca389c;hb=HEAD;hp=f6217328274876c9fa981e9ca3969d44c4ed783a;hpb=9e57ce716f03daa8ae27979af757819078595d6a;p=youtube-dl diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index f62173282..34095501c 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -1,4 +1,5 @@ from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,18 +8,25 @@ from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P[^?#/]+)' IE_NAME = 'AcademicEarth:Course' + _TEST = { + 'url': 'http://academicearth.org/playlists/laws-of-nature/', + 'info_dict': { + 'id': 'laws-of-nature', + 'title': 'Laws of Nature', + 'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.', + }, + 'playlist_count': 3, + } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - playlist_id = m.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) title = self._html_search_regex( - r'

]*?>(.*?)

', webpage, u'title') + r'

]*?>(.*?)

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

]*?>(.*?)

', - webpage, u'description', fatal=False) - print(description) + webpage, 'description', fatal=False) urls = re.findall( r'
  • \s*?', webpage)