X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/63a6927374492ef47c8fd6de67d0760ace4dd0ed..7a227c758cbd03f91f4e8848a6c65f9acd4b140c:/youtube_dl/extractor/academicearth.py diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index ac05f82..47313fb 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -1,24 +1,34 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P[^?#/]+)' - IE_NAME = u'AcademicEarth:Course' + _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': 4, + } 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) + r'

]*?>(.*?)

', + webpage, 'description', fatal=False) urls = re.findall( - r'

', + r'
  • \s*?', webpage) entries = [self.url_result(u) for u in urls]