|
@ -1,4 +1,5 @@ |
|
|
from __future__ import unicode_literals |
|
|
from __future__ import unicode_literals |
|
|
|
|
|
|
|
|
import re |
|
|
import re |
|
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
from .common import InfoExtractor |
|
@ -18,15 +19,14 @@ class AcademicEarthCourseIE(InfoExtractor): |
|
|
} |
|
|
} |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
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) |
|
|
webpage = self._download_webpage(url, playlist_id) |
|
|
title = self._html_search_regex( |
|
|
title = self._html_search_regex( |
|
|
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title') |
|
|
|
|
|
|
|
|
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title') |
|
|
description = self._html_search_regex( |
|
|
description = self._html_search_regex( |
|
|
r'<p class="excerpt"[^>]*?>(.*?)</p>', |
|
|
r'<p class="excerpt"[^>]*?>(.*?)</p>', |
|
|
webpage, u'description', fatal=False) |
|
|
|
|
|
|
|
|
webpage, 'description', fatal=False) |
|
|
urls = re.findall( |
|
|
urls = re.findall( |
|
|
r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">', |
|
|
r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">', |
|
|
webpage) |
|
|
webpage) |
|
|