diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-02-24 14:18:12 +0100 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-02-24 14:18:12 +0100 |
| commit | 9e57ce716f03daa8ae27979af757819078595d6a (patch) | |
| tree | 0d41c1bccb5aaa6cf78148de49fd9999dcb5f6ef /youtube_dl | |
| parent | cd7ee7aa444ac85ddf6ca29645195f331d96d139 (diff) | |
[academicearth] Fix extraction
The courses seems to be no longer available, changed the test to a playlist.
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/academicearth.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index 72f81d01a..f62173282 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -5,7 +5,7 @@ from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)' + _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)' IE_NAME = 'AcademicEarth:Course' def _real_extract(self, url): @@ -14,12 +14,13 @@ class AcademicEarthCourseIE(InfoExtractor): webpage = self._download_webpage(url, playlist_id) title = self._html_search_regex( - r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title') + r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title') description = self._html_search_regex( - r'<p class="excerpt">(.*?)</p>', + r'<p class="excerpt"[^>]*?>(.*?)</p>', webpage, u'description', fatal=False) + print(description) urls = re.findall( - r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">', + r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">', webpage) entries = [self.url_result(u) for u in urls] |