diff options
author | Petr Půlpán <Pulpan3@gmail.com> | 2014-06-29 13:45:10 +0200 |
---|---|---|
committer | Petr Půlpán <Pulpan3@gmail.com> | 2014-06-29 13:45:10 +0200 |
commit | 31a196d7f55d7d7676c08553474a5ec122178177 (patch) | |
tree | 60649df84215697fb7d0f4fb819b86cea76c5da2 /youtube_dl/extractor/teachertube.py | |
parent | 9b27e6c3b49175e1e9b8f809607e7fbdee4cb9ac (diff) |
[TeacherTube] add user + collection, removed classrooms
Diffstat (limited to 'youtube_dl/extractor/teachertube.py')
-rw-r--r-- | youtube_dl/extractor/teachertube.py | 28 |
1 files changed, 19 insertions, 9 deletions
diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index d9868d569..73b4a3634 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -86,22 +86,32 @@ class TeacherTubeIE(InfoExtractor): } -class TeacherTubeClassroomIE(InfoExtractor): - IE_NAME = 'teachertube:classroom' - IE_DESC = 'teachertube.com online classrooms' +class TeacherTubeUserIE(InfoExtractor): + IE_NAME = 'teachertube:user:collection' + IE_DESC = 'teachertube.com user and collection videos' - _VALID_URL = r'https?://(?:www\.)?teachertube\.com/view_classroom\.php\?user=(?P<user>[0-9a-zA-Z]+)' + _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user_id = mobj.group('user') - rss = self._download_xml( - 'http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id, - user_id, 'Downloading classroom RSS') + urls = [] + webpage = self._download_webpage(url, user_id) + urls.extend(re.findall( + r'"sidebar_thumb_time">[0-9:]+</div>\s+<a href="(https?://(?:www\.)?teachertube\.com/(video|audio)/[^"]+)">', + webpage)) + + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1] + for p in pages: + more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) + webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages) + 1)) + urls.extend(re.findall( + r'"sidebar_thumb_time">[0-9:]+</div>\s+<a href="(https?://(?:www\.)?teachertube\.com/(video|audio)/[^"]+)">', + webpage)) entries = [] - for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'): - entries.append(self.url_result(url.attrib['url'], 'TeacherTube')) + for url in urls: + entries.append(self.url_result(url, 'TeacherTube')) return self.playlist_result(entries, user_id) |