diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-07-03 21:08:44 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-07-03 21:08:44 +0700 |
commit | 7aeb67b39b055e9586e7ab21c108a3176cfe0203 (patch) | |
tree | 28c896eda472705503ccf4510d631dac83b84e5d /youtube_dl/extractor | |
parent | 93881db22a331ac7ce855c4680998aedf9a68cfa (diff) |
[teachertube:user:collection] Update media regex
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/teachertube.py | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 1a438e1e4..7167a036e 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -92,23 +92,21 @@ class TeacherTubeUserIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?' + _MEDIA_RE = r'(?s)"sidebar_thumb_time">[0-9:]+</div>.+?<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">' + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user_id = mobj.group('user') 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)) + urls.extend(re.findall(self._MEDIA_RE, 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)) + urls.extend(re.findall(self._MEDIA_RE, webpage)) entries = [] for url in urls: |