diff options
author | Philipp Hagemeister <[email protected]> | 2014-07-21 12:47:01 +0200 |
---|---|---|
committer | Philipp Hagemeister <[email protected]> | 2014-07-21 12:47:01 +0200 |
commit | 1a30deca50d6256bb833aee672d5055d72319aca (patch) | |
tree | 2f98e10a6a3f86e6499d2f95c822c45605c551c7 | |
parent | d8624e6a80751c09a48ff6b9db1d4d85e377c437 (diff) | |
download | youtube-dl-1a30deca50d6256bb833aee672d5055d72319aca.tar.gz youtube-dl-1a30deca50d6256bb833aee672d5055d72319aca.zip |
[teachertube] Fix title and playlist recognition
-rw-r--r-- | youtube_dl/extractor/common.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/teachertube.py | 20 |
2 files changed, 12 insertions, 10 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 3213abacf..9b36e0789 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -469,7 +469,7 @@ class InfoExtractor(object): display_name = name return self._html_search_regex( r'''(?ix)<meta - (?=[^>]+(?:itemprop|name|property)=["\']%s["\']) + (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?) [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), html, display_name, fatal=fatal, **kwargs) diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 2c2113b14..46d727d1d 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -62,7 +62,7 @@ class TeacherTubeIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - title = self._html_search_meta('title', webpage, 'title') + title = self._html_search_meta('title', webpage, 'title', fatal=True) TITLE_SUFFIX = ' - TeacherTube' if title.endswith(TITLE_SUFFIX): title = title[:-len(TITLE_SUFFIX)].strip() @@ -101,7 +101,11 @@ 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)/[^"]+)">' + _MEDIA_RE = r'''(?sx) + class="?sidebar_thumb_time"?>[0-9:]+</div> + \s* + <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)" + ''' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -111,14 +115,12 @@ class TeacherTubeUserIE(InfoExtractor): webpage = self._download_webpage(url, user_id) 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] + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-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(self._MEDIA_RE, webpage)) - - entries = [] - for url in urls: - entries.append(self.url_result(url, 'TeacherTube')) + webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages))) + video_urls = re.findall(self._MEDIA_RE, webpage) + urls.extend(video_urls) + entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls] return self.playlist_result(entries, user_id) |