github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[teachertube] Fix title and playlist recognition

Browse source
This commit is contained in:
Philipp Hagemeister 2014-07-21 12:47:01 +02:00
parent d8624e6a80
commit 1a30deca50
2 changed files with 12 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
youtube_dl/extractor/common.py
View file

@ -469,7 +469,7 @@ def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs
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)

20
youtube_dl/extractor/teachertube.py
View file

@ -62,7 +62,7 @@ def _real_extract(self, url):
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 @@ def _real_extract(self, url):
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)