jon1scr
/
yt-dlc
forked from minhngoc25a/yt-dlc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[teachertube:user:collection] Update media regex

This commit is contained in:
Sergey M․ 2014-07-03 21:08:44 +07:00
parent 93881db22a
commit 7aeb67b39b
1 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
youtube_dl/extractor/teachertube.py
View File

@ -92,23 +92,21 @@ class TeacherTubeUserIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?' _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): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user') user_id = mobj.group('user')
urls = [] urls = []
webpage = self._download_webpage(url, user_id) webpage = self._download_webpage(url, user_id)
urls.extend(re.findall( urls.extend(re.findall(self._MEDIA_RE, webpage))
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] pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1]
for p in pages: for p in pages:
more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) 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)) webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages) + 1))
urls.extend(re.findall( urls.extend(re.findall(self._MEDIA_RE, webpage))
r'"sidebar_thumb_time">[0-9:]+</div>\s+<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">',
webpage))
entries = [] entries = []
for url in urls: for url in urls: