w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[vimeo] Improve playlists extraction

Browse source
This commit is contained in:
Sergey M․ 2015-11-19 21:29:32 +06:00
parent e8110b8125
commit 2c94198eb6
1 changed files with 9 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
youtube_dl/extractor/vimeo.py
View file

@ -486,8 +486,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
password_request, list_id, password_request, list_id,
'Verifying the password', 'Wrong password') 'Verifying the password', 'Wrong password')
def _extract_videos(self, list_id, base_url): def _title_and_entries(self, list_id, base_url):
video_ids = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
page_url = self._page_url(base_url, pagenum) page_url = self._page_url(base_url, pagenum)
webpage = self._download_webpage( webpage = self._download_webpage(
@ -496,18 +495,18 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
if pagenum == 1: if pagenum == 1:
webpage = self._login_list_password(page_url, list_id, webpage) webpage = self._login_list_password(page_url, list_id, webpage)
yield self._extract_list_title(webpage)
for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break break
entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') def _extract_videos(self, list_id, base_url):
for video_id in video_ids] title_and_entries = self._title_and_entries(list_id, base_url)
return {'_type': 'playlist', list_title = next(title_and_entries)
'id': list_id, return self.playlist_result(title_and_entries, list_id, list_title)
'title': self._extract_list_title(webpage),
'entries': entries,
}
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)