From 2c94198eb62a9ce46a09badfdb232f8b5243a893 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 19 Nov 2015 21:29:32 +0600 Subject: [PATCH] [vimeo] Improve playlists extraction --- youtube_dl/extractor/vimeo.py | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index b72341a2b..cb8c0d484 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -486,8 +486,7 @@ def _login_list_password(self, page_url, list_id, webpage): password_request, list_id, 'Verifying the password', 'Wrong password') - def _extract_videos(self, list_id, base_url): - video_ids = [] + def _title_and_entries(self, list_id, base_url): for pagenum in itertools.count(1): page_url = self._page_url(base_url, pagenum) webpage = self._download_webpage( @@ -496,18 +495,18 @@ def _extract_videos(self, list_id, base_url): if pagenum == 1: 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: break - entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo') - for video_id in video_ids] - return {'_type': 'playlist', - 'id': list_id, - 'title': self._extract_list_title(webpage), - 'entries': entries, - } + def _extract_videos(self, list_id, base_url): + title_and_entries = self._title_and_entries(list_id, base_url) + list_title = next(title_and_entries) + return self.playlist_result(title_and_entries, list_id, list_title) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url)