From e1e8b6897b2e2610c45eb53fe44e1e07c3c39e82 Mon Sep 17 00:00:00 2001 From: Will Sewell Date: Fri, 21 Nov 2014 23:16:12 +0000 Subject: [PATCH] [vk.com] Updated the extract_videos_from_page function with a much simpler 1-liner. --- youtube_dl/extractor/vk.py | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 7136a0cb2..e8d7cdeae 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -11,7 +11,8 @@ from ..utils import ( compat_urllib_parse, compat_str, unescapeHTML, - unified_strdate) + unified_strdate, + orderedSet) class VKIE(InfoExtractor): @@ -216,13 +217,6 @@ class VKUserVideosIE(InfoExtractor): 'playlist_mincount': 4, } - def extract_videos_from_page(self, page): - ids_in_page = [] - for mobj in re.finditer(r'href="/video([0-9_]+)"', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) - return ids_in_page - def _real_extract(self, url): # Extract page id mobj = re.match(self._VALID_URL, url) @@ -232,7 +226,7 @@ class VKUserVideosIE(InfoExtractor): # Download page and get video ids page_id = mobj.group(1) page = self._download_webpage(url, page_id) - video_ids = self.extract_videos_from_page(page) + video_ids = orderedSet(m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page)) self._downloader.to_screen('[vk] User videos %s: Found %i videos' % (page_id, len(video_ids))) -- 2.22.2