From dc786d3db59a611cbcb716a476602719e74a34e5 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sat, 18 Jul 2015 17:22:25 +0600 Subject: [PATCH] [vk:uservideos] Improve extraction --- youtube_dl/extractor/vk.py | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 8f677cae3..93c5b18c9 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -291,23 +291,32 @@ class VKIE(InfoExtractor): class VKUserVideosIE(InfoExtractor): IE_NAME = 'vk.com:user-videos' IE_DESC = 'vk.com:All of a user\'s videos' - _VALID_URL = r'https?://vk\.com/videos(?P[0-9]+)(?:m\?.*)?' + _VALID_URL = r'https?://vk\.com/videos(?P-?[0-9]+)$' _TEMPLATE_URL = 'https://vk.com/videos' - _TEST = { + _TESTS = [{ 'url': 'http://vk.com/videos205387401', 'info_dict': { 'id': '205387401', + 'title': "Tom Cruise's Videos", }, 'playlist_mincount': 4, - } + }, { + 'url': 'http://vk.com/videos-77521', + 'only_matching': True, + }] def _real_extract(self, url): page_id = self._match_id(url) - page = self._download_webpage(url, page_id) - video_ids = orderedSet( - m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page)) - url_entries = [ + + webpage = self._download_webpage(url, page_id) + + entries = [ self.url_result( 'http://vk.com/video' + video_id, 'VK', video_id=video_id) - for video_id in video_ids] - return self.playlist_result(url_entries, page_id) + for video_id in set(re.findall(r'href="/video(-?[0-9_]+)"', webpage))] + + title = unescapeHTML(self._search_regex( + r'\s*([^<]+?)\s+\|\s+\d+\s+videos', + webpage, 'title', default=page_id)) + + return self.playlist_result(entries, page_id, title) -- 2.40.0