From 394df6d7d0f4a5b90e45a519ba1c803484c0e087 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 22 Aug 2014 21:41:51 +0700 Subject: [PATCH] [nuvid] Adapt to latest layout changes --- youtube_dl/extractor/nuvid.py | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 280328b783..58ec81f911 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -38,7 +38,7 @@ def _real_extract(self, url): webpage = self._download_webpage( request, video_id, 'Downloading %s page' % format_id) video_url = self._html_search_regex( - r'Continue to watch video', webpage, '%s video URL' % format_id, fatal=False) + r'', webpage, '%s video URL' % format_id, fatal=False) if not video_url: continue formats.append({ @@ -49,19 +49,24 @@ def _real_extract(self, url): webpage = self._download_webpage( 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') title = self._html_search_regex( - r'
\s+]*>([^<]+)', webpage, 'title').strip() - thumbnail = self._html_search_regex( - r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', - webpage, 'thumbnail URL', fatal=False) + [r'', + r'
\s*]*>([^<]+)'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( - r'Length:\s*(\d{2}:\d{2})',webpage, 'duration', fatal=False)) + r'\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_regex( - r'Added:\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) + r'\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) return { 'id': video_id, 'title': title, - 'thumbnail': 'http://m.nuvid.com%s' % thumbnail, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, 'duration': duration, 'upload_date': upload_date, 'age_limit': 18,