diff options
| author | Sergey M․ <dstftw@gmail.com> | 2016-08-13 19:55:09 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2016-08-13 19:55:09 +0700 |
| commit | 77afa008dd14efd930f8504609815a8ad2fedc7f (patch) | |
| tree | f7b9d87cc5423a43e4f412791f30d3675959dc0e | |
| parent | db535435b30540029b292e7217fb443bcc670aab (diff) | |
[4tube] Fix metadata extraction (Closes #10321)
| -rw-r--r-- | youtube_dl/extractor/fourtube.py | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index fc4a5a0fb..9776c8422 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -43,14 +43,14 @@ class FourTubeIE(InfoExtractor): 'uploadDate', webpage)) thumbnail = self._html_search_meta('thumbnailUrl', webpage) uploader_id = self._html_search_regex( - r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">', + r'<a class="item-to-subscribe" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">', webpage, 'uploader id', fatal=False) uploader = self._html_search_regex( - r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">', + r'<a class="item-to-subscribe" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">', webpage, 'uploader', fatal=False) categories_html = self._search_regex( - r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>', + r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="[^"]*?list[^"]*?">(.*?)</ul>', webpage, 'categories', fatal=False) categories = None if categories_html: @@ -59,10 +59,10 @@ class FourTubeIE(InfoExtractor): r'(?s)<li><a.*?>(.*?)</a>', categories_html)] view_count = str_to_int(self._search_regex( - r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">', + r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">', webpage, 'view count', fatal=False)) like_count = str_to_int(self._search_regex( - r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">', + r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">', webpage, 'like count', fatal=False)) duration = parse_duration(self._html_search_meta('duration', webpage)) |