diff options
| author | Sergey M․ <[email protected]> | 2018-09-11 02:29:45 +0700 |
|---|---|---|
| committer | Sergey M․ <[email protected]> | 2018-09-11 02:32:01 +0700 |
| commit | 79facb27735baf27d65baf050121d68e26654a02 (patch) | |
| tree | 91803fa9c2cf12c5f552c0f1050bf6ce0fecab47 | |
| parent | 96dbf70de63c08fc27e9bd7bec97670325225758 (diff) | |
| download | youtube-dl-79facb27735baf27d65baf050121d68e26654a02.tar.gz youtube-dl-79facb27735baf27d65baf050121d68e26654a02.zip | |
[tube8] Fix metadata extraction (closes #17520)
| -rw-r--r-- | youtube_dl/extractor/tube8.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 368c45729..db93b0182 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -45,7 +45,7 @@ class Tube8IE(KeezMoviesIE): r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') description = self._html_search_regex( - r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False) + r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False) uploader = self._html_search_regex( r'<span class="username">\s*(.+?)\s*<', webpage, 'uploader', fatal=False) @@ -55,19 +55,19 @@ class Tube8IE(KeezMoviesIE): dislike_count = int_or_none(self._search_regex( r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False)) view_count = str_to_int(self._search_regex( - r'<strong>Views: </strong>([\d,\.]+)\s*</li>', + r'Views:\s*</dt>\s*<dd>([\d,\.]+)', webpage, 'view count', fatal=False)) comment_count = str_to_int(self._search_regex( r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)) category = self._search_regex( - r'Category:\s*</strong>\s*<a[^>]+href=[^>]+>([^<]+)', + r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)', webpage, 'category', fatal=False) categories = [category] if category else None tags_str = self._search_regex( - r'(?s)Tags:\s*</strong>(.+?)</(?!a)', + r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)', webpage, 'tags', fatal=False) tags = [t for t in re.findall( r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None |