From 79facb27735baf27d65baf050121d68e26654a02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 11 Sep 2018 02:29:45 +0700 Subject: [PATCH] [tube8] Fix metadata extraction (closes #17520) --- youtube_dl/extractor/tube8.py | 8 ++++---- 1 file 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 @@ def _real_extract(self, url): r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') description = self._html_search_regex( - r'>Description:\s*(.+?)\s*<', webpage, 'description', fatal=False) + r'(?s)Description:\s*
(.+?)
', webpage, 'description', fatal=False) uploader = self._html_search_regex( r'\s*(.+?)\s*<', webpage, 'uploader', fatal=False) @@ -55,19 +55,19 @@ def _real_extract(self, url): 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'Views: ([\d,\.]+)\s*', + r'Views:\s*\s*
([\d,\.]+)', webpage, 'view count', fatal=False)) comment_count = str_to_int(self._search_regex( r'(\d+)', webpage, 'comment count', fatal=False)) category = self._search_regex( - r'Category:\s*\s*]+href=[^>]+>([^<]+)', + r'Category:\s*\s*
\s*]+href=[^>]+>([^<]+)', webpage, 'category', fatal=False) categories = [category] if category else None tags_str = self._search_regex( - r'(?s)Tags:\s*(.+?)\s*
(.+?)]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None