From 1413cd87ebe7297aa48fae43bce9c92a751641fb Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 5 Jan 2012 10:46:21 +0100 Subject: [PATCH] Correct distinction between unicode and bytes (Closes: #257) --- youtube_dl/__init__.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 2404e2359c..fef2afe172 100755 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -290,6 +290,15 @@ def _orderedSet(iterable): res.append(el) return res +def _unescapeHTML(s): + """ + @param s a string (of type unicode) + """ + assert type(s) == type(u'') + + htmlParser = HTMLParser.HTMLParser() + return htmlParser.unescape(s) + class DownloadError(Exception): """Download Error exception. @@ -1590,8 +1599,6 @@ def report_extraction(self, video_id): self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) def _real_extract(self, url): - htmlParser = HTMLParser.HTMLParser() - # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -1635,7 +1642,7 @@ def _real_extract(self, url): if mobj is None: self._downloader.trouble(u'ERROR: unable to extract title') return - video_title = htmlParser.unescape(mobj.group('title')).decode('utf-8') + video_title = _unescapeHTML(mobj.group('title').decode('utf-8')) video_title = sanitize_title(video_title) simple_title = _simplify_title(video_title)