From 781cc523af69a98efbd1b93cc89cec76145b8d14 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda - Campagna Date: Tue, 10 Apr 2012 18:54:40 +0200 Subject: [PATCH] removed the undocumented HTMLParser.unescape, replaced with _unescapeHTML; fixed a bug in the use of _unescapeHTML (missing _, from d6a96153471ae7e93693cb4dee46cbec1492af7b) --- youtube-dl | 28 ++++++++++++++-------------- youtube_dl/__init__.py | 28 ++++++++++++++-------------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/youtube-dl b/youtube-dl index 752d762eb..78fb07ea1 100755 --- a/youtube-dl +++ b/youtube-dl @@ -308,13 +308,13 @@ def clean_html(html): # Strip html tags html = re.sub('<.*?>', '', html) # Replace html entities - html = re.sub(ur'(?u)&(.+?);', htmlentity_transform, html) + html = _unescapeHTML(html) return html def sanitize_title(utitle): """Sanitizes a video title so it could be used as part of a filename.""" - utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) + utitle = _unescapeHTML(utitle) return utitle.replace(unicode(os.sep), u'%') @@ -371,8 +371,8 @@ def _unescapeHTML(s): """ assert type(s) == type(u'') - htmlParser = HTMLParser.HTMLParser() - return htmlParser.unescape(s) + result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s) + return result def _encodeFilename(s): """ @@ -1324,8 +1324,8 @@ class YoutubeIE(InfoExtractor): end = start + float(dur) start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) - caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) - caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional + caption = _unescapeHTML(caption) + caption = _unescapeHTML(caption) # double cycle, inentional srt += str(n) + '\n' srt += start + ' --> ' + end + '\n' srt += caption + '\n\n' @@ -2143,7 +2143,7 @@ class YahooIE(InfoExtractor): self._downloader.trouble(u'ERROR: Unable to extract media URL') return video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') - video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) + video_url = _unescapeHTML(video_url) try: # Process video information @@ -3410,11 +3410,11 @@ class EscapistIE(InfoExtractor): return descMatch = re.search('([^<]+)', coursepage) if m: - info['title'] = unescapeHTML(m.group(1)) + info['title'] = _unescapeHTML(m.group(1)) else: info['title'] = info['id'] info['stitle'] = _simplify_title(info['title']) m = re.search('([^<]+)', coursepage) if m: - info['description'] = unescapeHTML(m.group(1)) + info['description'] = _unescapeHTML(m.group(1)) links = _orderedSet(re.findall('', coursepage)) info['list'] = [ { 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(vpage), } for vpage in links] @@ -4007,7 +4007,7 @@ class StanfordOpenClassroomIE(InfoExtractor): info['list'] = [ { 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(cpage), } for cpage in links] diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 752d762eb..78fb07ea1 100755 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -308,13 +308,13 @@ def clean_html(html): # Strip html tags html = re.sub('<.*?>', '', html) # Replace html entities - html = re.sub(ur'(?u)&(.+?);', htmlentity_transform, html) + html = _unescapeHTML(html) return html def sanitize_title(utitle): """Sanitizes a video title so it could be used as part of a filename.""" - utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) + utitle = _unescapeHTML(utitle) return utitle.replace(unicode(os.sep), u'%') @@ -371,8 +371,8 @@ def _unescapeHTML(s): """ assert type(s) == type(u'') - htmlParser = HTMLParser.HTMLParser() - return htmlParser.unescape(s) + result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s) + return result def _encodeFilename(s): """ @@ -1324,8 +1324,8 @@ def _closed_captions_xml_to_srt(self, xml_string): end = start + float(dur) start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) - caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) - caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional + caption = _unescapeHTML(caption) + caption = _unescapeHTML(caption) # double cycle, inentional srt += str(n) + '\n' srt += start + ' --> ' + end + '\n' srt += caption + '\n\n' @@ -2143,7 +2143,7 @@ def _real_extract(self, url, new_video=True): self._downloader.trouble(u'ERROR: Unable to extract media URL') return video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') - video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) + video_url = _unescapeHTML(video_url) try: # Process video information @@ -3410,11 +3410,11 @@ def _real_extract(self, url): return descMatch = re.search('([^<]+)', coursepage) if m: - info['title'] = unescapeHTML(m.group(1)) + info['title'] = _unescapeHTML(m.group(1)) else: info['title'] = info['id'] info['stitle'] = _simplify_title(info['title']) m = re.search('([^<]+)', coursepage) if m: - info['description'] = unescapeHTML(m.group(1)) + info['description'] = _unescapeHTML(m.group(1)) links = _orderedSet(re.findall('', coursepage)) info['list'] = [ { 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(vpage), } for vpage in links] @@ -4007,7 +4007,7 @@ def _real_extract(self, url): info['list'] = [ { 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(cpage), } for cpage in links]