From: Filippo Valsorda Date: Fri, 13 Apr 2012 20:09:24 +0000 (+0200) Subject: some HTMLParser bugfixes X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=9beb5af82ecfbb35ee534692e73fb38f4399698a;p=youtube-dl some HTMLParser bugfixes --- diff --git a/youtube-dl b/youtube-dl index c4b5c07ca..e4d7beb2d 100755 Binary files a/youtube-dl and b/youtube-dl differ diff --git a/youtube-dl.exe b/youtube-dl.exe index cb9654283..287b78af5 100755 Binary files a/youtube-dl.exe and b/youtube-dl.exe differ diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d77154dcb..ae98e1264 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -359,8 +359,8 @@ class YoutubeIE(InfoExtractor): pass # description - video_description = get_element_by_id("eow-description", video_webpage) - if video_description: video_description = clean_html(video_description.decode('utf8')) + video_description = get_element_by_id("eow-description", video_webpage.decode('utf8')) + if video_description: video_description = clean_html(video_description) else: video_description = '' # closed captions @@ -1055,8 +1055,8 @@ class VimeoIE(InfoExtractor): video_thumbnail = config["video"]["thumbnail"] # Extract video description - video_description = get_element_by_id("description", webpage) - if video_description: video_description = clean_html(video_description.decode('utf8')) + video_description = get_element_by_id("description", webpage.decode('utf8')) + if video_description: video_description = clean_html(video_description) else: video_description = '' # Extract upload date diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index a19656000..0f903c64a 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -73,7 +73,7 @@ def htmlentity_transform(matchobj): # Unknown entity in name, return its literal representation return (u'&%s;' % entity) - +HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix class IDParser(HTMLParser.HTMLParser): """Modified HTMLParser that isolates a tag with the specified id""" def __init__(self, id): @@ -83,8 +83,17 @@ class IDParser(HTMLParser.HTMLParser): self.depth = {} self.html = None self.watch_startpos = False + self.error_count = 0 HTMLParser.HTMLParser.__init__(self) + def error(self, message): + print self.getpos() + if self.error_count > 10 or self.started: + raise HTMLParser.HTMLParseError(message, self.getpos()) + self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line + self.error_count += 1 + self.goahead(1) + def loads(self, html): self.html = html self.feed(html)