From: Philipp Hagemeister Date: Fri, 1 Feb 2013 16:29:50 +0000 (+0100) Subject: Work around buggy HTML Parser in Python < 2.7.3 (Closes #662) X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=3b024e17afcfe12f4ea55e9a200b9cbd61ec3f99;p=youtube-dl Work around buggy HTML Parser in Python < 2.7.3 (Closes #662) --- diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 532e8c782..e6ce028d6 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -280,6 +280,12 @@ class AttrParser(compat_html_parser.HTMLParser): lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] lines[-1] = lines[-1][:self.result[2][1]] return '\n'.join(lines).strip() +# Hack for https://github.com/rg3/youtube-dl/issues/662 +if sys.version_info < (2, 7, 3): + AttrParser.parse_endtag = (lambda self, i: + i + len("") + if self.rawdata[i:].startswith("") + else compat_html_parser.HTMLParser.parse_endtag(self, i)) def get_element_by_id(id, html): """Return the content of the tag with the specified ID in the passed HTML document"""