Work around buggy HTML Parser in Python < 2.7.3 (Closes #662)

This commit is contained in:
Philipp Hagemeister 2013-02-01 17:29:50 +01:00
parent ec71c13ab8
commit 3b024e17af
1 changed files with 6 additions and 0 deletions

View File

@ -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("</scr'+'ipt>")
if self.rawdata[i:].startswith("</scr'+'ipt>")
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"""