Do not override stdlib html parser 'locatestarttagend' regex (fixes #4081)

'<a href="foo" ><img src="bar" / ></a>' wouldn't be parsed right (the problem is '/ >', '/>' worked fine).
We need to change it in python 2.6 (for example the description of youtube videos wouldn't be extracted).
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-11-02 17:28:42 +01:00
parent ac35c26686
commit 4f195f55f0
1 changed files with 3 additions and 1 deletions

View File

@ -152,7 +152,9 @@ def xpath_text(node, xpath, name=None, fatal=False):
return n.text
compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
if sys.version_info < (2, 7):
compat_html_parser.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 BaseHTMLParser(compat_html_parser.HTMLParser):
def __init(self):
compat_html_parser.HTMLParser.__init__(self)