Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

Process <img> and <frame> tags. Don't bother skipping second href.

This commit is contained in:
Guido van Rossum 1997-02-01 05:16:08 +00:00
parent de99d310cc
commit 6133ec656e
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
Tools/webchecker/webchecker.py
View File

@ -564,11 +564,21 @@ class MyHTMLParser(sgmllib.SGMLParser):
sgmllib.SGMLParser.__init__ (self) sgmllib.SGMLParser.__init__ (self)
def start_a(self, attributes): def start_a(self, attributes):
self.link_attr(attributes, 'href')
def end_a(self): pass
def do_img(self, attributes):
self.link_attr(attributes, 'src', 'lowsrc')
def do_frame(self, attributes):
self.link_attr(attributes, 'src')
def link_attr(self, attributes, *args):
for name, value in attributes: for name, value in attributes:
if name == 'href': if name in args:
if value: value = string.strip(value) if value: value = string.strip(value)
if value: self.links[value] = None if value: self.links[value] = None
return # match only first href
def do_base(self, attributes): def do_base(self, attributes):
for name, value in attributes: for name, value in attributes:
@ -578,7 +588,6 @@ class MyHTMLParser(sgmllib.SGMLParser):
if verbose > 1: if verbose > 1:
print " Base", value print " Base", value
self.base = value self.base = value
return # match only first href
def getlinks(self): def getlinks(self):
return self.links.keys() return self.links.keys()