From: Guido van Rossum <guido@python.org>
Date: Sat, 1 Feb 1997 05:16:08 +0000 (+0000)
Subject: Process <img> and <frame> tags. Don't bother skipping second href.
X-Git-Tag: v1.5a1~393
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=6133ec656e39496a95b92f9677f17bdc8f703dd0;p=python

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

diff --git a/Tools/webchecker/webchecker.py b/Tools/webchecker/webchecker.py
index 9e676caf01..69e462a94c 100755
--- a/Tools/webchecker/webchecker.py
+++ b/Tools/webchecker/webchecker.py
@@ -564,11 +564,21 @@ class MyHTMLParser(sgmllib.SGMLParser):
 	sgmllib.SGMLParser.__init__ (self)
 
     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:
-	    if name == 'href':
+	    if name in args:
 		if value: value = string.strip(value)
 		if value: self.links[value] = None
-		return	# match only first href
 
     def do_base(self, attributes):
 	for name, value in attributes:
@@ -578,7 +588,6 @@ class MyHTMLParser(sgmllib.SGMLParser):
 		    if verbose > 1:
 			print "  Base", value
 		    self.base = value
-		return	# match only first href
 
     def getlinks(self):
 	return self.links.keys()