def feed_page(self, name, data):
if name == self.linkinfo:
print >>stderr, 'Loading: %r' % name
for line in data.split('\n'):
if line:
(name,strs) = eval(line)
self.dic[name] = strs
else:
try:
n = name.index('/')
base_href = 'http://'+name[n+1:]
if not self.linkinfo:
self.baseid = name[:n]
handler = HTMLLinkFinder(self, base_href, self)
parser = HTMLParser3(handler, charset=self.default_charset)
parser.feed(data)
parser.close()
if not self.acldb or self.acldb.allowed(name):
tree = parsestr(data, charset=self.default_charset, base_href=base_href)
n = self.analyzer.add_tree(name, tree)
print >>stderr, 'Added: %d: %s' % (n, name)
else:
print >>stderr, 'Skipped: %s' % name
except ValueError:
pass
return
def feed_page(self, name, data): self.feed_tree(name, parsestr(data, charset=self.default_charset)) return
