记录一段用HTMLParser解析html的python代码:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
data = urllib.urlopen('http://10.85.40.153').read()
 
#data = response.read()
print data
 
class parseHtml(HTMLParser.HTMLParser):
    def handle_starttag(self, tag, attrs):
        print tag
        if 'input'.__contains__(tag):
            for name, value in attrs:
                print 'name=%s,value=%s' % (name, value)
                if value.__contains__('Home'):
                    print value
                    print self.get_starttag_text()
 
 
 
parse = parseHtml()
parse.feed(data)