#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys
import urllib ,urllib2
import re
def baidu(w):
url= "http://www.baidu.com/s?"
values = {
"w":w.encode('gbk','ignore')
}
data = urllib.urlencode(values)
newurl = url + data
response = urllib2.urlopen(newurl)
the_page = response.read().decode('gbk','ignore')
return the_page
def ana(data,mysite):
o = re.compile("href=\"(.+?)\"")
f = o.findall(data)
line = 1
for ff in f:
if not re.search("baidu",ff) and not re.search("^s\?",ff) and re.search("^http:\/\/",ff):
if re.search(mysite,ff):
print "* " ,line ,ff
else:
print line ,ff
line += 1
if __name__ == "__main__":
mysite = sys.argv[2]
data = baidu(sys.argv[1].decode('utf-8'))
ana(data,mysite)

python bd.py "vbs" "ruanchen.com"