Posted in Python onSeptember 17, 2009
源码如下 :保存成utf-8 bd.py 文件
#!/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)
用法 python bd.py "关键字" 我的域名部分 :
例:
python bd.py "vbs" "3water.com"
phpsir 开发 一个检测百度关键字网站排名的python 程序
声明:登载此文出于传递更多信息之目的,并不意味着赞同其观点或证实其描述。
Reply on: @reply_date@
@reply_contents@