分享一个获取代理ip的python函数

python编写的自动获取代理IP列表的爬虫

#/usr/local env python
#coding utf-8
import os
import urllib
from bs4 import BeautifulSoup

def log():
    f=open("f:\daili.txt",‘a‘)
    f.write(ip)
    f.close()

def fenxi():
    page = urllib.urlopen(url)
    data = page.read()
    soup=BeautifulSoup(data)
    #print soup
    list=soup.find_all(‘span‘)
    for i in list:
        #print i.get_text()
        global ip
        ip= i.get_text()
        s="\n".join(ip.split(‘#‘))
        print s
        log()  
for i in range(1,10):
    if i==1:
        url = ‘http://www.youdaili.cn/Daili/http/556.html‘
        print url
        fenxi()
    else:
        url = ‘http://www.youdaili.cn/Daili/http/556_‘+str(i)+‘.html‘
        print url
        fenxi()
        
       运行结果：
||||||||IP知识库最新代理IPwww.Youdaili.Cn07-09免费代理国内外http代理ip地址1.186.200.211:[email protected]#印度

2.135.238.92:[email protected]#哈萨克斯坦

2.181.177.7:[email protected]#伊朗

2.183.155.2:[email protected]#伊朗