分享一个获取代理ip的python函数
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
|
#coding:utf-8
from
bs4
import
BeautifulSoup
import
requests
import
random
def
getproxyip():
headers
=
{
'Accept'
:
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
,
'Accept-Encoding'
:
'gzip,deflate,sdch'
,
'Host'
:
'www.ip-adress.com'
,
'User-Agent'
:
'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:24.0) Gecko/20100101 Firefox/24.0'
}
proxy_req
=
requests.get(proxy_url,headers
=
headers)
proxy_soup
=
BeautifulSoup(proxy_req.text)
proxy_ip
=
proxy_soup.find_all(
'tr'
,{
'class'
:
'yellow'
})
return
proxy_ip[random.randrange(
0
,
4
)].td.text
|
#/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1.186.200.211:8080@HTTP#印度
2.135.238.92:9090@HTTP#哈萨克斯坦
2.181.177.7:8080@HTTP#伊朗
2.183.155.2:8082@HTTP#伊朗
本文提供了一个使用Python编写的函数,用于从特定网站自动获取代理IP列表。
2173

被折叠的 条评论
为什么被折叠?



