|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- import urllib.request
- import os
- import re
- import time
- def url_open(url):
- a =urllib.request.Request(url)
- a.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6823.400 QQBrowser/10.3.3117.400')
- req = urllib.request.urlopen(a)
- html = req.read().decode('utf-8')
- return html
- def zhuyao(html):
- p = r'(?:(?:[01]\d\d|2[0-4]\d|25[0-5]|[0-9]\d|[0-9])\.){3}(?:[01]\d\d|2[0-4]\d|25[0-5]|[0-9]\d|[0-9])'
- ipopen = re.findall(p,html)
-
-
- with open('文件ip代理','a') as f:
- for each in ipopen:
- each = each+'\n'
- f.write(each)
-
-
-
- if __name__=='__main__':
- cishu = 0
- os.mkdir('ip代理')
- os.chdir('ip代理')
- for each in range(10):
- cishu+=1
- url = 'https://www.kuaidaili.com/free/intr/'+str(cishu)+'/'
- zhuyao(url_open(url))
- time.sleep(5)
复制代码 |
|