import urllib.request
import re
def open_url(url):
req=urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6')
page=urllib.request.urlopen(req)
html=page.read().decode('utf-8')
return html
def get_img(html):
p=r'(?:(?:[01]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[01]?\d?\d|2[0-4]\d|25[0-5])'#?:正则表达式的扩展
iplist=re.findall(p,html)
for each in iplist:
print(each)
if __name__=='__main__':
url="http://www.xicidaili.com/"#代理地址框
get_img(open_url(url))
爬虫学习:一个ip地址下载器
最新推荐文章于 2023-08-10 14:45:27 发布