爬虫练习P190

获取代理IP地址

import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')
    return html

def get_img(html):
    # 第一个正则已经不行了
    # p = r'(([0-1]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])\.){3}([0-1]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])'
    # p = r'\d{0,3}\.\d{0,3}\.\d{0,3}\.\d{0,3}'
    p = r'(?:(?:[0-1]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])\.){3}(?:[0-1]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])'
    imglist = re.findall(p, html)
    for each in imglist:
        print(each)

if __name__ == '__main__':
    # 代理地址改一下，书上的地址http://cn-proxy.com已经挂了
    url = "http://www.data5u.com/"
    get_img(open_url(url))