一些代理ip有需要的可以直接用

Chysial

import urllib.request
import re
import os
import random
def url_open(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/80.0.3987.132 Safari/537.36")
    proxies = ["125.108.123.66:9000","183.166.103.45:9999","115.195.84.31:8118","61.178.149.237:59042"]
    proxy = random.choice(proxies)
    proxy_support = urllib.request.ProxyHandler({'http':proxy})
    opener = urllib.request.build_opener(proxy_support)
    urllib.request.install_opener(opener)
    response = urllib.request.urlopen(req)
    html = response.read().decode("utf-8")
    return html
def split_addrs_port(temp_str):
    [a,b] = temp_str.split(">",2)
    [c,d] =b.split("<",2)
    return c
    
def get_addrs_port(url):
    html = url_open(url)
    compile_ip = re.compile(r'("IP">(([0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}([0-1]?\d?\d|2[0-4]\d|25[0-5])<)')
    compile_port = re.compile(r""PORT">\d{0,5}<")
    url_addrs_temp = compile_ip.findall(html)
    url_port_temp= compile_port.findall(html)
    list_addrs_port = []
    for i in range(len(url_addrs_temp)):
        url_addrs = split_addrs_port(str(url_addrs_temp[i][0]))
        url_port = split_addrs_port(str(url_port_temp[i]))
        url_addrs_port = url_addrs + ":" + url_port
        list_addrs_port.append(url_addrs_port)
    return list_addrs_port

def save_addrs_port(addrs_port):
    with open("ip_port.txt","a") as f:
        for each in addrs_port:
            f.write(str(each) + "\n")
    

def download_url(folder = "proxy_support", pages = "10"):
    os.chdir("C:\\Users\\Chysial\\Desktop")
    '''os.mkdir(folder)'''
    os.chdir(folder)


    for i in range(int(pages)):
        page_num =i+1
        url = "https://www.kuaidaili.com/free/inha/"
        pages_url = url +str(page_num)
        url_addrs_port = get_addrs_port(pages_url)
        save_addrs_port(url_addrs_port)
        print(url_addrs_port)

if __name__ == "__main__":
    download_url()

    

Chysial

修改版的，可以直接用，不会出现错误的ip爬取

import urllib.request
import re
import os
import random
import urllib.error

def url_open(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/80.0.3987.132 Safari/537.36")
    proxies = ["125.108.123.66:9000","183.166.103.45:9999","115.195.84.31:8118","61.178.149.237:59042"]
    proxy = random.choice(proxies)
    proxy_support = urllib.request.ProxyHandler({'http':proxy})
    opener = urllib.request.build_opener(proxy_support)
    urllib.request.install_opener(opener)
    response = urllib.request.urlopen(req)
    html = response.read().decode("utf-8")
    return html

    
def split_addrs_port(temp_str):
    [a,b] = temp_str.split(">",2)
    [c,d] =b.split("<",2)
    return c
    
def get_addrs_port(url):
    html = url_open(url)
    compile_ip = re.compile(r'("IP">(([0-1]?\d?\d|2[0-4]\d|25[0-5])\.){3}([0-1]?\d?\d|2[0-4]\d|25[0-5])<)')
    compile_port = re.compile(r""PORT">\d{0,5}<")
    url_addrs_temp = compile_ip.findall(html)
    url_port_temp= compile_port.findall(html)
    list_addrs_port = []
    for i in range(len(url_addrs_temp)):
        url_addrs = split_addrs_port(str(url_addrs_temp[i][0]))
        url_port = split_addrs_port(str(url_port_temp[i]))
        url_addrs_port = url_addrs + ":" + url_port
        list_addrs_port.append(url_addrs_port)
    return list_addrs_port

def save_addrs_port(addrs_port):
    with open("ip_port.txt","a") as f:
        for each in addrs_port:
            f.write(str(each) + "\n")
    

def download_url(folder = "proxy_support3", pages = "10"):
    os.chdir("C:\\Users\\Chysial\\Desktop")
    os.mkdir(folder)
    os.chdir(folder)
    url = "https://www.kuaidaili.com/free/inha/"
    url_list = []
    for i in range(int(pages)):
        page_num =i+1
        pages_url = url + str(page_num)
        try:
            url_addrs_port = get_addrs_port(pages_url)
            save_addrs_port(url_addrs_port)
            print(url_addrs_port)
        except urllib.error.HTTPError as e:
            print(e.code)
            continue

       

if __name__ == "__main__":
    download_url()