2017-4-30爬取代理IP并验证

之前有一次被豆瓣封IP了,就想着自己构建一些IP加UA.今天参考了这篇文章爬虫（2）--- 构建简单代理IP池先简单的爬取了一些免费代理IP并验证了下可用性.

选择的是西刺免费代理IP

西刺代理.png

• 分析页面写一个抓取地址和端口的re

pattern = '(\d+\.\d+\.\d+\.\d+)\s*(\d+)'

把IP格式整理好写进列表

re_list = re.findall(pattern, html)
    ip_list = []
    for ip in re_list:
        ip = ip[0] + ':' + ip[1]
        ip_list.append(ip)
    return ip_list

• 逐个验证这些IP的可用性

proxies = {
        "http": ip,
    }
    try:
        res = requests.get(tar_url, proxies=proxies, headers=headers, timeout=5)
        if res.status_code == 200:
            tmp_proxies.append(ip)
            return ip
        else:
            res.raise_for_status()  # 如果响应状态码不是200,主动抛出异常
    except requests.RequestException as e:
        print("验证代理IP" + ip + "时发生如下错误 :")
        print(e)

刚开始我也是选的baidu.com来验证是否可用的,程序跑完50个IP竟然全部作为可用IP返回,抱着这么好的事情怎么会发生在我身上的心态,换了一个url重新测一遍,有15个能用,通过率大概30%,这才对嘛.

• 最后写个函数封装一下,全部代码如下.很简陋,待日后完善,准备的思路是一个IP固定搭配一个UA,这样才像一个用户嘛.

#! usr/bin/env python3
# -*- coding:utf-8 -*-


import requests
import re
import random


url = 'http://www.xicidaili.com/nn'
headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.3'
                         '6 (KHTML, like Gecko) Ubuntu Chromium/56.0.2924.7'
                         '6 Chrome/56.0.2924.76 Safari/537.36'}


def get_user_agent():
    '''
    功能: 随机获取UA
    :return: 返回一个随机UA
    '''
    user_agents=[
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
        "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
        "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
        "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
        "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
        "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
        "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
        "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
        "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
        "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
        "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
        "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
    ]
    user_agent = random.choice(user_agents)
    return user_agent


def get_proxies():
    '''
    功能: 爬取西刺高匿IP
    :return: IP列表
    '''
    html = requests.get(url=url, headers=headers).text
    pattern = '(\d+\.\d+\.\d+\.\d+)\s*(\d+)'
    re_list = re.findall(pattern, html)
    ip_list = []
    for ip in re_list:
        ip = ip[0] + ':' + ip[1]
        ip_list.append(ip)
    return ip_list

def test_proxy(ip):
    '''
    功能: 利用百度逐个验证IP的有效性
    :param ip: 当前被验证的IP
    :return: 
    '''
    tar_url = "http://www.tjcu.edu.cn/"
    user_agent = get_user_agent()
    headers = {
        'User-Agent': user_agent
    }
    proxies = {
        "http": ip,
    }
    try:
        res = requests.get(tar_url, proxies=proxies, headers=headers, timeout=5)
        if res.status_code == 200:
            tmp_proxies.append(ip)
            return ip
        else:
            res.raise_for_status()  # 如果响应状态码不是200,主动抛出异常
    except requests.RequestException as e:
        print("验证代理IP" + ip + "时发生如下错误 :")
        print(e)


if __name__ == '__main__':
    init_proxies = get_proxies()  # 获取原始代理IP
    tmp_proxies = []
    for i in init_proxies:
        tmp_proxy = test_proxy(i)  # 逐个验证
    print(tmp_proxies)