爬虫代码报错:Remote end closed connection without response

原因分析
1.UA被识别为爬虫,封了,解决–> 设置cookie池

import random

def cookie_list():
    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",
         ]
    return  random.choice(USER_AGENTS)

# 1.创建分类列表的request对象
def create_request(home, page):  
    # headers中其他都可以不要Cookie一定要换成自己登陆后的,就可以跳过登陆限制'的反扒操作
    headers_list = [
        { "Cookie": "PHPSESSID=qi9ranhi2lij71djb02u7o91v0; __gads=ID=e4fb5dbf213abcd9-22edd6cecbca00be:T=1629049647:RT=1629049647:S=ALNI_Mbb0RAV9Wb9qckiP3Jq97_qLKv4dg; Hm_lvt_c6cce8b84b577676ccc134fddd949561=1632486881; wordpress_logged_in_062e3588f38b2a80e98972c30cba7a30=sdfsd%7C1633236765%7C27mpYUFLu0mdTO5HqHUXszYYEMZPP6ZbWA90au1eQZh%7C962095abecf06c0b91fffce27119e30c0c0fabd43bba901c250c07e8602ebbb1; Hm_lpvt_c6cce8b84b577676ccc134fddd949561=1633229536", "User-Agent": cookie_list()},
        { "Cookie": "PHPSESSID=qi9ranhi2lij71djb02u7o91v0; __gads=ID=e4fb5dbf213abcd9-22edd6cecbca00be:T=1629049647:RT=1629049647:S=ALNI_Mbb0RAV9Wb9qckiP3Jq97_qLKv4dg; Hm_lvt_c6cce8b84b577676ccc134fddd949561=1632486881; wordpress_logged_in_062e3588f38b2a80e98972c30cba7a30=sdfsd%7C1633236765%7C27mpYUFLu0mdTO5HqHUXszYYEMZPP6ZbWA90au1eQZh%7C962095abecf06c0b91fffce27119e30c0c0fabd43bba901c250c07e8602ebbb1; Hm_lpvt_c6cce8b84b577676ccc134fddd949561=1633173215", "User-Agent": cookie_list()},
        { "Cookie": "PHPSESSID=qi9ranhi2lij71djb02u7o91v0; __gads=ID=e4fb5dbf213abcd9-22edd6cecbca00be:T=1629049647:RT=1629049647:S=ALNI_Mbb0RAV9Wb9qckiP3Jq97_qLKv4dg; Hm_lvt_c6cce8b84b577676ccc134fddd949561=1632486881; wordpress_logged_in_062e3588f38b2a80e98972c30cba7a30=sdfsd%7C1633236765%7C27mpYUFLu0mdTO5HqHUXszYYEMZPP6ZbWA90au1eQZh%7C962095abecf06c0b91fffce27119e30c0c0fabd43bba901c250c07e8602ebbb1; Hm_lpvt_c6cce8b84b577676ccc134fddd949561=1633229023", "User-Agent": cookie_list()}
        ]
    headers = random.choice(headers_list)
    # url地址 "http://250a.com/zonghe/page/1"
    url = home + page

    # 定义request对象
    request = urllib.request.Request(url = url, headers= headers)

    return request 

2.ip被识别爬虫,封了,还没遇到,遇到再说
3.代码过一会重新运行下,还可以再爬,不过还会遇到这个问题

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 2
    评论
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

坏孩子充电自习室

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值