爬虫如何获取免费代理IP（二）

news2024/11/15 13:28:29

89ip代理爬取代码实现

一、代码实现

import requests
import time
import random
from fake_useragent import UserAgent
from lxml import etree
import os
import csv

"""
89ip代理爬取
"""


class IPSipder(object):

    def __init__(self):
        self.url = "https://www.89ip.cn/index_{}.html"
        self.headers = {'User-Agent': UserAgent().random}
        # 统计有效ip个数
        self.count = 0

    # 获取ip表格行
    def get_html(self, url):
        html = requests.get(url=url, headers=self.headers).text
        parser_html = etree.HTML(html)
        tr_list = parser_html.xpath('//tbody/tr')
        return tr_list

    # 提取ip和port
    def parser_html(self, tr_list):
        proxies_list = []
        for tr in tr_list:
            # 获取ip
            ip = tr.xpath('./td/text()')[0].strip()
            # 获取port
            port = tr.xpath('./td/text()')[1].strip()
            # 将ip和port封装到字典中，便于proxies代理调用
            ip_dict = {
                "http": "http://" + ip + ":" + port,
                "https": "https://" + ip + ":" + port
            }
            # 将获取的所有ip和port放入列表
            proxies_list.append(ip_dict)

        return proxies_list

        # 保存有效ip到csv文件，如不要保存，可用在run方法中将其注释掉即可

    def save_ip(self, proxy, save_filename):
        try:
            if proxy:
                # 设置将保持的文件放到桌面
                save_path = "c:/Users/" + os.getlogin() + "/Desktop/"
                save_file = save_path + save_filename
                print('保存位置：', save_file + '.csv')
                with open(save_file + ".csv", 'a+', encoding='utf-8') as f:
                    fieldnames = ['http', 'https']
                    writer = csv.DictWriter(f, fieldnames=fieldnames)
                    writer.writerows(proxy)
        except Exception as e:
            print(e.args)

    # 检查哪些IP是可用的
    def check_ip(self, proxies_list):
        use_proxy = []
        for ip in proxies_list:
            try:
                response = requests.get(url="http://httpbin.org/", headers=self.headers, proxies=ip, timeout=3)
                # 使用百度一直失败，不知何原因
                # response = requests.get(url="https://www.baidu.com/", headers=self.headers, proxies=ip, timeout=3)
                # 判断哪些ip可用
                if response.status_code == 200:
                    # 将可用IP封装到列表，共后期使用或保存
                    use_proxy.append(ip)
                    self.count += 1
                    print('当前检测ip', ip, '检测可用')
            except Exception as e:
                # print(e.args)
                print('当前检测ip', ip, '请求超时，检测不合格')
            # else:
            #     print('当前检测ip', ip, '检测可用')
        return use_proxy

    def run(self):
        begin = int(input("请输入要抓取的开始页："))
        end = int(input("请输入要抓取的终止页："))
        filename = input("请输入保存文件名称：")
        for page in range(begin, end + 1):
            print(f"#################抓取第{page}页################################")
            # 重构url
            url = self.url.format(page)
            # 解析出所有的ip行
            parser_html = self.get_html(url)
            # 获取所有的ip代理
            proxies_list = self.parser_html(parser_html)
            # 筛选可用的ip
            proxy_id = self.check_ip(proxies_list)
            # 将可用的IP代理存入文件中:如若不想保存到文件中，将下面这行代码注销即可
            self.save_ip(proxy_id, filename)
        # 随机休眠2~3秒
        time.sleep(random.randint(2, 3))


if __name__ == "__main__":
    spider = IPSipder()
    # 执行
    spider.run()
    print(f'共统计到有效ip' + str(spider.count) + "个！")

二、代码运行

请输入要抓取的开始页：2
请输入要抓取的终止页：2
请输入保存文件名称：proxy-ip
#################抓取第2页################################
当前检测ip {'http': 'http://139.196.151.191:9999', 'https': 'https://139.196.151.191:9999'} 检测可用
当前检测ip {'http': 'http://114.102.45.39:8089', 'https': 'https://114.102.45.39:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://114.231.46.231:8089', 'https': 'https://114.231.46.231:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://124.71.157.181:8020', 'https': 'https://124.71.157.181:8020'} 检测可用
当前检测ip {'http': 'http://121.40.137.141:80', 'https': 'https://121.40.137.141:80'} 请求超时，检测不合格
当前检测ip {'http': 'http://117.69.232.45:8089', 'https': 'https://117.69.232.45:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://114.102.45.89:8089', 'https': 'https://114.102.45.89:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://115.29.148.215:8999', 'https': 'https://115.29.148.215:8999'} 检测可用
当前检测ip {'http': 'http://120.46.197.14:8083', 'https': 'https://120.46.197.14:8083'} 检测可用
当前检测ip {'http': 'http://113.223.215.128:8089', 'https': 'https://113.223.215.128:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://112.124.2.212:20000', 'https': 'https://112.124.2.212:20000'} 检测可用
当前检测ip {'http': 'http://114.102.47.164:8089', 'https': 'https://114.102.47.164:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://117.69.154.91:41122', 'https': 'https://117.69.154.91:41122'} 请求超时，检测不合格
当前检测ip {'http': 'http://123.182.59.167:8089', 'https': 'https://123.182.59.167:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://223.215.176.74:8089', 'https': 'https://223.215.176.74:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://114.231.105.68:8089', 'https': 'https://114.231.105.68:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://121.43.34.143:80', 'https': 'https://121.43.34.143:80'} 请求超时，检测不合格
当前检测ip {'http': 'http://121.40.109.183:80', 'https': 'https://121.40.109.183:80'} 请求超时，检测不合格
当前检测ip {'http': 'http://116.63.130.30:7890', 'https': 'https://116.63.130.30:7890'} 请求超时，检测不合格
当前检测ip {'http': 'http://114.102.44.113:8089', 'https': 'https://114.102.44.113:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://116.63.130.30:443', 'https': 'https://116.63.130.30:443'} 请求超时，检测不合格
当前检测ip {'http': 'http://114.231.46.160:8089', 'https': 'https://114.231.46.160:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://183.164.243.29:8089', 'https': 'https://183.164.243.29:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://114.102.44.137:8089', 'https': 'https://114.102.44.137:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://117.57.93.63:8089', 'https': 'https://117.57.93.63:8089'} 请求超时，检测不合格
当前检测ip {'http': 'http://159.226.227.90:80', 'https': 'https://159.226.227.90:80'} 请求超时，检测不合格
当前检测ip {'http': 'http://159.226.227.99:80', 'https': 'https://159.226.227.99:80'} 请求超时，检测不合格
当前检测ip {'http': 'http://183.164.243.44:8089', 'https': 'https://183.164.243.44:8089'} 请求超时，检测不合格
保存位置： c:/Users/qwy/Desktop/proxy-ip.csv
共统计到有效ip5个！