1.技巧

打印的字标红

# \033[31m可用\033[0m
例如：
a = 1
print(a,'\033[31m变红\033[0m')

2.IP池 与 IP提取

ip池

# coding=gbk
# -*- coding:uft-8 -*-
# @Time: 2022/12/18
# @Author: 十架bgm
# @FileName: IP池12-18
import requests                         #导入模块
from lxml import etree
from faker import Factory
Fact =Factory.create()
ua = Fact.user_agent()
def request_header():
    headers = {
        'User-Agent': ua
    }
    return headers

'''
创建两个列表用来存放代理ip
'''
all_ip_list = []  #用于存放从网站上抓取到的ip
usable_ip_list = [] #用于存放通过检测ip后是否可以使用

#发送请求，获得响应
def send_request():
    #爬取7页，可自行修改
    for i in range(1,8):
        print(f'正在抓取第{i}页……')
        response = requests.get(url=f'http://www.ip3366.net/free/?page={i}', headers=request_header())
        # text = response.text.encode('ISO-8859-1')
        text = response.text
        # print(text.decode('gbk'))
        #使用xpath解析，提取出数据ip，端口
        html = etree.HTML(text)
        tr_list = html.xpath('/html/body/div[2]/div/div[2]/table/tbody/tr')
        for td in tr_list:
            ip_ = td.xpath('./td[1]/text()')[0] #ip
            port_ = td.xpath('./td[2]/text()')[0]  #端口
            proxy = ip_ + ':' + port_   #115.218.5.5:9000
            all_ip_list.append(proxy)
            test_ip(proxy)      #开始检测获取到的ip是否可以使用
    print('抓取完成！')
    print(f'抓取到的ip个数为：{len(all_ip_list)}')
    print(f'可以使用的ip个数为：{len(usable_ip_list)}')
    print('分别有：\n', usable_ip_list)
#检测ip是否可以使用
def test_ip(proxy):
    #构建代理ip
    proxies = {
        "http": "http://" + proxy,
        "https": "http://" + proxy,
        # "http": proxy,
        # "https": proxy,
    }
    try:
        response = requests.get(url='https://www.baidu.com/',headers=request_header(),proxies=proxies,timeout=1) #设置timeout，使响应等待1s
        response.close()
        if response.status_code == 200:
            usable_ip_list.append(proxy)
            print(proxy, '\033[31m可用\033[0m')
        else:
            print(proxy, '不可用')
    except:
        print(proxy,'请求异常')

if __name__ == '__main__':
    send_request()
    for usable_ip in usable_ip_list:
        with open('usableIP.csv', 'a', encoding='utf-8') as f:
            f.write(usable_ip + '\n')

ip提取(从csv文件提取)

# coding=gbk
# -*- coding:uft-8 -*-
# @Time: 2022/12/19
# @Author: 十架bgm
# @FileName: 从csv文件提取ip
import random
import pandas as pd
import requests
from faker import Factory
Fact =Factory.create()
ua = Fact.user_agent()
# data = pd.read_csv('./爬虫练习/自动获取海量ip/usableIP.csv')
data = pd.read_csv('./usableIP.csv')   # 读取csv文件
# print(data)
ips = data['IP']     # 只提取'IP'这列的数据
ip_list = []
for i in ips:
    ip_list.append(i)
print(f'ip池：{ip_list}')
print(f'ip数量为:{len(ip_list)}')
ip = ip_list[random.randint(0,len(ip_list)-1)]  # 随机提取
print(f'随机抽取的id为:{ip}')

headers = {
        'User-Agent': ua
    }
proxies = {
        "http": ip,
        "https": ip,
        # "http": proxy,
        # "https": proxy,
    }

response = requests.get(url='https://api.ipify.org/?format=json',headers=headers,proxies=proxies,timeout=1)
print(f'访问网站“https://api.ipify.org/?format=json”的ip是：{response.text}')