Python采集网站ip代理

proxies_dict = {
    "http": "http://" + ip:端口,
    "https": "http://" + ip:端口,
}

# 导入数据请求模块
import requests  # 数据请求模块 第三方模块 pip install requests
# 导入 正则表达式模块
import re  # 内置模块
# 导入数据解析模块
import parsel  # 数据解析模块 第三方模块 pip install parsel  >>> 这个是scrapy框架核心组件

url = f'https://www.kuaidaili.com/free/inha/{page}/'  # 确定请求url地址
# 用requests模块里面get 方法 对于url地址发送请求, 最后用response变量接收返回数据
response = requests.get(url)

print(response.text)

ip_list = re.findall('<td data-title="IP">(.*?)</td>', response.text, re.S)
port_list = re.findall('<td data-title="PORT">(.*?)</td>', response.text, re.S)
print(ip_list)
print(port_list)

# #list > table > tbody > tr > td:nth-child(1)
# //*[@id="list"]/table/tbody/tr/td[1]
selector = parsel.Selector(response.text) # 把html 字符串数据转成 selector 对象
ip_list = selector.css('#list tbody tr td:nth-child(1)::text').getall()
port_list = selector.css('#list tbody tr td:nth-child(2)::text').getall()
print(ip_list)
print(port_list)

selector = parsel.Selector(response.text) # 把html 字符串数据转成 selector 对象
ip_list = selector.xpath('//*[@id="list"]/table/tbody/tr/td[1]/text()').getall()
port_list = selector.xpath('//*[@id="list"]/table/tbody/tr/td[2]/text()').getall()

for ip, port in zip(ip_list, port_list):
    # print(ip, port)
    proxy = ip + ':' + port
    proxies_dict = {
        "http": "http://" + proxy,
        "https": "http://" + proxy,
    }
    print(proxies_dict)

try:
    response = requests.get(url=url, proxies=proxies_dict, timeout=1)
    if response.status_code == 200:
        print('当前代理IP: ', proxies_dict,  '可以使用')
        lis_1.append(proxies_dict)
except:
    print('当前代理IP: ', proxies_dict,  '请求超时, 检测不合格')


print('获取的代理IP数量: ', len(lis))
print('获取可用的IP代理数量: ', len(lis_1))
print('获取可用的IP代理: ', lis_1)