from fake_useragent import UserAgent
headers = {
        # 'User-Agent': UserAgent().random #常見瀏覽器的請求頭偽裝（如：火狐,谷歌）
        'User-Agent': UserAgent().Chrome #谷歌瀏覽器
    }

response = requests.get(url='http://www.ip3366.net/free/', headers=request_header())
        # text = response.text.encode('ISO-8859-1')
        # print(text.decode('gbk'))

	#使用xpath解析，提取出數(shù)據(jù)ip，端口
        html = etree.HTML(response.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

#構建代理ip
	proxy = ip + ':' + port
	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) #設置timeout，使響應等待1s
        response.close()
        if response.status_code == 200:
            print(proxy, '\033[31m可用\033[0m')
        else:
            print(proxy, '不可用')
    except:
        print(proxy,'請求異常')

import requests                         #導入模塊
from lxml import etree
from fake_useragent import UserAgent
#簡單的反爬，設置一個請求頭來偽裝成瀏覽器
def request_header():
    headers = {
        # 'User-Agent': UserAgent().random #常見瀏覽器的請求頭偽裝（如：火狐,谷歌）
        'User-Agent': UserAgent().Chrome #谷歌瀏覽器
    }
    return headers
'''
創(chuàng)建兩個列表用來存放代理ip
'''
all_ip_list = []  #用于存放從網(wǎng)站上抓取到的ip
usable_ip_list = [] #用于存放通過檢測ip后是否可以使用

#發(fā)送請求，獲得響應
def send_request():
    #爬取7頁，可自行修改
    for i in range(1,8): 
        print(f'正在抓取第{i}頁……')
        response = requests.get(url=f'http://www.ip3366.net/free/?page={i}', headers=request_header())
        text = response.text.encode('ISO-8859-1')
        # print(text.decode('gbk'))
        #使用xpath解析，提取出數(shù)據(jù)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)      #開始檢測獲取到的ip是否可以使用
    print('抓取完成！')
    print(f'抓取到的ip個數(shù)為：{len(all_ip_list)}')
    print(f'可以使用的ip個數(shù)為：{len(usable_ip_list)}')
    print('分別有：\n', usable_ip_list)
#檢測ip是否可以使用
def test_ip(proxy):
    #構建代理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) #設置timeout，使響應等待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,'請求異常')
if __name__ == '__main__':
    send_request()