我就废话不多说啦，大家还是直接看代码吧！

import requests,randomfrom lxml import etreeimport threadingimport timeangents = [ "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",]def get_all_xici_urls(start_num,stop_num): xici_urls = [] for num in range(start_num,len(stop_num)+1): xici_http_url = 'http:///" user_agent = self.get_user_agent() headers = {'User-Agent': user_agent} if choice == 'http': proxies = { "http": "http://"+ip_port, } elif choice == 'https': proxies = { "https": "https://" + ip_port, } try: thisIP = "".join(ip_port.split(":")[0:1]) res = requests.get(tar_url, proxies=proxies, headers=headers, timeout=8) proxyIP = res.text.strip() if proxyIP == thisIP: return proxyIP else: return False except: return False def store_txt(self, choice='http', first=1, end=2): """ 将测试通过的ip_port保存为txt文件 :param choice: :param first: :param end: :return: """ user_agent = self.get_user_agent() headers = {'User-Agent': user_agent} ip_list = self.get_proxy(headers=headers, choice=choice, first=first, end=end) with codecs.open("Http_Agent.txt", 'a', 'utf-8') as file: for ip_port in ip_list: ip_port = self.test_proxy(ip_port, choice=choice) print(ip_port) if ip_port: file.write('\'' + ip_port + "\'\n")

以上这篇Python使用requests xpath 并开启多线程爬取西刺代理ip实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。