Форум сайта python.su
Есть код для парсинга прокси с gatherproxy.com:
import re import requests from fake_useragent import UserAgent ua = UserAgent() headers = {'User-Agent': ua.random} class GatherProxy(object): url = 'http://gatherproxy.com/proxylist' pre1 = re.compile(r'gp\.insertPrx\({.*?}\)') pre2 = re.compile(r'(?<=":").+?(?=",")') def get_elite_proxy(self, pages=4, uptime=25): proxies = set() for i in range(1, pages + 1): params = {"Type": "elite", "PageIdx": str(i), "Uptime": str(uptime)} r = requests.post(self.url + "/anonymity/?t=Elite", params=params, headers=headers) r = r.text for td in self.pre1.findall(r): try: tmp = self.pre2.findall(str(td)) proxies.add(tmp[1] + ":" + str(int(tmp[3], 16))) except: pass return proxies P = GatherProxy() prox = P.get_elite_proxy()
Отредактировано hubble (Май 13, 2018 21:21:09)
Офлайн