爬虫为何使用 requests 代理，依然被封堵？

def setProxiesConfig(): url = 'http://www.xicidaili.com/nn/' headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36' } web_data = requests.get(url, headers=headers) soup = BeautifulSoup(web_data.text, 'lxml') ips = soup.find_all('tr') ip_list = [] for i in range(1, len(ips)): ip_info = ips[i] tds = ip_info.find_all('td') ip_list.append(tds[1].text + ':' + tds[2].text) print(ip_list) return ip_list #获取随机 IP def get_random_ip(ip_list): proxy_list = [] for ip in ip_list: proxy_list.append('http://' + ip) proxy_ip = random.choice(proxy_list) proxies = {'http': proxy_ip} return proxies

获取列表后，随机取一个 IP{'http':'http://ip:9999'} 然后放到 get 中

headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36' } ipC=get_random_ip(ip_list) web_data = requests.get(URL, headers=headers,proxie= ,verify=False,timeout=10) soup = BeautifulSoup(web_data.text, 'lxml')

爬取了 46 个页面的时候还可以操作，但是之后就开始提示 timeout 了，就无论如何也不能爬取了，这是为啥？

11 replies 2019-02-18 18:44:03 +08:00