scrapy IP代理池

免费的IP代理池采用的是西刺的高匿IP代理：http://www.xicidaili.com/nn/

1.设置代理IP的方法：

   request.meta["proxy"] = “http://221.238.67.231:8081"

2.爬取西刺网站的IP地址保存到MySql，并取出可用的ip：

import requests
from  scrapy.selector import Selector
import MySQLdb

conn = MySQLdb.connect(host="127.0.0.1",user="root",passwd="root",db="表名",charset="utf8")
cursor =conn.cursor()

def crawl_ips():
    #爬取西刺的免费up代理
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"}
    for i in range(1057):              #设置爬取页数
        re = requests.get("http://www.xicidaili.com/nn/{0}".format(i),headers=headers)

    selector =Selector(text=re.text)
    all_trs = selector.css("#ip_list tr")

    ip_list = []
    for tr in all_trs[1:]:
        speed_str = tr.css(".bar::attr(title)").extract()[0]
        if speed_str:
            speed = float(speed_str.split("秒")[0])
        all_texts = tr.css("td::text").extract()
        ip = all_texts[0]
        port = all_texts[1]
        proxy_type = all_texts[5]
        if proxy_type !="HTTP" and proxy_type !="HTTPS":
            proxy_type =all_texts[4]

        ip_list.append((ip, port, speed,proxy_type ))

        for ip_info in ip_list:
            cursor.execute(
                "insert ignore into proxy_ip(ip, port, speed, proxy_type) VALUES('{0}', '{1}', {2}, '{3}')".format(
                    ip_info[0], ip_info[1], ip_info[2],ip_info[3]
                )
            )

            conn.commit()


class GetIP(object):
    def delete_ip(self, ip):
        #从数据库中删除无效的ip
        delete_sql = """
            delete from proxy_ip where ip='{0}'
        """.format(ip)
        cursor.execute(delete_sql)
        conn.commit()
        return True

    def judge_ip(self, ip, port):
        #判断ip是否可用
        http_url = "http://www.baidu.com"
        proxy_url = "http://{0}:{1}".format(ip, port)
        try:
            proxy_dict = {
                "http":proxy_url,
            }
            response = requests.get(http_url, proxies=proxy_dict)
        except Exception as e:
            print ("invalid ip and port")
            self.delete_ip(ip)
            return False
        else:
            code = response.status_code
            if code >= 200 and code < 300:
                print ("effective ip")
                return True
            else:
                print  ("invalid ip and port")
                self.delete_ip(ip)
                return False


    def get_random_ip(self):
        #从数据库中随机获取一个可用的ip
        random_sql = """
              SELECT ip, port FROM proxy_ip
            ORDER BY RAND()
            LIMIT 1
            """
        result = cursor.execute(random_sql)
        for ip_info in cursor.fetchall():
            ip = ip_info[0]
            port = ip_info[1]

            judge_re = self.judge_ip(ip, port)
            if judge_re:
                return "http://{0}:{1}".format(ip, port)
            else:
                return self.get_random_ip()

# print(crawl_ips())       #用以调用crawl_ips
if __name__ == "__main__":
    get_ip = GetIP()
    get_ip.get_random_ip()

3.在middleware中调用代理ip：

class RandomProxyMiddleware(object):
    #动态设置ip代理
    def process_request(self, request, spider):
        get_ip = GetIP()
        request.meta["proxy"] = get_ip.get_random_ip()

scrapy官方ip代理包：scrapy-proxies

scrapy IP代理池

浏览过的版块