scrapy實現ip代理池

首先需要在ip代理的網站爬取有用的ip，保存到數據庫中

import requests
from scrapy.selector import Selector
import pymysql

conn = pymysql.connect(host = '127.0.0.1', user = 'root' ,passwd = 'root',db = 'mysql18_text',charset = 'utf8')
cursor = conn.cursor()

def crawl_ips():
    #爬取xici的免費ip代理
    agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:62.0) Gecko/20100101 Firefox/62.0'
    header = {
        'User-Agent':agent
    }

    for i in range(1,3458):
        reas = requests.get('http://www.xicidaili.com/nn/',headers = header)
        Selectora = Selector(reas)
        all_trs = Selectora.xpath('//table[@id="ip_list"]/tr')
        ip_list = []
        for tr in all_trs[1:]:
            spend_str = tr.xpath('./td/div[@class="bar"]/@title').extract()[0] ##提取速度
            if spend_str:
                speed = float(spend_str.split('秒')[0])
                all_text = tr.xpath('./td/text()').extract()
                ip = all_text[0]
                port = all_text[1]
                proxy_type = all_text[5]
                ip_list.append((ip,port,speed,proxy_type))
        for ip_info in ip_list:
            cursor.execute(
                """insert project_ip(ip,port,speed,proxy_type) VALUES('{0}','{1}','{2}','HTTP')""".format(
                    ip_info[0],ip_info[1],ip_info[2]
                )
            )
            conn.commit()
        print(ip_list)
        
        
crawl_ips()

conn.close()
cursor.close()

隨機在數據庫中獲取一個ip的代碼

class GetIP(object):
    
    def delete_ip(self,ip):
        #從數據庫中刪除無效的ip
        delete_sql = """
            delete from project_ip where ip='{0}'
        """.format(ip)
        cursor.execute(delete_sql)
        conn.commit()
        return True
    
    
    def judge_ip(self,ip,port):
        #判斷一個ip是否可用
        http_url = 'http://www.baidu.com'
        proxy_url = 'https://{0}:{1}'.format(ip,port)
        
        try:
            proxy_dict = {
                'http':proxy_url,
            }
            requests.get(http_url,proxies = proxy_dict)
            return True
        except Exception as e:
            print("ip出現異常")
            #出現異常后就把這個ip給刪除掉
            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')
                self.delete_ip(ip)
                return False


    
    def get_random_ip(self):
        #從數據庫中隨機獲取到一個可用的ip
        random_sql = """
            SELECT ip,port FROM project_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:#如果返回True
　　　　　　　　  return "http://'{0}':'{1}'".format(ip,port)
　　　　　　　else:
　　　　　　　　　 return get_random_ip()

Middleware動態設置ip代理

class RandomProxyMiddleware(object):
    def process_request(self,request,spider):
        get_ip = GetIP()#這里需要導入那個函數
        request.meta['proxy'] = get_ip.get_random_ip()