Scrapy学习-13-使用DownloaderMiddleware设置IP代理池及IP变换

设置IP代理池及IP变换方案

方案一：

使用国内免费的IP代理

 http://www.xicidaili.com

# 创建一个tools文件夹，新建一个py文件，用于获取代理IP和PORT
from scrapy.selector import Selector
import MySQLdb
import requests

conn = MySQLdb.connect(host="192.168.1.1", user="root", passwd="", db="databasename", charset="utf8")
cursor = conn.cursor()

def crawl_ips():
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36"}
    for i in range(1568):
        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]

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

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

            conn.commit()

class GetIP(object):

    def delete_ip(self, 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):
        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):
        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()

if __name__ == "__main__":
    get_ip = GetIP()
    get_ip.get_random_ip()

# 修改settings配置
DOWNLOADER_MIDDLEWARES = {
    'ArticleSpider.middlewares.JSPageMiddleware': 1,
    'ArticleSpider.middlewares.RandomProxyMiddleware': 1
}

方案二：

改造github开源项目成为适合自己的proxies代理工具

 https://github.com/aivarsk/scrapy-proxies

方案三：

官方提供github开源项目，收费版本，但相对稳定

 https://github.com/scrapy-plugins/scrapy-crawlera

方案四：

使用tor洋葱网络，匿名伪装自己的IP地址