scrapy爬虫tools---------UserAgent | ip代理池

最新推荐文章于 2025-06-22 12:58:04 发布

原创最新推荐文章于 2025-06-22 12:58:04 发布 · 175 阅读

1 ·

CC 4.0 BY-SA版权

python爬虫专栏收录该内容

25 篇文章

订阅专栏

本文详细介绍如何使用fake-useragent库实现随机更换User-Agent，以及如何构建和维护IP代理池来提升Scrapy爬虫的稳定性和效率。通过具体代码示例，展示了如何设置随机User-Agent类型，以及如何爬取并验证IP代理的有效性。

使用fakeuseragent

pip install fake-useragent

settinf.py设置随机模式RANDOM_UA_TYPE = "random"

from fake_useragent import UserAgent

class RandomUserAgentMiddlware(object):
    #随机更换user-agent
    def __init__(self, crawler):
        super(RandomUserAgentMiddlware, self).__init__()
        self.ua = UserAgent()
        self.ua_type = crawler.settings.get("RANDOM_UA_TYPE", "random")

    @classmethod
    def from_crawler(cls, crawler):
        return cls(crawler)

    def process_request(self, request, spider):
        def get_ua():
            return getattr(self.ua, self.ua_type)

        request.headers.setdefault('User-Agent', get_ua())

------------------------------------------------------------------------------------------------------------------------------------------------------------------------

IP代理池

ip动态变化：重启路由器等

ip代理的原理：

不直接发送自己真实ip，而使用中间代理商（代理服务器），那么服务器不知道我们的ip也就不会把我们禁掉
setting.py设置

# _*_ coding: utf-8 _*_
__author__ = 'mtianyan'
__date__ = '2017/5/24 16:27'
import requests
from scrapy.selector import Selector
import MySQLdb

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


def crawl_ips():
    #爬取西刺的免费ip代理
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0"}
    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):
        #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())
if __name__ == "__main__":
    get_ip = GetIP()
    get_ip.get_random_ip()