基于scrapy的搜索引擎（五）：反爬突破

起步

对抗过程

scrapy架构

request 与 response

随机更换user-agent

middlewares.py
from fake_useragent import UserAgent
ua = UserAgent()

class RandomUserAgentMiddLware(object):
# user-agent 随机切换
    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())

settings.py

DOWNLOADER_MIDDLEWARES = {
    'PictureSpider.middlewares.RandomUserAgentMiddLware': 543,
    'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
}
RANDOM_UA_TYPE = "random"

使用ip代理

原理：

方式一：爬取西刺，组建免费ip代理池：
西刺页面
xic_ip.py

import requests
from scrapy.selector import Selector
import pymysql

conn = pymysql.connect(host="xxxxxxxx", port=3306, user="xxxxxx", password="xxxxxxx", db="xxxxxxx", 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},'{3}')".format(
                    ip_info[0], ip_info[1], ip_info[3], ip_info[2]
                )
            )

            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()

缺点：不稳定，速度较慢

中间件设置,使用从数据库随机获得的ip：

from tools.xic_ip import GetIP

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()

可以利用scrapy-proxies加以改造：

缺点：它从文件中读取，不如数据库方便

方式二：使用scrapy-crawla（收费，需注册账号）:

方式三：利用YC

方式四：限制爬虫的访问速度，保护好自己的源ip

验证码识别

云打码的使用

其他手段

对于不需要登录就能爬取的网页，禁用cookies

COOKIES_ENABLED = False

配置scrapy自带的扩展限制爬虫速度：

不同的项目配置不同的settings:

custom_settings = {
        "COOKIES_ENABLED": True
    }