11.scrapy之随机设置请求头和ip代理池中间件

Request和Response都会首先经过中间件，所以我们在中间件中定义需要添加的header和params

scrapy中最重要的的两个类Response和Request

from scrapy import Request

class Request(object_ref):

    def __init__(self, url, callback=None, method='GET', headers=None, body=None,
                 cookies=None, meta=None, encoding='utf-8', priority=0,
                 dont_filter=False, errback=None, flags=None):

request是由spider产生

User-Agent

1.我们可以通过下述方式添加header

class ZhihuSpider(scrapy.Spider):
    name = "zhihu"
    allowed_domains = ["www.zhihu.com"]
    start_urls = ['https://www.zhihu.com/']

    headers = {
        "HOST": "www.zhihu.com",
        "Referer": "https://www.zhizhu.com",
        'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
    }

    def parse(self, response):
        ........
                yield scrapy.Request(url, headers=self.headers, callback=self.parse)

2.随机添加User-Agent
我们可以提前准备user-agent的列表，这样request的时候随机抽取放到header中去。不过python中有现成的库已经帮我们完成了这个任务
https://github.com/hellysmile/fake-useragent

pip install fake-useragent

from fake_useragent import UserAgent
ua = UserAgent()
ua.random

我们在middleware中定义随机请求头，毕竟request要经过中间件才发送出去

# pipeline.py
from fake_useragent import UserAgent
class RandomUserAgentMiddleware(object):
    def __init__(self, crawler):
        super(RandomUserAgentMiddleware, self).__init__()

        self.ua = UserAgent()
        self.per_proxy = crawler.settings.get('RANDOM_UA_PER_PROXY', False)
        self.ua_type = crawler.settings.get('RANDOM_UA_TYPE', 'random')
        self.proxy2ua = {}

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

    def process_request(self, request, spider):
        def get_ua():
            '''Gets random UA based on the type setting (random, firefox…)'''
            return getattr(self.ua, self.ua_type)

        if self.per_proxy:
            proxy = request.meta.get('proxy')
            if proxy not in self.proxy2ua:
                self.proxy2ua[proxy] = get_ua()
                logger.debug('Assign User-Agent %s to Proxy %s'
                             % (self.proxy2ua[proxy], proxy))
            request.headers.setdefault('User-Agent', self.proxy2ua[proxy])
        else:
            ua = get_ua()
            request.headers.setdefault('User-Agent', get_ua())

IP代理

ip代理是通过request的meta属性进行传入

    def process_request(self,request,spider):
        get_ip = GetIP()  #自己定义获取proxy ip函数
        request.meta["proxy"] = get_ip

1.自己定义爬虫抓取西刺网上的代理ip，存放到数据库中使用
2.pip install scrapy-proxies
https://github.com/aivarsk/scrapy-proxies

以下是爬取西刺网的免费代理ip代码：

import requests
from bs4 import BeautifulSoup
import pymysql

conn = pymysql.connect(
    host='127.0.0.1',
    user='root',
    password='123456',
    database='xiciip',
    port=3306
)
cursor = conn.cursor()

def crawl_ips():
    #爬取西刺网代理ip
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36"
    }
    for i in range(1,100):
        print("==================",i)
        re = requests.get("http://www.xicidaili.com/nn/{0}".format(i),headers=headers)
        text = re.text
        soup = BeautifulSoup(text)
        tr_list = soup.select("tr")
        tr_list = tr_list[1:]
        for td_list in tr_list:
            td_ip = td_list.select("td")[1].get_text()
            td_port = td_list.select("td")[2].get_text()
            http_type = td_list.select("td")[5].get_text()
            speed = float((td_list.select("td")[6].div.get('title'))[:-1])
            if speed > 1:
                continue
            insert_sql = """insert into iplist(http_type,ip,port,speed) values(%s,%s,%s,%s)"""
            cursor.execute(insert_sql,((http_type,td_ip,td_port,speed)))
            conn.commit()
            print(td_ip)
    conn.close()


class GetIP(object):
    def delete_ip(self,ip):
        #从数据库中删除无效的ip
        delete_sql = """delete from iplist where ip=%s"""
        cursor.execute(delete_sql,(ip))
        conn.commit()
        return True

    def judge_ip(self,http_type,ip,port):
        #判断ip是否可用
        http_url = "http://www.baidu.com"
        proxy_url = "{0}://{1}:{1}".format(http_type,ip,port)
        try:
            proxy = {'http_type': ip+":"+port}
            response = requests.get(http_url,proxies=proxy)
        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):
        #从数据库随机取一个可用ip
        random_sql = """
        select http_type,ip,port from iplist order by rand() limit 1
        """
        result = cursor.execute(random_sql)
        for ip_info in cursor.fetchall():
            http_type = ip_info[0]
            ip = ip_info[1]
            port = ip_info[2]

            judge_re = self.judge_ip(http_type,ip,port)
            if judge_re:
                return http_type+"://"+ip+":"+port
            else:
                return self.get_random_ip()

if __name__ == "__main__":
    crawl_ips()
# getip = GetIP()
# print(getip.get_random_ip())