scrapy分布式写入到mysql_scrapy 分布式爬取数据同步写入数据库

from scrapy importsignalsimporttimefrom scrapy.contrib.downloadermiddleware.useragent importUserAgentMiddlewareimportrandom#UA池代码的编写(单独给UA池封装一个下载中间件的一个类)#1,导包UserAgentMiddlware类

classRandomUserAgent(UserAgentMiddleware):defprocess_request(self, request, spider):#从列表中随机抽选出一个ua值

ua =random.choice(user_agent_list)#ua值进行当前拦截到请求的ua的写入操作

request.headers.setdefault('User-Agent',ua)#批量对拦截到的请求进行ip更换#class Proxy(object):#def process_request(self, request, spider):##对拦截到请求的url进行判断(协议头到底是http还是https)##request.url返回值:http://www.xxx.com#h = request.url.split(':')[0] #请求的协议头#if h == 'https':#ip = random.choice(PROXY_https)#request.meta['proxy'] = 'https://'+ip

#PROXY_https = [#'120.83.49.90:9000',#'95.189.112.214:35508',#]

user_agent_list=["Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1"

"(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1","Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11"

"(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6"

"(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6"

"(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6","Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1"

"(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1","Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5"

"(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5","Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5"

"(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3"

"(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3","Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24"

"(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24","Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24"

"(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"]

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值