设为首页 加入收藏

TOP

scrapy 一些设置和问题(一)
2019-02-17 14:08:04 】 浏览:102
Tags:scrapy 一些 设置 问题

scrapy设置ua池

设置后在setting启用

DOWNLOADER_MIDDLEWARES = {
'laogou.middlewares.LaogouDownloaderMiddleware': 543,
'laogou.middlewares.randomUserAgentMiddleware': 400,
'laogou.middlewares.randomProxyMiddleware': 400,
}
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware

class randomUserAgentMiddleware(UserAgentMiddleware):

    def __init__(self,user_agent=''):
        self.user_agent = user_agent

    def process_request(self, request, spider):
        ua = random.choice(self.user_agent_list)
        if ua:
            request.headers.setdefault('User-Agent', ua)
    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"
    ]

scrapy设置ip池

from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware

class randomHttpProxyMiddleware(HttpProxyMiddleware):
    def __init__(self,ip = ''):
        self.ip = ip
    def process_request(self, request, spider):
        ip = random.choice(self.ip_list)
        if ip:
            request.meta['proxy'] = ip
    ip_list = [
        'https://182.122.176.49:9999',
        'https://125.123.141.20:9999'
    ]

 

scrapy 设置自定义cookie:class LaogouwangSpider(scrapy.Spider):    

   name = 'laogouwang'    
   # allowed_domains = ['ww
首页 上一页 1 2 下一页 尾页 1/2/2
】【打印繁体】【投稿】【收藏】 【推荐】【举报】【评论】 【关闭】 【返回顶部
上一篇Python——数据类型 下一篇禁用 urllib3 的安全请求警告

最新文章

热门文章

Hot 文章

Python

C 语言

C++基础

大数据基础

linux编程基础

C/C++面试题目