Scrapy爬虫：模拟浏览器和使用代理

采用settings.py的方式进行设置user agent和proxy列表

http://www.tuicool.com/articles/VRfQR3U

http://jinbitou.net/2016/12/01/2229.html（本人用的这种）

网站的反爬虫策略：

http://www.cnblogs.com/tyomcat/p/5447853.html

1.在settings.py同级目录下新建文件useragent.py

# -*-coding:utf-8-*-
from scrapy import log
import logging

import random
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
class UserAgent(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:
            #显示当前使用的useragent
            #print "********Current UserAgent:%s************" %ua
            #记录
            log.msg('Current UserAgent: '+ua, level=logging.DEBUG)
            request.headers.setdefault('User-Agent', ua)

    #the default user_agent_list composes chrome,I E,firefox,Mozilla,opera,netscape
    #for more user agent strings,you can find it in http://www.useragentstring.com/pages/useragentstring.php
    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"
       ]

2.在settings.py同级目录新建文件proxymiddlewares.py

# -*- coding: utf-8 -*-
import random, base64


class ProxyMiddleware(object):

    proxyList = [ \
        '121.193.143.249:80','112.126.65.193:80','122.96.59.104:82','115.29.98.139:9999','117.131.216.214:80','116.226.243.166:8118','101.81.22.21:8118','122.96.59.107:843'    
        ]

    def process_request(self, request, spider):
        # Set the location of the proxy
        pro_adr = random.choice(self.proxyList)
        print("USE PROXY -> " + pro_adr)
        request.meta['proxy'] = "http://" + pro_adr

3.修改settings.py (注意DOWNLOADER_MIDDLEWARES)

# -*- coding: utf-8 -*-

BOT_NAME = 'ip_proxy_pool'

SPIDER_MODULES = ['ip_proxy_pool.spiders']
NEWSPIDER_MODULE = 'ip_proxy_pool.spiders'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

ITEM_PIPELINES = {
   'ip_proxy_pool.pipelines.IpProxyPoolPipeline': 300,
}

#爬取间隔
DOWNLOAD_DELAY = 1

# 禁用cookie
COOKIES_ENABLED = False


# 重写默认请求头
DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html, application/xhtml+xml, application/xml',
  'Accept-Language': 'zh-CN,zh;q=0.8',
  'Host':'ip84.com',
  'Referer':'http://ip84.com/',
  'X-XHR-Referer':'http://ip84.com/'
}

#激活自定义UserAgent和代理IP
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'ip_proxy_pool.useragent.UserAgent': 1,
   'ip_proxy_pool.proxymiddlewares.ProxyMiddleware':100,
   'scrapy.downloadermiddleware.useragent.UserAgentMiddleware' : None,
}

4.开始爬取即可

Scrapy爬虫：模拟浏览器和使用代理

猜你喜欢