Python爬虫框架Scrapy实例四下载中间件设置

还是豆瓣top250爬虫的例子,添加下载中间件,主要是设置动态Uesr-Agent和代理IP

Scrapy代理IP、Uesr-Agent的切换都是通过DOWNLOADER_MIDDLEWARES进行控制,我们在settings.py同级目录下创建middlewares.py文件,包装所有请求。

middlewares.py

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

import random
import base64
from settings import USER_AGENTS
from settings import PROXIES


class RandomUserAgent(object):
    def process_request(self, request, spider):
        useragent = random.choice(USER_AGENTS)
        request.headers.setdefault("User-Agent", useragent)


class RandomProxy(object):
    def process_request(self, request, spider):
        proxy = random.choice(PROXIES)

        if proxy['user_passwd'] is None:
            # 没有代理账户验证的免费代理的使用
            request.meta['proxy'] = "http//" + proxy['ip_port']
        else:
            request.meta['proxy'] = "http//" + proxy['ip_port']
            # 对账户密码进行base64编码转换
            base64_userpasswd = base64.b64decode(proxy['user_passwd'])
            # 对应到代理服务器的信令格式里
            request.headers['Proxy-Authorization'] = 'Basic ' + base64_userpasswd

settings.py

USER_AGENTS = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52"
]

PROXIES = [
    {'ip_port': '111.8.60.9:8123', 'user_passwd': ''},
    {'ip_port': '101.71.27.120:80', 'user_passwd': 'user2:pass2'},
    {'ip_port': '122.96.59.104:80', 'user_passwd': 'user3:pass3'},
    {'ip_port': '122.224.249.122:8088', 'user_passwd': 'user4:pass4'},
]

DOWNLOADER_MIDDLEWARES = { 'douban.middlewares.RandomUserAgent': 100,
'douban.middlewares.RandomProxy': 200, }