1.初始化一些User-Agent

建立一個檔案叫useragent.py

agents = [
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
    "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 GTB5",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; tr; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8 ( .NET CLR 3.5.30729; .NET4.0E)",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0a2) Gecko/20110622 Firefox/6.0a2",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre",
    "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0 )",
    "Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90)",
    "Mozilla/5.0 (Windows; U; Windows XP) Gecko MultiZilla/1.6.1.0a",
    "Mozilla/2.02E (Win95; U)",
    "Mozilla/3.01Gold (Win95; I)",
    "Mozilla/4.8 [en] (Windows NT 5.1; U)",
    "Mozilla/5.0 (Windows; U; Win98; en-US; rv:1.4) Gecko Netscape/7.1 (ax)",

]
 

2.去阿布雲購買一個動態的套餐

3.編寫scrapy的middleware

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

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals
from .useragent import agents
import random
import base64
from tutorial import settings


# 專業版代理伺服器
#proxyServer = "http://http-pro.abuyun.com:9010"
# 動態版
proxyServer = "http://http-dyn.abuyun.com:9020"

# 代理隧道驗證資訊

proxyUser = "******"
proxyPass = "******"

# for Python2
#proxyAuth = "Basic " + base64.b64encode(proxyUser + ":" + proxyPass)

# for Python3
proxyAuth = "Basic " + base64.urlsafe_b64encode(bytes((proxyUser + ":" + proxyPass), "ascii")).decode("utf8")



class TutorialDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        #設定user-agent
        agent = random.choice(agents)
        request.headers["User-Agent"] = agent
        #設定proxy
        request.meta["proxy"] = proxyServer
        request.headers["Proxy-Authorization"] = proxyAuth


        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)
 

4. 修改settings

DOWNLOADER_MIDDLEWARES = {
   'tutorial.middlewares.TutorialDownloaderMiddleware': 543,
}

5.其他說明

user-agent 有PC版本，也有手機瀏覽器版本，要注意你請求的目標網址會不會對手機瀏覽器做優化，這樣PC和手機是不同的2個頁面，我這邊的user-agent全是pc版本的。如果要除錯手機瀏覽器版本的，可以全換成手機的。

關於代理，有免費的和付費的。免費的太麻煩，成功率又低，還是算了吧。

付費分2種，一種是給api去獲取代理ip，像芝麻http代理，這種就麻煩了，估計還要自己寫東西來定時請求代理ip，然後儲存到redis中供所有爬蟲共用。

一種就是像這種阿布雲，只要寫一個，它自己會動態處理，方便很多。缺點是分散式爬蟲不好共享，需要買多個。。。

國外的跟scrapy比較容易整合的代理是crawlera，太貴了。也是很方便設定的。還有免費的開源的，可以通過digitalocean設定的scrapoxy，還沒怎麼研究。