Scrapy_middlewares.py

Scrapy

1.SpiderMiddleware（很少使用，不解释）

class (projectname)SpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider 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_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.
        # Should return None or raise an exception.
        return None
    
    
    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

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

2.DownloaderMiddleware

class (projectname)DownloaderMiddleware(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
    
    #request被引擎调度给download之前执行，例如加代理，设置请求头等
    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
        return None
    
    #response被download发送到引擎之前
    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

    #当process_request异常时处理方法
    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)

实例一：加代理或请求头

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
    #获取在settings.py中定义的MY_USER_AGENT
    request_header = spider.settings['MY_USER_AGENT']
    currentHEADER = random.choice(request_header)
    request.headers["User-Agent"] = currentHEADER
    request.headers["Referer"] = 'http://www.***.cn/sipopublicsearch/patentsearch/searchHomeIndex-searchHomeIndex.shtml'
    cookie = 'WEE_SID=A7UWjgTfFIfVay_Bu6-y_pl_VvU3O3qsmwVIpx0oNP_AEixCvHKP!916921061!-2068312840!1537976698079; IS_LOGIN=true;'

    request.headers["Cookie"] = cookie

    '''
   #自定义ip 
   requestIP=[{"ipaddr": "	112.74.179.128:4111"},
           {"ipaddr": "119.23.247.125:4111"},
           ]
    currentIP=random.choice(requestIP)
    request.meta["proxy"] = "http://" + currentIP["ipaddr"]
   '''
    '''
    #动态ip
    # 代理服务器
    proxyServer = "http://http-cla.abuyun.com:9030"
    # 代理隧道验证信息
    proxyUser = "H0XDU0L156P12L**"
    proxyPass = "C85A97D40A0E95**"
    proxyAuth = "Basic " + base64.urlsafe_b64encode(bytes((proxyUser + ":" + proxyPass), "ascii")).decode("utf8")
    request.meta["proxy"] = proxyServer
    request.headers["Proxy-Authorization"] = proxyAuth
    '''

实例二：对接selenium

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
    request_header = spider.settings['MY_USER_AGENT']
    currentHEADER = random.choice(request_header)
    request.headers["User-Agent"] = currentHEADER
    if request.url=="http://lol.qq.com/web201310/info-heros.shtml#Navi":
        browser=webdriver.Chrome()
        browser.get(request.url)
        # 这里返回了response，下面的process_response就不会被执行了，直接返回给spider进行解析
        #from scrapy.http import HtmlResponse
        return HtmlResponse(url=request.url,body=browser.page_source,request=request,encoding='utf-8',status=200)