scrapy之中间件

1 Dowloader Middeware

下载中间件的用途
    1、在process——request内，自定义下载，不用scrapy的下载
    2、对请求进行二次加工，比如
        设置请求头
        设置cookie
        添加代理
            scrapy自带的代理组件：
                from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware
                from urllib.request import getproxies

class DownMiddleware1(object):
    def process_request(self, request, spider):
        """
        请求需要被下载时，经过所有下载器中间件的process_request调用
        :param request: 
        :param spider: 
        :return:  
            None,继续后续中间件去下载；
            Response对象，停止process_request的执行，开始执行process_response
            Request对象，停止中间件的执行，将Request重新调度器
            raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
        """
        pass



    def process_response(self, request, response, spider):
        """
        spider处理完成，返回时调用
        :param response:
        :param result:
        :param spider:
        :return: 
            Response 对象：转交给其他中间件process_response
            Request 对象：停止中间件，request会被重新调度下载
            raise IgnoreRequest 异常：调用Request.errback
        """
        print('response1')
        return response

    def process_exception(self, request, exception, spider):
        """
        当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
        :param response:
        :param exception:
        :param spider:
        :return: 
            None：继续交给后续中间件处理异常；
            Response对象：停止后续process_exception方法
            Request对象：停止中间件，request将会被重新调用下载
        """
        return None

#1、与middlewares.py同级目录下新建proxy_handle.py
import requests

def get_proxy():
    return requests.get("http://127.0.0.1:5010/get/").text

def delete_proxy(proxy):
    requests.get("http://127.0.0.1:5010/delete/?proxy={}".format(proxy))
    
    

#2、middlewares.py
from Amazon.proxy_handle import get_proxy,delete_proxy

class DownMiddleware1(object):
    def process_request(self, request, spider):
        """
        请求需要被下载时，经过所有下载器中间件的process_request调用
        :param request:
        :param spider:
        :return:
            None,继续后续中间件去下载；
            Response对象，停止process_request的执行，开始执行process_response
            Request对象，停止中间件的执行，将Request重新调度器
            raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
        """
        proxy="http://" + get_proxy()
        request.meta['download_timeout']=20
        request.meta["proxy"] = proxy
        print('为%s 添加代理%s ' % (request.url, proxy),end='')
        print('元数据为',request.meta)

    def process_response(self, request, response, spider):
        """
        spider处理完成，返回时调用
        :param response:
        :param result:
        :param spider:
        :return:
            Response 对象：转交给其他中间件process_response
            Request 对象：停止中间件，request会被重新调度下载
            raise IgnoreRequest 异常：调用Request.errback
        """
        print('返回状态吗',response.status)
        return response


    def process_exception(self, request, exception, spider):
        """
        当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
        :param response:
        :param exception:
        :param spider:
        :return:
            None：继续交给后续中间件处理异常；
            Response对象：停止后续process_exception方法
            Request对象：停止中间件，request将会被重新调用下载
        """
        print('代理%s，访问%s出现异常:%s' %(request.meta['proxy'],request.url,exception))
        import time
        time.sleep(5)
        delete_proxy(request.meta['proxy'].split("//")[-1])
        request.meta['proxy']='http://'+get_proxy()

        return request

2 Spider Middleware

1、爬虫中间件方法介绍

from scrapy import signals

class 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) #当前爬虫执行时触发spider_opened
        return s

    def spider_opened(self, spider):
        # spider.logger.info('我是egon派来的爬虫1: %s' % spider.name)
        print('我是egon派来的爬虫1: %s' % spider.name)

    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).
        print('start_requests1')
        for r in start_requests:
            yield r

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.
        # 每个response经过爬虫中间件进入spider时调用

        # 返回值：Should return None or raise an exception.
        #1、None: 继续执行其他中间件的process_spider_input
        #2、抛出异常：
        # 一旦抛出异常则不再执行其他中间件的process_spider_input
        # 并且触发request绑定的errback
        # errback的返回值倒着传给中间件的process_spider_output
        # 如果未找到errback，则倒着执行中间件的process_spider_exception

        print("input1")
        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.
        print('output1')

        # 用yield返回多次，与return返回一次是一个道理
        # 如果生成器掌握不好（函数内有yield执行函数得到的是生成器而并不会立刻执行），生成器的形式会容易误导你对中间件执行顺序的理解
        # for i in result:
        #     yield i
        return result

    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.
        print('exception1')

2、当前爬虫启动时以及初始请求产生时

#步骤一：
'''
打开注释：
SPIDER_MIDDLEWARES = {
   'Baidu.middlewares.SpiderMiddleware1': 200,
   'Baidu.middlewares.SpiderMiddleware2': 300,
   'Baidu.middlewares.SpiderMiddleware3': 400,
}

'''


#步骤二：middlewares.py
from scrapy import signals

class SpiderMiddleware1(object):
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened) #当前爬虫执行时触发spider_opened
        return s

    def spider_opened(self, spider):
        print('我是egon派来的爬虫1: %s' % spider.name)

    def process_start_requests(self, start_requests, spider):
        # Must return only requests (not items).
        print('start_requests1')
        for r in start_requests:
            yield r


        
        
class SpiderMiddleware2(object):
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)  # 当前爬虫执行时触发spider_opened
        return s

    def spider_opened(self, spider):
        print('我是egon派来的爬虫2: %s' % spider.name)

    def process_start_requests(self, start_requests, spider):
        print('start_requests2')
        for r in start_requests:
            yield r


class SpiderMiddleware3(object):
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)  # 当前爬虫执行时触发spider_opened
        return s

    def spider_opened(self, spider):
        print('我是egon派来的爬虫3: %s' % spider.name)

    def process_start_requests(self, start_requests, spider):
        print('start_requests3')
        for r in start_requests:
            yield r


#步骤三：分析运行结果
#1、启动爬虫时则立刻执行：

我是egon派来的爬虫1: baidu
我是egon派来的爬虫2: baidu
我是egon派来的爬虫3: baidu


#2、然后产生一个初始的request请求，依次经过爬虫中间件1,2,3：
start_requests1
start_requests2
start_requests3

3、process_spider_input返回None时

#步骤一：打开注释：
SPIDER_MIDDLEWARES = {
   'Baidu.middlewares.SpiderMiddleware1': 200,
   'Baidu.middlewares.SpiderMiddleware2': 300,
   'Baidu.middlewares.SpiderMiddleware3': 400,
}

'''

#步骤二：middlewares.py
from scrapy import signals

class SpiderMiddleware1(object):

    def process_spider_input(self, response, spider):
        print("input1")

    def process_spider_output(self, response, result, spider):
        print('output1')
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception1')


class SpiderMiddleware2(object):

    def process_spider_input(self, response, spider):
        print("input2")
        return None

    def process_spider_output(self, response, result, spider):
        print('output2')
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception2')


class SpiderMiddleware3(object):

    def process_spider_input(self, response, spider):
        print("input3")
        return None

    def process_spider_output(self, response, result, spider):
        print('output3')
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception3')


#步骤三：运行结果分析

#1、返回response时，依次经过爬虫中间件1,2,3
input1
input2
input3

#2、spider处理完毕后，依次经过爬虫中间件3,2,1
output3
output2
output1

4、process_spider_input抛出异常时

#步骤一：
'''
打开注释：
SPIDER_MIDDLEWARES = {
   'Baidu.middlewares.SpiderMiddleware1': 200,
   'Baidu.middlewares.SpiderMiddleware2': 300,
   'Baidu.middlewares.SpiderMiddleware3': 400,
}

'''

#步骤二：middlewares.py

from scrapy import signals

class SpiderMiddleware1(object):

    def process_spider_input(self, response, spider):
        print("input1")

    def process_spider_output(self, response, result, spider):
        print('output1')
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception1')


class SpiderMiddleware2(object):

    def process_spider_input(self, response, spider):
        print("input2")
        raise Type

    def process_spider_output(self, response, result, spider):
        print('output2')
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception2')


class SpiderMiddleware3(object):

    def process_spider_input(self, response, spider):
        print("input3")
        return None

    def process_spider_output(self, response, result, spider):
        print('output3')
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception3')

        

#运行结果        
input1
input2
exception3
exception2
exception1

#分析：
#1、当response经过中间件1的 process_spider_input返回None，继续交给中间件2的process_spider_input
#2、中间件2的process_spider_input抛出异常，则直接跳过后续的process_spider_input，将异常信息传递给Spiders里该请求的errback
#3、没有找到errback，则该response既没有被Spiders正常的callback执行，也没有被errback执行，即Spiders啥事也没有干，那么开始倒着执行process_spider_exception
#4、如果process_spider_exception返回None，代表该方法推卸掉责任，并没处理异常，而是直接交给下一个process_spider_exception，全都返回None，则异常最终交给Engine抛出

5、指定errback

#步骤一：spider.py
import scrapy


class BaiduSpider(scrapy.Spider):
    name = 'baidu'
    allowed_domains = ['www.baidu.com']
    start_urls = ['http://www.baidu.com/']


    def start_requests(self):
        yield scrapy.Request(url='http://www.baidu.com/',
                             callback=self.parse,
                             errback=self.parse_err,
                             )

    def parse(self, response):
        pass

    def parse_err(self,res):
        #res 为异常信息，异常已经被该函数处理了，因此不会再抛给因此，于是开始走process_spider_output
        return [1,2,3,4,5] #提取异常信息中有用的数据以可迭代对象的形式存放于管道中，等待被process_spider_output取走



#步骤二：
'''
打开注释：
SPIDER_MIDDLEWARES = {
   'Baidu.middlewares.SpiderMiddleware1': 200,
   'Baidu.middlewares.SpiderMiddleware2': 300,
   'Baidu.middlewares.SpiderMiddleware3': 400,
}

'''

#步骤三：middlewares.py

from scrapy import signals

class SpiderMiddleware1(object):

    def process_spider_input(self, response, spider):
        print("input1")

    def process_spider_output(self, response, result, spider):
        print('output1',list(result))
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception1')


class SpiderMiddleware2(object):

    def process_spider_input(self, response, spider):
        print("input2")
        raise TypeError('input2 抛出异常')

    def process_spider_output(self, response, result, spider):
        print('output2',list(result))
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception2')


class SpiderMiddleware3(object):

    def process_spider_input(self, response, spider):
        print("input3")
        return None

    def process_spider_output(self, response, result, spider):
        print('output3',list(result))
        return result

    def process_spider_exception(self, response, exception, spider):
        print('exception3')



#步骤四：运行结果分析
input1
input2
output3 [1, 2, 3, 4, 5] #parse_err的返回值放入管道中，只能被取走一次，在output3的方法内可以根据异常信息封装一个新的request请求
output2 []
output1 []