Scrapy Spider MiddleWare 设置

# -*- 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 newrecord.settings import NOW_Y, NOW_M, NOW_D, YES_Y, YES_M, YES_D

from scrapy import signals

import time

import base64 # DownloadMiddleware # 0 47 167 宝蓝色RGB

# 在process_request downloadmiddleware 中添加代理

# proxy_user_pass = 'USERNAME:PASSWORD'

# encoded_user_pass = base64.b64encode(proxy_user_pass)

# request.headers['Proxy-Authorization']='Basic'+encoded_user_passwd

# request.meta['proxy']='IP:PORT'

class NewrecordSpiderMiddleware(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

# 进入spider 的response 的数据

# 和 downloadmiddle里面的process_response类似

# 先去downloadmiddleware那里的process_response 再到这里处理:

def process_spider_input(self, response, spider): # 处理进入spider中的response数据，但返回的是None

print('-----------------------3--------------------') # 对response筛选之后不能阻止进入spider 啥用？try--except---Exception,

print('---进入spidermiddleware----process_spider_input------response.url----%s--------'%(response.url))

# Called for each response that goes through the spider

try:

# middleware and into the spider.

# Should return None or raise an exception.

return None

except Exception as e:

print(e)

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.

# result :经过parse_item 处理过后的输出结果，等于item数据也可以在这里处理，不过是在Pipline处理过后的数据

# parse_item 输出的结果先进入pipeline管道里去处理item数据最后回到process_spider_output这里，再就是关闭spider:

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

# 处理start_urls 后面的url无关: 否则这方法不会运行，只能是start_urls参数

# 并且def 里面的东西只能是process_start_requests

# 处理start_urls 与后面的url无关:

def process_start_requests(self, start_urls, 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 start_urls (not items).

for r in start_urls:

if str(r).find('rank_news') >= 0:

print('---------------------0-----------------------------')

print('-------------------进入Spider MiddleWare里面的开始爬去网页url-----------start_requests===:%s', r)

yield r

def spider_opened(self, spider):

spider.logger.info('Spider opened: %s ' %spider.name)

class NewrecordDownloaderMiddleware(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):

crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)

return s

# Proxy-Authorization base64代理账户验证

# request.meta['proxy'] = "http://YOUR_PROXY_IP:PORT"

# encoded_user_pass = base64.b64encode(proxy_user_pass)

# request.headers['Proxy-Authorization'] = 'Basic ' + encoded_user_pass

# request.meta['proxy'] = ['127.0.0.1:8000']

# request.meta['item']='' 在request meta 数据里面增加数据可以用来传参

# request(url, meta['item']=item[], callback= '')

# request.cookies['']='' 往request里面增加cookies

def process_request(self, request, spider):

print('---------------1------------------')

print('----------------进入DownloadMiddleWare中的request的url是：%s----------------' %(request.url))

return None

# return None: continue processing this exception

# return a Response object: stops process_exception() chain

# return a Request object: stops process_exception() chain

def process_response(self, request, response, spider): 　　# 处理所有爬过的网站的response,通过response.url 可以筛选

print('-----------------------------2---------------------------------')　　 # 需要的爬取的网址，但这个在Rules里面更方便

print('----------------进入DownloadMiddleWare中的response的url是：%s----------------' %(response.url))

return response 　　　　 # 返回的response 进入spider 中的process_spider_input

def process_exception(self, request, exception, spider):

pass

def spider_opened(self, spider):

spider.logger.info('Spider opened: %s' % spider.name)

121 1,19 顶端

Scrapy Spider MiddleWare 设置

猜你喜欢