(1)第一步:内容介绍
(2)
网易新闻的链接:https://news.163.com/
重点爬取五个板块的文字:国内,国际,军事,航空,无人机
需求:爬取基于文字的新闻数据
三步走
第一步:
新建项目
scrapy startproject wangyiPro
cd wangyiPro/
建立爬虫文件
scrapy genspider wangyi www.xxxx.com
第二步:组织数据结构和写爬虫文件
wangyi.py
import scrapy class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,8] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() title=li.xpath('./a/text()').extract_first() print(url+":"+title)
在settings.py加上UA和robots设置
注意,在爬取数据量很小的时候可以不加,在某些网站上,这个案例就是这样
第三步:执行
scrapy crawl wangyi --nolog
结果:
(3)很多时间花费在解析数据上了
# -*- coding: utf-8 -*- import scrapy class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,8] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() title=li.xpath('./a/text()').extract_first() # print(url+":"+title) #对每一个板块对应的url发起请求，获取页面数据（标题，缩略图，关键字，发布时间，url） yield scrapy.Request(url=url,callback=self.parseSecond) def parseSecond(self,response): div_list=response.xpath('//div[@class="data_row news_article clearfix"]') print(len(div_list)) for div in div_list: head=div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() url=div.xpath('.//div[@class="news_title"]/h3/a/@href').extract_first() imgUrl=div.xpath('./a/img/@src').extract_first() publish_t=div.xpath('.//div[@class="news_tag"]/span/text()').extract_first() tag=div.xpath('.//div[@class="keywords"]/a/text()').extract() tag="".join(tag)
动态加载的数据拿不到,用selenium
(4)selenium的初步应用
# -*- coding: utf-8 -*- import scrapy from selenium import webdriver #第一步,导包 #第二步,实例化浏览器,保证浏览器只能实例化一次 class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def __init__(self): # 第二步,实例化一个浏览器对象(保证实例化一次) self.bro=webdriver.Chrome(executable_path='./chromedriver') def closed(self,spider): # 最后一步:必须在整个爬虫结束后,才关闭浏览器 print('爬虫结束') self.bro.quit def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,8] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() title=li.xpath('./a/text()').extract_first() # print(url+":"+title) #对每一个板块对应的url发起请求，获取页面数据（标题，缩略图，关键字，发布时间，url） yield scrapy.Request(url=url,callback=self.parseSecond) def parseSecond(self,response): div_list=response.xpath('//div[@class="data_row news_article clearfix"]') print(len(div_list)) for div in div_list: head=div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() url=div.xpath('.//div[@class="news_title"]/h3/a/@href').extract_first() imgUrl=div.xpath('./a/img/@src').extract_first() publish_t=div.xpath('.//div[@class="news_tag"]/span/text()').extract_first() tag=div.xpath('.//div[@class="keywords"]/a/text()').extract() tag="".join(tag)
(5)selenium在下载中间件中的配置2
爬虫文件wangyi.py
# -*- coding: utf-8 -*- import scrapy from selenium import webdriver #第一步,导包 #第二步,实例化浏览器,保证浏览器只能实例化一次 class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def __init__(self): # 第二步,实例化一个浏览器对象(保证实例化一次) self.bro=webdriver.Chrome(executable_path='./wangyiPro/chromedriver.exe') def closed(self,spider): # 最后一步:必须在整个爬虫结束后,才关闭浏览器 print('爬虫结束') self.bro.quit() def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,8] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() title=li.xpath('./a/text()').extract_first() # print(url+":"+title) #对每一个板块对应的url发起请求，获取页面数据（标题，缩略图，关键字，发布时间，url） yield scrapy.Request(url=url,callback=self.parseSecond) def parseSecond(self,response): div_list=response.xpath('//div[@class="data_row news_article clearfix"]') # print(len(div_list)) for div in div_list: head=div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() url=div.xpath('.//div[@class="news_title"]/h3/a/@href').extract_first() imgUrl=div.xpath('./a/img/@src').extract_first() publish_t=div.xpath('.//div[@class="news_tag"]/span/text()').extract_first() tag=div.xpath('.//div[@class="keywords"]/a/text()').extract() tag="".join(tag)
middlewares.py
from scrapy import signals class WangyiproDownloaderMiddleware(object): def process_request(self, request, spider): return None #拦截响应的对象(拦截下载器传递给Spider的响应对象) #request:响应对象对应的请求对象 #response:拦截到的响应对象 #spider:爬虫文件中对应的爬虫类的实例 def process_response(self, request, response, spider): print(request.url+"这是下载中间件") return response
开启UA和robot以及下载中间件
settings.py
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36' # Obey robots.txt rules ROBOTSTXT_OBEY = False DOWNLOADER_MIDDLEWARES = { 'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543, }
(6)网易爬虫程序wangyi.py
# -*- coding: utf-8 -*- import scrapy from selenium import webdriver #第一步,导包 #第二步,实例化浏览器,保证浏览器只能实例化一次 class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def __init__(self): # 第二步,实例化一个浏览器对象(保证实例化一次) self.bro=webdriver.Chrome(executable_path='./wangyiPro/chromedriver.exe') # urls = [] def closed(self,spider): # 最后一步:必须在整个爬虫结束后,才关闭浏览器 print('爬虫结束') self.bro.quit() def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 # global urls for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() # urls.append(url) title=li.xpath('./a/text()').extract_first() # print(url+":"+title) print(url) #对每一个板块对应的url发起请求，获取页面数据（标题，缩略图，关键字，发布时间，url） yield scrapy.Request(url=url,callback=self.parseSecond) def parseSecond(self,response): div_list=response.xpath('/html/body/div/div[3]/div[4]/div[1]/div/div/ul/li/div/div') print(len(div_list)) for div in div_list: head=div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() url=div.xpath('.//div[@class="news_title"]/h3/a/@href').extract_first() imgUrl=div.xpath('./a/img/@src').extract_first() publish_t=div.xpath('.//div[@class="news_tag"]/span/text()').extract_first() tag=div.xpath('.//div[@class="keywords"]/a/text()').extract() tag="".join(tag)
settings.py文件
DOWNLOADER_MIDDLEWARES = { 'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543, } LOG_LEVEL = 'ERROR' USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36' # Obey robots.txt rules ROBOTSTXT_OBEY = False
middlewares.py
from scrapy import signals from time import sleep from scrapy.http import HtmlResponse class WangyiproDownloaderMiddleware(object): def process_request(self, request, spider): return None #拦截响应的对象(拦截下载器传递给Spider的响应对象) #request:响应对象对应的请求对象 #response:拦截到的响应对象 #spider:爬虫文件中对应的爬虫类的实例 def process_response(self, request, response, spider): # print(request.url+"这是下载中间件") #响应对象中存储页面数据的篡改 #spider.url_list可以提前拿出来,问题出在这个http是否加s和无人机这个模块是独特的解析方式上边 if request.url in['http://news.163.com/domestic/','http://news.163.com/world/','http://war.163.com/','http://news.163.com/air/']: # if request.url in spider.urls: # print('this is process_response!!!!!!!!!!!!!!!!!!!!!!!!!1') spider.bro.get(url=request.url) sleep(2) #页面数据就是包含了动态加载出来的新闻数据对应的页面数据 page_text=spider.bro.page_source return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request) # 实例化新的响应对象,作用域 else: return response
(7)向下滑动与打印解析的内容(),这个有问题明天需要测试一下
wangyi.py爬虫文件
# -*- coding: utf-8 -*- import scrapy from selenium import webdriver #第一步,导包 #第二步,实例化浏览器,保证浏览器只能实例化一次 class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def __init__(self): # 第二步,实例化一个浏览器对象(保证实例化一次) self.bro=webdriver.Chrome(executable_path='./wangyiPro/chromedriver.exe') # urls = [] def closed(self,spider): # 最后一步:必须在整个爬虫结束后,才关闭浏览器 print('爬虫结束') self.bro.quit() def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 # global urls for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() # urls.append(url) title=li.xpath('./a/text()').extract_first() # print(url+":"+title) print(url) #对每一个板块对应的url发起请求，获取页面数据（标题，缩略图，关键字，发布时间，url） yield scrapy.Request(url=url,callback=self.parseSecond) def parseSecond(self,response): div_list=response.xpath('/html/body/div/div[3]/div[4]/div[1]/div/div/ul/li/div/div') print(len(div_list)) for div in div_list: head=div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() url=div.xpath('.//div[@class="news_title"]/h3/a/@href').extract_first() imgUrl=div.xpath('./a/img/@src').extract_first() publish_t=div.xpath('.//div[@class="news_tag"]/span/text()').extract_first() tag=div.xpath('.//div[@class="keywords"]/a/text()').extract() tags=[] for t in tag: t=t.strip(' ') tags.append(t) tag="".join(tags) # print(head+":"+url+":"+imgUrl+":"+tag)
settings.py爬虫文件
# -*- coding: utf-8 -*- # Scrapy settings for wangyiPro project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://doc.scrapy.org/en/latest/topics/settings.html # https://doc.scrapy.org/en/latest/topics/downloader-middleware.html # https://doc.scrapy.org/en/latest/topics/spider-middleware.html BOT_NAME = 'wangyiPro' SPIDER_MODULES = ['wangyiPro.spiders'] NEWSPIDER_MODULE = 'wangyiPro.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'wangyiPro (+http://www.yourdomain.com)' USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36' # Obey robots.txt rules ROBOTSTXT_OBEY = False # Configure maximum concurrent requests performed by Scrapy (default: 16) #CONCURRENT_REQUESTS = 32 # Configure a delay for requests for the same website (default: 0) # See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay # See also autothrottle settings and docs #DOWNLOAD_DELAY = 3 # The download delay setting will honor only one of: #CONCURRENT_REQUESTS_PER_DOMAIN = 16 #CONCURRENT_REQUESTS_PER_IP = 16 # Disable cookies (enabled by default) #COOKIES_ENABLED = False # Disable Telnet Console (enabled by default) #TELNETCONSOLE_ENABLED = False # Override the default request headers: #DEFAULT_REQUEST_HEADERS = { # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', # 'Accept-Language': 'en', #} # Enable or disable spider middlewares # See https://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'wangyiPro.middlewares.WangyiproSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { 'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543, } LOG_LEVEL = 'ERROR' # Enable or disable extensions # See https://doc.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html #ITEM_PIPELINES = { # 'wangyiPro.pipelines.WangyiproPipeline': 300, #} # Enable and configure the AutoThrottle extension (disabled by default) # See https://doc.scrapy.org/en/latest/topics/autothrottle.html #AUTOTHROTTLE_ENABLED = True # The initial download delay #AUTOTHROTTLE_START_DELAY = 5 # The maximum download delay to be set in case of high latencies #AUTOTHROTTLE_MAX_DELAY = 60 # The average number of requests Scrapy should be sending in parallel to # each remote server #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0 # Enable showing throttling stats for every response received: #AUTOTHROTTLE_DEBUG = False # Enable and configure HTTP caching (disabled by default) # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings #HTTPCACHE_ENABLED = True #HTTPCACHE_EXPIRATION_SECS = 0 #HTTPCACHE_DIR = 'httpcache' #HTTPCACHE_IGNORE_HTTP_CODES = [] #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
middlewares.py
# -*- 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 time import sleep from scrapy.http import HtmlResponse class WangyiproDownloaderMiddleware(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. 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 #拦截响应的对象(拦截下载器传递给Spider的响应对象) #request:响应对象对应的请求对象 #response:拦截到的响应对象 #spider:爬虫文件中对应的爬虫类的实例 def process_response(self, request, response, spider): # print(request.url+"这是下载中间件") #响应对象中存储页面数据的篡改 #spider.url_list可以提前拿出来 if request.url in['http://news.163.com/domestic/','http://news.163.com/world/','http://war.163.com/','http://news.163.com/air/']: # if request.url in spider.urls: # print('this is process_response!!!!!!!!!!!!!!!!!!!!!!!!!1') spider.bro.get(url=request.url) sleep(2) # js='window.scrollTo(0,documnet.body.scrollHeight)' # spider.bro.execute_script(js) # sleep(2) #缓冲加载数据,一定要给予浏览器一定的缓冲加载数据的时间 #页面数据就是包含了动态加载出来的新闻数据对应的页面数据 page_text=spider.bro.page_source return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request) # 实例化新的响应对象,作用域 else: return response
items.py
# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # https://doc.scrapy.org/en/latest/topics/items.html import scrapy class WangyiproItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() pass
pipelines.py
# -*- coding: utf-8 -*- # Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html class WangyiproPipeline(object): def process_item(self, item, spider): # print(item['title']+':'+item['content']) return item
执行:
scrapy crawl wangyi --nolog
(8)加上传入管道和传递item,以及meta传递参数和获取文章内容的编写
爬虫文件wangyi.py
# -*- coding: utf-8 -*- import scrapy from selenium import webdriver #第一步,导包 from wangyiPro.items import WangyiproItem #第二步,实例化浏览器,保证浏览器只能实例化一次 class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['https://news.163.com/'] def __init__(self): # 第二步,实例化一个浏览器对象(保证实例化一次) self.bro=webdriver.Chrome(executable_path='./wangyiPro/chromedriver.exe') # urls = [] def closed(self,spider): # 最后一步:必须在整个爬虫结束后,才关闭浏览器 print('爬虫结束') self.bro.quit() def parse(self, response): lis=response.xpath('//div[@class="ns_area list"]/ul/li') indexs=[3,4,6,7,] li_list=[] #存储的就是国内,国际,军事,航空,无人机五个模块对应的li标签对象 # global urls for index in indexs: li_list.append(lis[index]) #获取四个板块中的链接和文字标题 for li in li_list: url=li.xpath('./a/@href').extract_first() # urls.append(url) title=li.xpath('./a/text()').extract_first() # print(url+":"+title) print(url) #对每一个板块对应的url发起请求，获取页面数据（标题，缩略图，关键字，发布时间，url） yield scrapy.Request(url=url,callback=self.parseSecond,meta={'title':title})#请求传参 def parseSecond(self,response): div_list=response.xpath('/html/body/div/div[3]/div[4]/div[1]/div/div/ul/li/div/div') print(len(div_list)) for div in div_list: head=div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() url=div.xpath('.//div[@class="news_title"]/h3/a/@href').extract_first() imgUrl=div.xpath('./a/img/@src').extract_first() publish_t=div.xpath('.//div[@class="news_tag"]/span/text()').extract_first() tag=div.xpath('.//div[@class="keywords"]/a/text()').extract() tags=[] for t in tag: t=t.strip(' ') tags.append(t) tag="".join(tags) #获取meta传递过来的数据值title title=response.meta['title'] #实例化item对象,将解析到的数据值存储到item对象中 item =WangyiproItem() item['head']=head item['url']=url item['imgUrl']=imgUrl item['publish_t']=publish_t item['tag']=tag item['title']=title #对url发起请求,获取对应页面中存储的新闻内容数据 yield scrapy.Request(url=url, callback=self.getContent, meta={'item': item}) # print(head+":"+url+":"+imgUrl+":"+tag) def getContent(self,response): #获取传递过来的item item=response.meta['item'] #解析当前页面中存储的新闻数据 content_list=response.xpath('//div[@class="post_text"]/p/text()').extract() content="".join(content_list) item['content']=content yield item
items.py
# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # https://doc.scrapy.org/en/latest/topics/items.html import scrapy class WangyiproItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() # pass head = scrapy.Field() url = scrapy.Field() imgUrl = scrapy.Field() publish_t = scrapy.Field() tag = scrapy.Field() title = scrapy.Field() content = scrapy.Field()
pipelines.py
# -*- coding: utf-8 -*- # Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html class WangyiproPipeline(object): def process_item(self, item, spider): print(item['title']+':'+item['content']) return item
settings.py
# -*- coding: utf-8 -*- # Scrapy settings for wangyiPro project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://doc.scrapy.org/en/latest/topics/settings.html # https://doc.scrapy.org/en/latest/topics/downloader-middleware.html # https://doc.scrapy.org/en/latest/topics/spider-middleware.html BOT_NAME = 'wangyiPro' SPIDER_MODULES = ['wangyiPro.spiders'] NEWSPIDER_MODULE = 'wangyiPro.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'wangyiPro (+http://www.yourdomain.com)' USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36' # Obey robots.txt rules ROBOTSTXT_OBEY = False # Configure maximum concurrent requests performed by Scrapy (default: 16) #CONCURRENT_REQUESTS = 32 # Configure a delay for requests for the same website (default: 0) # See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay # See also autothrottle settings and docs #DOWNLOAD_DELAY = 3 # The download delay setting will honor only one of: #CONCURRENT_REQUESTS_PER_DOMAIN = 16 #CONCURRENT_REQUESTS_PER_IP = 16 # Disable cookies (enabled by default) #COOKIES_ENABLED = False # Disable Telnet Console (enabled by default) #TELNETCONSOLE_ENABLED = False # Override the default request headers: #DEFAULT_REQUEST_HEADERS = { # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', # 'Accept-Language': 'en', #} # Enable or disable spider middlewares # See https://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'wangyiPro.middlewares.WangyiproSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { 'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543, } LOG_LEVEL = 'ERROR' # Enable or disable extensions # See https://doc.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'wangyiPro.pipelines.WangyiproPipeline': 300, } # Enable and configure the AutoThrottle extension (disabled by default) # See https://doc.scrapy.org/en/latest/topics/autothrottle.html #AUTOTHROTTLE_ENABLED = True # The initial download delay #AUTOTHROTTLE_START_DELAY = 5 # The maximum download delay to be set in case of high latencies #AUTOTHROTTLE_MAX_DELAY = 60 # The average number of requests Scrapy should be sending in parallel to # each remote server #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0 # Enable showing throttling stats for every response received: #AUTOTHROTTLE_DEBUG = False # Enable and configure HTTP caching (disabled by default) # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings #HTTPCACHE_ENABLED = True #HTTPCACHE_EXPIRATION_SECS = 0 #HTTPCACHE_DIR = 'httpcache' #HTTPCACHE_IGNORE_HTTP_CODES = [] #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
middlewares.py
# -*- 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 time import sleep from scrapy.http import HtmlResponse class WangyiproDownloaderMiddleware(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. 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 #拦截响应的对象(拦截下载器传递给Spider的响应对象) #request:响应对象对应的请求对象 #response:拦截到的响应对象 #spider:爬虫文件中对应的爬虫类的实例 def process_response(self, request, response, spider): # print(request.url+"这是下载中间件") #响应对象中存储页面数据的篡改 #spider.url_list可以提前拿出来 if request.url in['http://news.163.com/domestic/','http://news.163.com/world/','http://war.163.com/','http://news.163.com/air/']: # if request.url in spider.urls: # print('this is process_response!!!!!!!!!!!!!!!!!!!!!!!!!1') spider.bro.get(url=request.url) sleep(2) # js='window.scrollTo(0,documnet.body.scrollHeight)' # spider.bro.execute_script(js) # sleep(2) #缓冲加载数据,一定要给予浏览器一定的缓冲加载数据的时间 #页面数据就是包含了动态加载出来的新闻数据对应的页面数据 page_text=spider.bro.page_source return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request) # 实例化新的响应对象,作用域 else: return response
主要是五个文件的编写:
wangyi.py爬虫文件
middlewares.py
settings.py
items.py
pipelines.py
(9)