selenium在scrapy中使用&爬取网易新闻
selenium在scrapy中的使用
示例:
需求:爬取网易新闻中的国内、国际,二个板块下所有的新闻数据(标题+内容)
爬取网站分析:
首页需要爬取2个板块对应的url,没有动态加载的数据
每一个板块对应的页面中新闻标题是【动态加载】,爬取新闻标题+详情页面的url
动态加载的数据,通过selenium来获取满足需求的响应数据,将其篡改到响应对象
每一条新闻详情页面中的数据不是动态加载,爬取的新闻内容
selenium在scrapy中使用流程
- 在爬虫类中实例化一个浏览器对象,将其作为爬虫类的一个属性
- 在中间中实现浏览器自动化相关的操作
- 在爬虫类中重写closed(self,spider),在其内部关闭浏览器对象
spider.py
import scrapy from selenium import webdriver from myspider01.items import Myspider01Item class NewsSpider(scrapy.Spider): name = 'news' # allowed_domains = ['www.baidu.com'] start_urls = ['https://news.163.com/'] model_urls = [] # 实例化一个全局浏览器对象 bro_obj = webdriver.Chrome() bro_obj.maximize_window() # 数据解析:每一个版块对应的url def parse(self, response): url_list = response.xpath('//*[@id="index2016_wrap"]/div[2]/div[2]/div[2]/div[2]/div/ul/li/a/@href') li_index = [1, 2] for index in li_index: print(index) self.model_urls.append(url_list[index].get()) # 对每一个版块对应url发起请求 print(self.model_urls) for url in self.model_urls: yield scrapy.Request(url, callback=self.parse_model) # 数据解析:新闻标题+新闻详情页面的url(动态加载数据) def parse_model(self, response): dev_list = response.xpath('/html/body/div/div[3]/div[3]/div[1]/div[1]/div/ul/li/div/div/div/div[1]/h3/a') for div in dev_list: title = div.xpath('./text()').get() new_detail_url = div.xpath('./@href').get() print("new_detail_url", new_detail_url) if new_detail_url: item = Myspider01Item() item["title"] = title yield scrapy.Request(url=new_detail_url, callback=self.parse_new_detail, meta={"item": item}) def parse_new_detail(self, response): """ 解析新闻内容,不涉及动态加载数据 :param response: :return: """ content = response.xpath('//*[@id="content"]/div[2]/p/text()').extract() content = "".join(content) item = response.meta["item"] item["content"] = content yield item def closed(self, spider): self.bro_obj.quit()
piplines.py
# Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html # useful for handling different item types with a single interface from itemadapter import ItemAdapter class WangyiPipeline: def process_item(self, item, spider): print("进入",item) return item
items.py
# Define here the models for your scraped items # # See documentation in: # https://docs.scrapy.org/en/latest/topics/items.html import scrapy class WangyiItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() title = scrapy.Field() content = scrapy.Field()
middlewares.py
# Define here the models for your spider middleware # # See documentation in: # https://docs.scrapy.org/en/latest/topics/spider-middleware.html from time import sleep from scrapy import signals # useful for handling different item types with a single interface from itemadapter import is_item, ItemAdapter class WangyiSpiderMiddleware: # 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, 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 Request 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) class WangyiDownloaderMiddleware: # 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 return None def process_response(self, request, response, spider): # 所有的响应对象中找出需要篡改的2个响应对象,篡改响应内容 if request.url in spider.model_urls: bro = spider.bro # selenium中webdriver的浏览器对象 # response指不满足需求的2个响应对象 # 篡改响应数据:首先获取满足需求的响应数据,将其篡改到响应对象 # 满足需求的响应数据就可以使用selenium获取 bro.get(request.url) # 使用selenium对五个板块的url发起请求 sleep(2) bro.execute_script('window.scrollTo(0,document.body.scrollHeight)') sleep(1) # 捕获到板块页面中加载出来的全部数据 page_text = bro.page_source # 方法1 # response.text = page_text # return response # 方法2 from scrapy.http import HtmlResponse # scrapy封装好的响应类 # 返回了一个新的响应对象,使用新的响应对象,替换原来不满足需求的响应对象 return HtmlResponse(url=request.url, body=page_text, encoding="utf-8", request=request) else: 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)
settings.py
# Scrapy settings for wangyi project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://docs.scrapy.org/en/latest/topics/settings.html # https://docs.scrapy.org/en/latest/topics/downloader-middleware.html # https://docs.scrapy.org/en/latest/topics/spider-middleware.html BOT_NAME = 'wangyi' SPIDER_MODULES = ['wangyi.spiders'] NEWSPIDER_MODULE = 'wangyi.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'wangyi (+http://www.yourdomain.com)' USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36' # Obey robots.txt rules ROBOTSTXT_OBEY = False LOG_LEVEL = "ERROR" # 定义只输出错误的日志 # 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'wangyi.middlewares.WangyiSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { 'wangyi.middlewares.WangyiDownloaderMiddleware': 543, } # Enable or disable extensions # See https://docs.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See https://docs.scrapy.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'wangyi.pipelines.WangyiPipeline': 300, } # Enable and configure the AutoThrottle extension (disabled by default) # See https://docs.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://docs.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'