scrapy爬取 素材网

spiders.py

# -*- coding: utf-8 -*- import scrapy # 引入数据模型类 from ..items import ImgItem class SucaiSpider(scrapy.Spider): name = 'sucai' allowed_domains = ['sc.chinaz.com'] start_urls = ['http://sc.chinaz.com//'] def parse(self, response): # 200 OK 请求成功 # 302 重定向 # 404 url地址不存在 # 403 没有权限访问，服务器拒绝连接 # 5XX 服务器的错误 # 找到图标的链接 tb_href = response.xpath('//div[@class="nav"]/ul/li[@class="nos"]/a[3]/@href').extract_first('') # 拼接完整的url tb_url = 'http://sc.chinaz.com'+tb_href # 发送一个请求 # 1.url请求的地址 2.callback 回调函数 默认调用parse() yield scrapy.Request( url=tb_url, callback=self.parse_list ) # 解析所有图标列表 def parse_list(self,response): # 根据xpath找到所有图标详情页的地址 detail_links = response.xpath('//ul[@class="pngblock imgload"]/li/p/a/@href').extract() # for循环遍历列表，取出每一个图片的详细地址，发起请求 for link in detail_links: yield scrapy.Request( url=link, # 请求成功了，调用parse_detail解析详情 callback=self.parse_detail, # 用于请求数据时，携带一些额外的参数 meta={'hello':'world'} ) # 找到下一页的链接 next_href = response.xpath('//a[@class="nextpage"]/@href').extract_first('') # 判断是否有下一页 if next_href: # 拼接下一页的地址 next_url = 'http://sc.chinaz.com/tubiao/'+next_href yield scrapy.Request( url=next_url, callback=self.parse_list ) # 解析详情页中的每一张图片地址 def parse_detail(self,response): # 解析图片分类名称 categray = response.xpath('//h2/a/text()').extract_first('') # 解析图片地址 imgs_src = response.xpath('//div[@class="png_pic"]/img/@src').extract() # for循环遍历所有图片的详细地址 for src in imgs_src: # 创建数据模型对象 img = ImgItem() # src图片下载地址必须放在列表中 img['src'] = [src] # 图片分类 img['categray'] = categray yield img

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 SucaiSpiderItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() pass # 新建图片的数据模型 class ImgItem(scrapy.Item): # 图标的下载地址 src = scrapy.Field() # 图标的分类 categray = 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 # 引入scrapy自带的图片下载类 from scrapy.pipelines.images import ImagesPipeline # 引入scrapy import scrapy class SucaiSpiderPipeline(object): def process_item(self, item, spider): return item # 1.下载图片 2.指定图片存放目录 # 继承于scrapy自带的图片下载类 class MyImagePipeline(ImagesPipeline): # 获取图片下载请求的函数 def get_media_requests(self, item, info): # 1.取出图片下载的url地址 url = item['src'][0] # 2.根据url地址创建请求对象 request = scrapy.Request( url=url, # 利用meta将item传递到file_path函数中 meta={"item":item} ) # 最终返回一个下载图片的请求对象的列表 return [request] # 重写file_path指定图片存放路径 def file_path(self, request, response=None, info=None): # 根据key取出meta中的item，这个item中包含的就是下载图片的数据 item = request.meta['item'] # 取出分类 categray = item['categray'] # 取出图片下载地址 src = item['src'][0] # 分割获取图片名称 name = src.split('/')[-1] # 最终只需要将图片的存放路径和图片的名称返回即可 return '%s/%s'%(categray, name)

settings.py

# -*- coding: utf-8 -*- # Scrapy settings for SuCai_Spider 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 = 'SuCai_Spider' SPIDER_MODULES = ['SuCai_Spider.spiders'] NEWSPIDER_MODULE = 'SuCai_Spider.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'SuCai_Spider (+http://www.yourdomain.com)' # 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 = { # 'SuCai_Spider.middlewares.SucaiSpiderSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'SuCai_Spider.middlewares.SucaiSpiderDownloaderMiddleware': 543, #} # 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 = { 'SuCai_Spider.pipelines.MyImagePipeline': 300, # 'scrapy.pipelines.images.ImagesPipeline': 200 } # 指定图片的下载地址是item的哪个属性 IMAGES_URLS_FIELD = 'src' # 指定图片存放的路径 IMAGES_STORE = 'imgs' # 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'

debug.py

# coding: utf-8 # 引入cmdline中的execute函数 from scrapy.cmdline import execute # 执行启动爬虫的命令 execute(['scrapy', 'crawl', 'sucai'])

middleware.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 class SucaiSpiderSpiderMiddleware(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) class SucaiSpiderDownloaderMiddleware(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 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): # Called with the response returned from the downloader. # Must either; # - return a Response object # - return a Request object # - or raise IgnoreRequest 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)

scrapy startproject name scrapy genspider name url