def start_requests(self): for i in range(1,101): page=i*2-1 #這里是構(gòu)造請(qǐng)求url的page,表示奇數(shù) url=self.start_url+str(page) yield scrapy.Request(url,meta={'search_page':page+1},callback=self.parse_url) #這里使用meta想回調(diào)函數(shù)傳入數(shù)據(jù)，回調(diào)函數(shù)使用response.meta['search-page']接受數(shù)據(jù)

def parse_url(self,response): if response.status==200: #判斷是否請(qǐng)求成功 # print response.url pids = set() #這個(gè)集合用于過濾和保存得到的id,用于作為后面的ajax請(qǐng)求的url構(gòu)成 try: all_goods = response.xpath("http://div[@id='J_goodsList']/ul/li") #首先得到所有衣服的整個(gè)框架，然后從中抽取每一個(gè)框架 for goods in all_goods: #從中解析每一個(gè) # scrapy.shell.inspect_response(response,self) #這是一個(gè)調(diào)試的方法，這里會(huì)直接打開調(diào)試模式 items = JdSpiderItem() #定義要抓取的數(shù)據(jù) img_url_src = goods.xpath("div/div[1]/a/img/@src").extract() # 如果不存在就是一個(gè)空數(shù)組[]，因此不能在這里取[0] img_url_delay = goods.xpath(  "div/div[1]/a/img/@data-lazy-img").extract() # 這個(gè)是沒有加載出來的圖片，這里不能寫上數(shù)組取第一個(gè)[0] price = goods.xpath("div/div[3]/strong/i/text()").extract() #價(jià)格 cloths_name = goods.xpath("div/div[4]/a/em/text()").extract() shop_id = goods.xpath("div/div[7]/@ data-shopid").extract() cloths_url = goods.xpath("div/div[1]/a/@href").extract() person_number = goods.xpath("div/div[5]/strong/a/text()").extract() pid = goods.xpath("@data-pid").extract() # product_id=goods.xpath("@data-sku").extract() if pid:  pids.add(pid[0]) if img_url_src: # 如果img_url_src存在  print img_url_src[0]  items['img_url'] = img_url_src[0] if img_url_delay: # 如果到了沒有加載完成的圖片，就取這個(gè)url  print img_url_delay[0]  items['img_url'] = img_url_delay[0] # 這里如果數(shù)組不是空的，就能寫了 if price:  items['price'] = price[0] if cloths_name:  items['cloths_name'] = cloths_name[0] if shop_id:  items['shop_id'] = shop_id[0]  shop_url = "https://mall.jd.com/index-" + str(shop_id[0]) + ".html"  items['shop_url'] = shop_url if cloths_url:  items['cloths_url'] = cloths_url[0] if person_number:  items['person_number'] = person_number[0] # if product_id: # print "************************************csdjkvjfskvnk***********************" # print self.comments_url.format(str(product_id[0]),str(self.count)) # yield scrapy.Request(url=self.comments_url.format(str(product_id[0]),str(self.count)),callback=self.comments) #yield scrapy.Request寫在這里就是每解析一個(gè)鍵褲子就會(huì)調(diào)用回調(diào)函數(shù)一次 yield items except Exception: print "********************************************ERROR**********************************************************************" yield scrapy.Request(url=self.search_url.format(str(response.meta['search_page']),",".join(pids)),callback=self.next_half_parse) #再次請(qǐng)求，這里是請(qǐng)求ajax加載的數(shù)據(jù)，必須放在這里，因?yàn)橹挥械鹊降玫剿械膒id才能構(gòu)成這個(gè)請(qǐng)求，回調(diào)函數(shù)用于下面的解析

#分析異步加載的網(wǎng)頁 def next_half_parse(self,response): if response.status==200: print response.url items=JdSpiderItem() #scrapy.shell.inspect_response(response,self) #y用來調(diào)試的 try: lis=response.xpath("http://li[@class='gl-item']") for li in lis:  cloths_url=li.xpath("div/div[1]/a/@href").extract()  img_url_1=li.xpath("div/div[1]/a/img/@src").extract()  img_url_2=li.xpath("div/div[1]/a/img/@data-lazy-img").extract()  cloths_name=li.xpath("div/div[4]/a/em/text()").extract()  price=li.xpath("div/div[3]/strong/i/text()").extract()  shop_id=li.xpath("div/div[7]/@data-shopid").extract()  person_number=li.xpath("div/div[5]/strong/a/text()").extract()  if cloths_url:  print cloths_url[0]  items['cloths_url']=cloths_url[0]  if img_url_1:  print img_url_1[0]  items['img_url']=img_url_1  if img_url_2:  print img_url_2[0]  items['img_url']=img_url_2[0]  if cloths_name:  items['cloths_name']=cloths_name[0]  if price:  items['price']=price[0]  if shop_id:  items['shop_id']=shop_id[0]  items['shop_url']="https://mall.jd.com/index-" + str(shop_id[0]) + ".html"  if person_number:  items['person_number']=person_number[0]  yield items #又一次的生成，這里是完整的數(shù)據(jù)，因此可以yield items except Exception: print "**************************************************"