我用Python爬虫 爬取网页 爬出来获取特定数据 为什么大部分显示null 而且每次执行一次 数据就会增加一些 到底是代码问题还是网页问题 求大神指点代码下:
def get_content(self, html): #获取一个网页的内容
div_list = html.xpath("//div[contains(@class,'listtyle')]")
item_list = []
for div in div_list:
for b in range(1,19):
food_img= div.xpath("./div[@class='listtyle1'][b]/a[@class='big']/img[@class='img']/@src")
food_img=food_img[0] if len(food_img)>0 else None
food_name = div.xpath("./div[@class='listtyle1'][b]/a[@class='big']/div[@class='i_w']/div[@class='i']/div[@class='c1']/strong/text()")
food_name = food_name[0] if len(food_name)>0 else None
food_effect=div.xpath("./div[@class='listtyle1'][b]/a[@class='big']/strong[@class='gx']/span/text()")
food_effect = food_effect[0] if len(food_effect)>0 else None
food_time=div.xpath("./div[@class='listtyle1'][b]/a[@class='big']/div[@class='i_w']/div[@class='i']/div[@class='c2']/ul/li[@class='li1']/text()")
food_time = food_time[0] if len(food_time)>0 else None
food_taste=div.xpath("./div[@class='listtyle1'][b]/a[@class='big']/div[@class='i_w']/div[@class='i']/div[@class='c2']/ul/li[@class='li2']/text()")
food_taste = food_taste[0] if len(food_taste)>0 else None
food_commentnum_likenum=div.xpath("./div[@class='listtyle1'][b]/a[@class='big']/div[@class='i_w']/div[@class='i']/div[@class='c1']/span/text()")
food_commentnum_likenum = food_commentnum_likenum[0] if len(food_commentnum_likenum)>0 else None
item=dict(
food_img1=food_img,
food_name1=food_name,
food_effect1=food_effect,
food_time1=food_time,
food_taste1=food_taste,
food_commentnum_likenum1=food_commentnum_likenum,
)
item_list.append(item)
return item_list