Catastrophe 2020-05-07
items.py
class LianhezaobaospyderItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# pass
body=scrapy.Field()
link=scrapy.Field()爬虫.py
from .. import items
def parse_news(self,response):
item=items.LianhezaobaospyderItem()
item[‘body‘]=response.xpath("//div[@class=‘xx‘]/text()").get()
item[‘link‘]=response.url
yield itemitem和字典类似,数据量大时,字典可能键值对错误