1.新建Item
import scrapy
class zhaopinItem(scrapy.Item):
company = scrapy.Field() #公司
content = scrapy.Field() #内容要求
url = scrapy.Field() #链接
pay = scrapy.Field() #薪资
zhiwei = scrapy.Field() #职位
didian = scrapy.Field() #地点
(2)pipelines.py文件中添加json支持
import json
import codecs
class JsonWithEncodingCnblogsPipeline(object):
def __init__(self):
FILE_SOURCE = '/Users/DDD/PycharmProjects/truespider/truespider/Json/'
filname = '招聘.json'
true_path = FILE_SOURCE+filname
self.file = codecs.open(true_path,'w',encoding='utf-8')
self.first_item = True
def process_item(self,item,spider):
line = json.dumps(dict(item), ensure_ascii=False) + ",\n"
self.file.write(line)
return item