一、保存数据格式为json

maintian.py
# -*- coding: utf-8 -*-
import scrapy

from MainTian.items import MaintianItem


class MaintianSpider(scrapy.Spider):
    """
    爬虫名字,可以根据name运行项目 1.scrapy crawl maitian
    第二种运行方式运行这个maintian.py文件:scrapy runspider maintian.py
    """
    name = 'maitian'

    # 爬取的域名范围
    allowed_domains = ['maitian.cn']

    # 开始的url
    start_urls = ['http://bj.maitian.cn/zfall/R2C55']

    # 解析方法
    def parse(self, response):
        item = MaintianItem()
        item['title'] = response.xpath('/html/body/section[2]/div[2]/div[2]/ul/li[1]/div[2]/h1/a/text()').extract()[
            0].strip()
        item['price'] = \
            response.xpath('/html/body/section[2]/div[2]/div[2]/ul/li[1]/div[2]/div/ol/strong/span/text()').extract()[
                0].strip()
        print(item)

        # 把数据返回给管道
        return item
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 MaintianItem(scrapy.Item):
    """
    定义数据格式
    """
    # name = scrapy.Field()
    title = scrapy.Field()
    price = 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

# JSON导出器，导出来的json文件
from scrapy.exporters import JsonItemExporter


class MaintianPipeline(object):
    def process_item(self, item, spider):
        """
        item值是方法def parse(self, response):return item返回的
        :param item:
        :param spider:
        :return:
        """
        # 1.写入的文件对象
        flie = open('maitian.json', 'wb')
        # 2.创建 导出器
        exporter = JsonItemExporter(flie)
        # 3.开启 导出器
        exporter.start_exporting()
        # 4.导出数据
        exporter.export_item(item)
        # 5.关闭 导出器
        exporter.finish_exporting()
        # 6.关闭文件
        flie.close()
        return item