python爬虫学习-scrapy爬取链家房源信息并存储

爬取链家租房页面第一页的房源信息，获取内容包括：标题、价格、URL

items.py

import scrapy


class ScrapytestItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    price = scrapy.Field()
    url = scrapy.Field()

pipelines.py

import json

class ScrapytestPipeline(object):
    #打开文件
    def open_spider(self,spider):
        self.file = open('58_chuzu.txt','w',encoding='utf-8')
        print('文件被打开了')
    
    #写入文件
    def process_item(self, item, spider):
        line = '{}\n'.format(json.dumps(dict(item),ensure_ascii=False))
        self.file.write(line)
        return item
    
    #关闭文件
    def close_spider(self,spider):
        self.file.close()
        print('文件被关闭了')

spider

import scra