import scrapy


class MaitianItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title= scrapy.Field()
    price = scrapy.Field()
    area = scrapy.Field()
    district = scrapy.Field()

ITEM_PIPELINES={‘maitian.pipelines.MaitianPipeline‘:300,}

MONGODB_HOST=‘127.0.0.1‘
MONGODB_PORT=27017
MONGODB_DBNAME=‘maitian‘
MONGODB_DOCNAME=‘zufang‘

import pymongo

import settings

class MaitianPipeline(object):
    def __init__(self):
        host=settings.MONGODB_HOST
        port= settings.MONGODB_PORT
        db_name = settings.MONGODB_DBNAME
        client=pymongo.MongoClient(host=host,port=port)
        db=client[db_name]
        self.post=db[settings.MONGODB_DOCNAME]

    def process_item(self, item, spider):
        zufang=dict(item)
        self.post.insert(zufang)
        return item

import scrapy
import sys
import os
# 将 项目的根目录添加到sys.path中
BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(BASE_DIR)
from items import MaitianItem

class MaitianSpider(scrapy.Spider):
    name="zufang"
    start_urls=["http://bj.maitian.cn/esfall"]

    def parse(self, response):
        for zufang_item in response.xpath(‘//div[@class="list_title"]‘):
            yield {
                ‘title‘:zufang_item.xpath(‘./h1/a/text()‘).extract_first(),
                ‘price‘: zufang_item.xpath(‘./div[@class="the_price"]/ol/strong/span/text()‘).extract_first(),
                ‘area‘: zufang_item.xpath(‘./p/span[1]/text()‘).extract_first(),
                ‘district‘: zufang_item.xpath(‘./p/text()‘).re(r‘昌平|朝阳|东城|大兴|房山|丰台|海淀|门头沟|平谷|石景山|顺义|通州|西城‘)[0],
            }
        next_page_url=response.xpath(‘//div[@id="paging"]/a[@class="down_page"]/@href‘).extract_first()
        if next_page_url is not None:
            yield scrapy.Request(response.urljoin(next_page_url))