从链家网上爬取租房数据并进行数据分析

数据爬取(scrapy)

# 创建工程
scrapy startproject lianjia
cd lianjia
scrapy genspider gethouse www.xxx.com

items.py

import scrapy


class LianjiaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name = scrapy.Field()
    community = scrapy.Field()
    area = scrapy.Field()
    house_type = scrapy.Field()
    acreage = scrapy.Field()
    price = scrapy.Field()

gethouse.py

import scrapy
from ..items import LianjiaItem
import re
page = 100
areas = ['dongcheng', 'xicheng', 'haidian', 'chaoyang']


class GethouseSpider(scrapy.Spider):
    name = 'gethouse'
    # allowed_domains = ['www.xxx.com']
    start_urls = []
    for area in areas:
        for i in range(1, page+1):
            start_urls.append('https://bj.lianjia.com/zufang/{}/pg{}/'.format(area, i))

    def parse(self, response)