爬取链家网站中的租房信息

最新推荐文章于 2024-10-19 23:42:06 发布

原创最新推荐文章于 2024-10-19 23:42:06 发布 · 792 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#爬虫 #python #数据挖掘

爬取链家网站中的租房信息

信息爬取代码

信息爬取代码

import requests
from lxml import etree
import pandas as pd

with open('zufang.csv', 'a+') as fp:
    str1 = '区域' + ',' + '小区名称' + ',' + '面积(㎡)' + ',' + '户型' + ',' + '价格(元/月)'+'\n'
    fp.write(str1)
    for i in range(0,101):
        url="https://bj.lianjia.com/zufang/pg{}".format(i)
        data=requests.get(url)
        data.encoding='utf-8'
        html = etree.HTML(data.text)
        for x in range(1,31):
            place_data=html.xpath("/html/body/div[3]/div[1]/div[5]/div[1]/div[1]/div[%d]/div/p[2]/a[1]"%(x))
            park_data=html.xpath("/html/body/div[3]/div[1]/div[5]/div[1]/div[1]/div[%d]/div/p[2]/a[3]"%(x))
            area_data=html.xpath("/html/body/div[3]/div[1]/div[5]/div[1]/div[1]/div[%d]/div/p[2]/text()[5]"%(x))
            kind_data=html.xpath("/html/body/div[3]/div[1]/div[5]/div[1]/div[1]/div[%d]/div/p[2]/text()[7]"%(x))
            price_data=html.xpath("/html/body/div[3]/div[1]/div[5]/div[1]/div[1]/div[%d]/div/span/em"%(x))
            list=[]
            placelist=[]
            parklist=[]
            arealist=[]
            kindlist=[]
            pricelist=[]
            for i in place_data:
                placelist.append(i.text)
            print(placelist[0])
            for i in park_data:
                parklist.append(i.text)
            print(parklist[0])
            for i in area_data:
                arealist.append(i)
            print(arealist[0].strip())
            for i in kind_data:
                kindlist.append(i)
            print(kindlist[0].strip())
            for i in price_data:
                pricelist.append(i.text)
            print(pricelist[0])
            str=placelist[0]+','+parklist[0]+','+arealist[0].strip()+','+kindlist[0].strip()+','+pricelist[0]+'\n'
            fp.write(str)