python 爬取Q房網信息

首先找到爬取網站
https://beijing.qfang.com/newhouse/list/n1

箭頭點擊,XPath下來你的要爬取的信息

把你要爬取的信息記錄下來

寫入代碼

from lxml import etree
import requests
import csv
import time

#寫一個函數


# def writecsv(item):
#     with open('qfang.csv','a',encoding= 'utf-8') as f:
#         write=csv.writer(f)
#         #防止出錯
#         try:
#              write.writerow(item)
#         except:
#             print('write error!')

if __name__ =='__main__':
    headers ={'user-Agent':'Mozilla/5.0'}
    start_url="https://beijing.qfang.com/newhouse/list/n"
    for x in range(1,9):
        url =start_url+str(x)
        #獲取網址
        html =requests.get(url,headers=headers)
        #不能頻繁獲取請求
        time.sleep(1)
        #構造一個選擇器,把文本源代碼傳給它
        selector= etree.HTML(html.text)
        xiaoqulist =selector.xpath('/html/body/div[4]/div/div[1]/div[4]/ul/li')
        #循環迭代
        for xiaoqu in xiaoqulist:
            try:
                mingcheng =xiaoqu.xpath('div[2]/div[1]/a/em/text()')[0]
                layout=xiaoqu.xpath('div[2]/div[2]/p[3]/a/text()')[0]
                area=xiaoqu.xpath('div[2]/div[3]/p[1]/text()')[0]
                place=xiaoqu.xpath('div[2]/div[3]/p[3]/text()')[0]
                money=xiaoqu.xpath('div[3]/p[2]/text()')[0]
            except IndexError as a:
                print(" ")

            # #構造一個list
            #item =[mingcheng,layout,area,place,money]

            # #寫一個函數
            #writecsv(item)
            #保存就print
            print('正在抓取:',mingcheng,layout,area,place,money)

你要爬取的信息