爬取58二手房

import requests
from lxml import etree

import csv

url = 'https://www.58.com/ershoufang/'
headers ={
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
    }
#爬取页面源码数据
response = requests.get(url=url,headers=headers).text
#数据解析
tree = etree.HTML(response)
#通过页面分析，获取了所有tr标签的对象
tr_list = tree.xpath('//table[@class="tbimg"]/tr')
fp = open('./58.txt','w',encoding='utf-8')

content = []
for tr in tr_list:
    #1.房屋基本信息    
    cont = tr.xpath('./td[2]/a/text()')[0]  #之前获取的是单个列表数据，使用[0]表示获取该列表中的第一个字符串
    #2.价格
    prices = tr.xpath('./td[3]/b/text()')[0]
    #3.居室
    house = tr.xpath('./td[4]/text()')[0]   
    #4.大小
    size = tr.xpath('./td[5]/b/text()')[0] 
    content.append([cont,prices,house,size])
#存储CSV
with open('./58.csv','w',encoding='utf-8') as fp:
    writer =csv.writer(fp)
    writer.writerow(['房屋基本信息','价格','居室','大小'])
    for row in content:
        writer.writerow(row)