网页编程网

# -*- coding: utf-8 -*-
import requests
from lxml import etree
import csv
headers={
'Referer':'https://image.baidu.com/search/index?',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/82.0.4068.4 Safari/537.36'
}
url='http://bj.ganji.com/zufang/'
response=requests.get(url,headers=headers)
#返回二进制形式，图片视频时用response.content
html=etree.HTML(response.text)
house_list=html.xpath('//div[@class="f-list js-tips-list"]/div')[1:]
with open('godd.csv','a',encoding='utf-8') as f:
    csv_writer=csv.writer(f,delimiter=',')
    for house in house_list:
        house_title=house.xpath('.//dd[@class="dd-item title"]/a/text()')[0]
        house_url=house.xpath('.//dd[@class="dd-item title"]/a/@href')[0]
        if not house_url.startswith('http'):
            house_url='http:'+house_url
        house_addr=house.xpath('.//span[@class="area"]/a[2]/span/text()')[0]
        house_price = house.xpath('//div[@class="price"]/span[1]/text()')[0]      
        csv_writer.writerow([house_title,house_addr,house_price,house_url])