摘要
文章使用Python爬虫并结合数据分析技术,对链家网上南京二手房的所有房源数据进行采集、清洗,再对清洗后的数据进行可视化分析,研究隐藏在这些海量数据背后的规律。由此可获得南京二手房的基本属性特征以及二手房源的分布情况,起到购房决策辅助作用。
This paper uses Python crawler and data analysis technology to collect and clean all the house source data of Nanjing second-hand house on lianjia.com,and then the cleaned data is analyzed and visualized to study the laws hidden behind it.By doing so,the basic attribute characteristics of second-hand house and the distribution of second-hand house in Nanjing can obtained,which plays an auxiliary role in the decision-making of house purchase.
作者
戴瑗
郑传行
Dai Yuan;Zheng Chuanxing(School of information,Guizhou university of F&E,Guiyang,Guizhou 550025,China)
出处
《计算机时代》
2021年第1期37-40,45,共5页
Computer Era
基金
贵州省科技计划项目(黔科合基础[2019]1054号)。
