Extracting News Information Based on Webpage Segmentation and Parsing DOM Tree Reversely

Abstract

Abstract.A new method of extracting news information based on webpage segmentation and parsing DOM tree reversely is presented and implemented in this paper, which intends to effectively extract news information for data mining. The method is proposed to get webpages' main DOM structure by segmenting webpages, further parse the main DOM structure reversely and finally extract news content, headlines, news agents and publication time. The experimental results show that the proposed method has achieved good performance on accuracy and meets the project demands.