earticle

영어

Eliminating noisy information and extracting information content from web pages are increasing to become an important research issue in information retrieval field. In this paper, we present an approach of information extraction based on Dom tree and weight value calculation, which contains the following steps, parse the web page to construct the Dom tree, extract the title and keywords, calculate the weight value and obtain the content. The experimental result shows that this method has the higher accuracy ratio by the various themes content extraction.