A generic Web news extraction approach

With the development of the Internet, the Web is becoming the largest data repository ever available in the history of humankind. Major efforts have been made in order to provide efficient access to relevant information within the web pages. Most previous works rely on the template of the web sites. When information like news needs to be extracted from different sites, it must create a template for every site which will spend much time and huge cost. In this paper, we present a generic news extraction method to easily identify news content based on a set of combined heuristics and to exact every part of news according to a predefined schema. Experimental results indicate that our approach is effective in extracting news across websites.