Web Site Mining Using Entropy Estimation

With the unstable growth of the Web, there is an ever-Increasing volume of data and information published in numerous Web pages. Web mining aims to develop new techniques to effectively extract and mine useful knowledge or information from these Web pages. And allows user to easily locate desired object from huge data. In this paper, we propose simple web site mining technique by mining product information from the pages of the e-commercial web site. For this we are taking the benefits of hierarchical structure of HTML language. First it discovers the set of product descriptions based on the measure of entropy at each node in the HTML tag tree of the retrieved web page. Afterward, a set of association rules based on heuristic features is employed for more accuracy in the product extraction.