WICE- Web Informative Content Extraction

With the accelerated Internet development a huge amount of data have been accumulated and stored on the Web. Web pages usually contain various contents, which are relevant or irrelevant with the main topic. The extraction of useful or relevant information in mass information becomes more complex and time consuming. Identifying of useful data region is a significant problem for information extraction from the Web documents. In this paper, we propose a system that can extract informative or useful content from Web pages across different sites. XPath-based extraction rules are generated to facilitate later extraction from other similar pages. We have performed experimental studies by using real Web pages over several Web sites namely, commerce, and business directory and publication sites. The result of extraction accuracy is also compared with other prior research and then observed that extraction results proved the validity of the approach convincingly.