Retrieving similar websites and web pages

Similar web pages are pages that are about the same topic and of the same type. Sites about soccer clubs are related with all the soccer websites, but only similar with other soccer clubs. The goal of this research is to find an approach which, based on the textual content, can find similar pages given a page. The method used for this approach is a twofold method. The first task is trying to find similar websites, the second task is to find similar pages on those similar websites. Similarity is based on the textual content and use keyword extraction to identify the main topics. The tf*idf measure is used to identify the best keywords. For calculating the similarity between two pages the Cosine Similarity measure is used. The conceived approach gives some satisfying results for finding related websites and similar pages, finding similar websites is a difficult task. The conclusion of this research is that it is hard to find similar websites only based on the textual content. Finally, there are some suggestions given for further improvements.