Semantic Similarity Based Focused Crawling

Finding useful information from the Web which has a large and distributed structure requires efficient search strategies. Distributed and dynamic nature of Web resources is a major problem for search engines maintain up-to-date index of the Web content as they have to crawl the Web periodically. A focused or topic-driven crawler is a specific type of crawler that analyzes its crawl boundary to find the links that are likely to be most relevant for the crawl while avoiding irrelevant regions of the Web. Yet many types of crawlers have been suggested that are usually different in their crawl strategy. The most important difference is in prioritizing links to download. To do this, focused crawler has an algorithm for classifying. In this paper we propose a new algorithm used to classify in focused crawlers. Our algorithm is based on page contents and uses a semantic classification.