Abstract—World Wide Web (WWW) is now a famous medium by which people all around the world can spread and gather information of all kind. However, there is large amount of irrelevant redundant and information on web pages also. Such information makes various web mining tasks web page crawling, web page classification, link based ranking and topic distillation complex. Previously, the relevant content was extracted only from textual part of web pages. But now-a-days the content on web page is not only in the text form but also as an image, video or audio. This paper proposes an improved algorithm for extracting informative content from web pages i.e. it extracts the relevant content not only as text but also as images, videos, audios, adobe flash files and online games. Experiments were conducted on different real websites show that precision and recall values of our approach is superior to the previous Word to Leaf Ratio approach.
 

Cite: Aanshi Bhardwaj and Veenu Mangat, "An Improvised Algorithm for Relevant Content Extraction from Web Pages," Journal of Emerging Technologies in Web Intelligence, Vol. 6, No. 2, pp. 226-230, May 2014. doi:10.4304/jetwi.6.2.226-230