Discovering Informative Blocks from Web Pages for Efficient Information Extraction using DOM tree

A webpage generally contains data along with navigation panels, advertisements, copyright and privacy notices. Except data these other things do not contain any important information. These blocks can be called as non-informative blocks. As these blocks are non-informative, they can affect the result of web data mining. To avoid this, it is important to separate the main data i.e. informative blocks and non-informative blocks from the web page. In a website these non-informative blocks are generally present in different web pages and have same format. Also, the data contained in these blocks is also same. In case of informative blocks, data contained by the block and their format are different. We need a structure at site level to capture the same format of the blocks and the data present in the blocks. DOM Tree structure is available at page level. Many tools are available to construct a DOM Tree of a webpage. But DOM Tree structure is not useful at site level. So, we need to construct a Site Style Tree (SST) for a website. After analyzing this SST, we can identify which part of SST is informative and which is non-informative. There is no tool available to construct a style tree for a given website. This work aims at constructing a style tree for given website and separating informative and non-informative blocks from the website.