There is large volume of information available to be mined from the World Wide Web. The information on the Web is contained in the form of structured and unstructured objects, which is known as data records. Such data records are important because essential information are available in these host pages, e.g., lists of products and there detail information. It is necessary to extract such data records to provide relevance information to user as per their requirements. Some of the approaches used to solve this problem are manual approach, supervised learning, and automatic techniques.