Web consist of vast chunks of information on Web sites the user can retrieve this information by using search input query to Web databases & obtain the relevant information. Web databases return the multiple search records dynamically on browser, these search records contain the Deep Web pages in the form of HTML pages. The conventional search engine does not index the hidden Web pages from Web databases. Several existing techniques have addressed the problem of how to extract efficient structure data from Deep Web. The deep web refers to the hidden database used by web sites. But the information extraction & annotation is key challenge in web mining. The retrieval of information should be done automatically & arrange in a systematic way for processing. Different techniques like wrapper induction is been induced. Various types of annotators are used on the basis of the data to be labeled. This paper describes the automatic annotation approach on the basis of different feature of text node and data units.