@incollection{, 64B1FD693C4097A27D1BEF937694C7AA , author={{Dr. M. Lavanya} and {Dr.M.UshaRani} and {Sree Vidyanikethan Engineering College}}, journal={{Global Journal of Computer Science and Technology}}, journal={{GJCST}}0975-41720975-435010.34257/gjcst, address={Cambridge, United States}, publisher={Global Journals Organisation}1251321 } @book{b0, , title={{of Network and Mobile Technologies}} , year={2010} 1 } @incollection{b1, , title={{HTML Page Analysis Based on Visual Cues}} , author={{ YYang } and { HZhang }} , booktitle={{6th International Conference on Document Analysis and Recognition}} Seattle, Washington, USA , year={2001} } @incollection{b2, , title={{Visual Segmentation-Based Data Record Extraction from Web Documents}} , author={{ LongzhuangLi } and { YonghuaiLiu } and { AbelObregon }} , booktitle={{IEEE International Conference on Information Reuse and Integration}} , year={2007} } @book{b3, , title={{}} , author={{ QingshuiLi }} } @incollection{b4, , title={{Study of Web Page Information topic extraction technology based on vision}} , author={{ KaiWu }} , booktitle={{IEEE International Conference on Computer Science and Information Technology (ICCSIT)}} , year={2010} 9 } @book{b5, , title={{Modern Information Retrieval}} , author={{ RBYates } and { BRNeto }} , year={1999} , publisher={Addison-Wesley} , address={New York} } @incollection{b6, , title={{Fast and effective text mining using linear-time document clustering}} , author={{ BLarsen } and { CAone }} , booktitle={{Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}} the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , year={1999} } @book{b7, , title={{}} , author={{ ChenHong } and { -Ping; Fang Wei; YangZhou }} , note={Zhuo Lin} } @incollection{b8, , title={{Automatic Data Records Extraction from List Page in Deep Web Sources}} , author={{ CuiZhi-Ming }} , journal={{Asia-Pacific Conference on Information Processingvol}} 1 , year={2009} } @incollection{b9, , title={{Automatic text summarization based on sentences clustering and extraction}} , author={{ ZhangPei-Ying } and { LiCun-He }} , booktitle={{2nd IEEE International Conference on Computer Science and Information Technology}} , year={2009} } @incollection{b10, , title={{ECON: An Approach to Extract Content from Web News Page}} , author={{ YanGuo } and { HuifengTang } and { LinhaiSong } and { YuWang } and { GuodongDing }} , booktitle={{Proceedings of the 12th International Asia-Pacific Web Conference (APWEB)}} the 12th International Asia-Pacific Web Conference (APWEB) , year={April 06-April 08 Buscan, Korea, 2010} } @incollection{b11, , title={{ViDE: A Vision-Based Approach for Deep Web Data Extraction}} , author={{ WeiLiu } and { XiaofengMeng } and { WeiyiMeng }} , journal={{IEEE Transactions on Knowledge and Data Engineering}} 22 3 , year={2010} } @incollection{b12, , title={{Employing Clustering Techniques for Automatic Information Extraction from HTML Documents}} , author={{ FAshraf } and { TOzyer } and { RAlhajj }} , journal={{IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews}} , editor={14. Manisha Marathe, Dr. S.H.Patil, G.V.Garje,M.S.Bewoor} 38 5 , year={2008. November 2009} , note={International Journal of Recent Trends in Engineering} } @incollection{b13, , title={{Automatic Extraction of Informative Blocks from WebPages}} , author={{ SandipDebnath } and { PrasenjitMitra } and { CLeeGiles }} , booktitle={{Proceedings of the ACM symposium on Applied computing}} the ACM symposium on Applied computingSanta Fe, New Mexico , year={2005} } @incollection{b14, , title={{Web page cleaning for web mining through feature weighting}} , author={{ LanYi } and { BingLiu }} , booktitle={{Proceedings of the 18th international joint conference on Artificial intelligence}} the 18th international joint conference on Artificial intelligenceAcapulco, Mexico , year={August 09 -15. 2003} } @incollection{b15, , title={{An Efficient Method of Eliminating Noisy Information in Web Pages for Data Mining}} , author={{ KTripathy } and { AKSingh }} , booktitle={{Proceedings of the Fourth International Conference on Computer and Information Technology}} the Fourth International Conference on Computer and Information Technology , year={2004} } @book{b16, , title={{A method of eliminating noises in Web pages by style tree model and its applications}} , author={{ ZhaoCheng } and { -Li } and { YiDong-Yun }} , year={2004} , publisher={Springer} 9 Wuhan University Journal of Natural Sciences, Wuhan University } @incollection{b17, , title={{Learning Block Importance Models for Web Pages}} , author={{ RuihuaSong } and { HaifengLiu } and { Ji-RongWen } and { Wei-YingMa }} , booktitle={{Proceedings of the 13th international conference on World Wide Web}} the 13th international conference on World Wide WebNew York, NY, USA , year={2004} } @incollection{b18, , title={{Learning Important Models for Web Page Blocks based on Layout and Content Analysis}} , author={{ RuihuaSong } and { HaifengLiu } and { Ji-RongWen } and { Wei-YingMa }} , journal={{ACM SIGKDD Explorations Newsletter}} 6 2 , year={2004. 2-57, 1973} }