Wrapper Induction Generation for Extracting the Web Infomation
Tang Yanhong · Jisuanji gongcheng · 2003
The key component in the Web information integration system is the wrapper construction for each Web sites needed. To deal with this problem that existing HTLR class of wrapper is too restrict to the Web pages extracted and narrow the applicability, this paper extends the HTLR wrapper, presenting the DHTLR class of wrapper and the induction generation algorithm. The DHTLR wrapper improves the HTLR wrapper , so its more applicable and can be used in more Web sites.