A Template-based Method for Theme Information Extraction from Web Pages
The introducing web page templates and DOM technology can effectively extract simple structured information from web information. In reference to previous research achievements of the foundation, this paper presents a new method of inductive web page templates. This method is able to contain various layout elements of the web page templates. The main research contents include the methods based on edit distance, about DOM document similarity judgment, clustering methods focus on web structure, the extraction methods of web page templates and programming a information extraction engine.
web extraction template method page ssimilarity web clustering
Gui-Sheng Yin Guang-Dong Guo Jing-Jing Sun
Department of Computer Science and Technology Harbin Engineering University
国际会议
太原
英文
721-725
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）