| 作成者 |
|
|
|
|
|
| 本文言語 |
|
| 出版者 |
|
| 発行日 |
|
| 収録物名 |
|
| 巻 |
|
| 号 |
|
| 開始ページ |
|
| 終了ページ |
|
| 出版タイプ |
|
| アクセス権 |
|
| 概要 |
Due to the explosive growth and popularity of the deep web, information extraction from deep web page has gained more and more attention. However, the HTML structure of web page has become more compli...cated, making it difficult to recognize target content by only analyzing the HTML source code. In this paper, we propose a method to extract the informative blocks from a deep web using the layout feature. We consider the visual rectangular region of an HTML element as a visual block in web page. We transform the elements’ layout of a visual block into a layout tree. By calculating the similarity of layout trees, we cluster the visual blocks that have similar layout feature. Finally, the cluster which has the largest area is extracted as the informative block cluster. The experiment results show that this method is optimal when the threshold of layout tree similarity is 0.4続きを見る
|
Mendeley出力
hirokawa_19