关键词: 簇 数据挖掘 信息抽取

Abstract:

This paper introduees the technology of wrapper and clustering. When we do not know their data sources, we will segment the web pages containing tags   and search the data section we care without artificial interference. Finally we take advantage of matching and indexing in order to extract information  and put them into databases. By studying the second search and data mining, we can search and extract data so as to offer individualized information wit  hout knowing the data source.

Key words: clustering, data mining, information extraction