Abstract: This paper introduces a method based on tag path to extract Web structured data．The method gets complete tag path collection by parsing the DOM tree of the Web document．Clustering of tag paths is performed based on introduced similarity measure and the data area can be targeted,then taking advantage of features of tag position,we can separate and filter record,finally complete data extraction．Experiments show that this method achieves higher precision and recall than the MDR when dealing with the page containing the structured data.

Key words: Tag path,Extracting structured data,Clustering