通常在使用爬虫时,爬取到网上的文章都是各式各样的格式处理起来比较麻烦,这里我们使用Apache-Tika来处理Excell格式的文章,如下:
packagecom.mengyao.tika.app; importjava.io.File; importjava.io.FileInputStream; importorg.apache.tika.metadata.Metadata; importorg.apache.tika.parser.ParseContext; importorg.apache.tika.parser.microsoft.ooxml.OOXMLParser; importorg.apache.tika.sax.BodyContentHandler; public classExcellApp { public static void main(final String[] args) throwsException { //Tika默认是10*1024*1024,这里防止文件过大导致Tika报错 BodyContentHandler handler = new BodyContentHandler(1024 * 1024 * 10); Metadata metadata = newMetadata(); FileInputStream inputstream = new FileInputStream(new File("D:/报价清单.xlsx")); ParseContext pcontext = newParseContext(); //解析Excell文档时应由超类AbstractParser的派生类OOXMLParser实现 OOXMLParser msofficeparser = newOOXMLParser(); msofficeparser.parse(inputstream, handler, metadata, pcontext); //获取Excell文档的内容 System.out.println("Excell文档内容:" +handler.toString()); //获取Excell文档的元数据 System.out.println("Excell文档元数据:"); String[] metadataNames =metadata.names(); for(String name : metadataNames) { System.out.println(name + " : " +metadata.get(name)); } } }