读取文件方式.docVIP

/blog/451564 JAVA读取WORD,EXCEL,PDF,TXT,RTF,HTML文件文本内容的方法示例 ? 以下是Java对几种文本文件内容读取代码。其中，OFFICE文档（WORD,EXCEL）使用了POI控件，PDF使用了PDFBOX控件。 ? 点击这里 查看相关控件的下载地址和配置方法。 ? ? ? WORD Java代码 package?textReader; ?? import?java.io.*; ?? import?org.apache.poi.hwpf.extractor.WordExtractor; ?? ?? public?class?WordReader?{ ?? ????public?WordReader(){ ?? ????} ?? ????/** ? ?????*?@param?filePath?文件路径 ? ?????*?@return?读出的Word的内容 ? ?????*/?? ????public?String?getTextFromWord(String?filePath){ ?? ????????String?result?=?null; ?? ????????File?file?=?new?File(filePath); ?? ????????try{ ?? ????????????FileInputStream?fis?=?new?FileInputStream(file); ?? ????????????WordExtractor?wordExtractor?=?new?WordExtractor(fis); ?? ????????????result?=?wordExtractor.getText(); ?? ????????}catch(FileNotFoundException?e){ ?? ????????????e.printStackTrace(); ?? ????????}catch(IOException?e){ ?? ????????????e.printStackTrace(); ?? ????????}; ?? ????????return?result; ?? ????} ?? }?? package textReader; import java.io.*; import org.apache.poi.hwpf.extractor.WordExtractor; public class WordReader { public WordReader(){ } /** * @param filePath 文件路径 * @return 读出的Word的内容 */ public String getTextFromWord(String filePath){ String result = null; File file = new File(filePath); try{ FileInputStream fis = new FileInputStream(file); WordExtractor wordExtractor = new WordExtractor(fis); result = wordExtractor.getText(); }catch(FileNotFoundException e){ e.printStackTrace(); }catch(IOException e){ e.printStackTrace(); }; return result; } } ?? ? EXCEL Java代码 package?textReader; ?? import?org.apache.poi.hssf.usermodel.HSSFWorkbook; ?? import?org.apache.poi.hssf.usermodel.HSSFSheet; ?? import?org.apache.poi.hssf.usermodel.HSSFRow; ?? import?org.apache.poi.hssf.usermodel.HSSFCell; ?? ?? import?java.io.FileInputStream; ?? import?java.io.FileNotFoundException; ?? import?java.io.IOException; ?? ?? ?? public?class?ExcelReader?{ ?? ?? ????@SuppressWarnings(deprecation) ?? ????/** ? ?