java 读取pdf、word、Excel文件
用到的jar：
itextpdf-5.5.8.jar （PDF）
poi.jar
public class FileUtils {
/**
* 判断文件是否存在
*
* @Title: isExcite
* @param @param filePath
* @param @return
* @return boolean 返回类型
* @throws
*/
public static boolean isExcite(String filePath) {
File file = new File(filePath);
// 如果文件夹不存在则创建
if (!file.exists() && !file.isDirectory()) {
return false;
} else {
return true;
}
}
/**
*
* @Title: getPdfFileText
* @Description: 获取指定位置pdf的文件内容
* @param @param fileName
* @param @return
* @param @throws IOException
* @return String 返回类型
* @throws
*/
public static String getPdfFileText(String fileName) throws IOException {
PdfReader reader = new PdfReader(fileName);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
StringBuffer buff = new StringBuffer();
TextExtractionStrategy strategy;
for (int i = 1; i <= reader.getNumberOfPages(); i++) {
strategy = parser.processContent(i,
new SimpleTextExtractionStrategy());
buff.append(strategy.getResultantText());
}
return buff.toString();
}
/**
* 获取doc文档
*
* @Title: getTextFromWord
* @param @param filePath
* @param @return
* @return String 返回类型
* @throws
*/
public static 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;
}
/**
* 读取excel内容
*
* @Title: getTextFromExcel
* @param @param filePath
* @param @return
* @return String 返回类型
* @throws
*/
public static String getTextFromExcel(String filePath) {
StringBuffer buff = new StringBuffer();
try {
// 创建对Excel工作簿文件的引用
HSSFWorkbook wb = new HSSFWorkbook(new FileInputStream(filePath));
// 创建对工作表的引用。
for (int numSheets = 0; numSheets < wb.getNumberOfSheets(); numSheets++) {
if (null != wb.getSheetAt(numSheets)) {
HSSFSheet aSheet = wb.getSheetAt(numSheets);// 获得一个sheet
for (int rowNumOfSheet = 0; rowNumOfSheet <= aSheet
.getLastRowNum(); rowNumOfSheet++) {
if (null != aSheet.getRow(rowNumOfSheet)) {
HSSFRow aRow = aSheet.getRow(rowNumOfSheet); // 获得一个行
for (int cellNumOfRow = 0; cellNumOfRow <= aRow
.getLastCellNum(); cellNumOfRow++) {
if (null != aRow.getCell(cellNumOfRow)) {
HSSFCell aCell = aRow.getCell(cellNumOfRow);// 获得列值
switch (aCell.getCellType()) {
case HSSFCell.CELL_TYPE_FORMULA:
break;
case HSSFCell.CELL_TYPE_NUMERIC:
buff
.append(
aCell
.getNumericCellValue())
.append(‘\t‘);
break;
case HSSFCell.CELL_TYPE_STRING:
buff.append(aCell.getStringCellValue())
.append(‘\t‘);
break;
}
}
}
buff.append(‘\n‘);
}
}
}
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return buff.toString();
}
/**
* 替换文件内容
* @Title: replaceContentToFile
* @param @param path 文件路径
* @param @param str 要替换的内容
* @param @param con 替换称的内容
* @return void 返回类型
* @throws
*/
public static void replaceContentToFile(String path, String str, String con) {
try {
if (isExcite(path)) {
FileReader read = new FileReader(path);
BufferedReader br = new BufferedReader(read);
StringBuilder content = new StringBuilder();
while (br.ready() != false) {
content.append(br.readLine());
content.append("\r\n");
}
int dex = content.indexOf(str);
if (dex != -1) {
System.out.println("找到标记!");
} else {
System.out.println("指定标记不存在!");
}
content.replace(dex, dex, con);
br.close();
read.close();
FileOutputStream fs = new FileOutputStream(path);
fs.write(content.toString().getBytes());
fs.close();
} else {
System.out.println("文件不存在!");
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
留着以后直接拿过来用。