毫无疑问支持.doc和.docx的只有POI
好多jar都是积分下载,要么就是官网下载,真心垃圾,jar包免费下载:
链接:https://pan.baidu.com/s/14MWWHN3cTsr0mmxMGkIObQ
提取码:93ob
复制这段内容后打开百度网盘手机App,操作更方便哦
新增支持读取txt文本和pdf,pdf需要iTextpdf.jar包,从上方链接下载即可
/**
* 读取txt文件
*
* @param filepath 本地txt或log文件
* @return 返回读取到的文件内容
*/
public static String readFileContent(String filepath) {
String content = "";
try {
InputStream is = new FileInputStream(new File(filepath));
InputStreamReader reader = new InputStreamReader(is);
BufferedReader bufferedReader = new BufferedReader(reader);
String line;
while ((line = bufferedReader.readLine()) != null) {
content = content + line + "\n";
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (NullPointerException e) {
e.toString();
}
return content;
}
/**
* 读取word内容
*
* @param path
*/
public static String readDoc(String path) {
String content = "";
try {
FileInputStream in = new FileInputStream(path);
//PoiFs 主要类 管理整个文件系统生命周期
POIFSFileSystem pfs = new POIFSFileSystem(in);
//获取文档所有的数据结构 可以说是一个“文档对象”
HWPFDocument hwpf = new HWPFDocument(pfs);
content = hwpf.getText().toString();
} catch (Exception e) {
e.printStackTrace();
}
return content;
}
/**
* 读取word内容
*
* @param path
*/
public static String readDocx(String path) {
String content = "";
try {
InputStream is = new FileInputStream(path);
XWPFDocument doc = new XWPFDocument(is);
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
content = extractor.getText();
} catch (Exception e) {
e.printStackTrace();
}
return content;
}
/**
* 读取Pdf文件的内容
*
* @param path :文件地址
*/
public String readPdf(String path) {
String content = "";
try {
PdfReader pr = new PdfReader(path);
int page = pr.getNumberOfPages();
for (int i = 1; i < page + 1; i++) {
content += PdfTextExtractor.getTextFromPage(pr, i);
}
} catch (IOException e) {
e.printStackTrace();
}
return content;
}