android中解析doc、docx、xls、xlsx格式文件

解析doc，要tm-extractors-0.4.jar这个包

解析xls，要jxl.jar这个包下载jxl.jar

    public static String readDOC(String path) {

// 创建输入流读取doc文件

FileInputStream in;

String text = null;

//                Environment.getExternalStorageDirectory().getAbsolutePath()+ "/aa.doc")

try {

in = new FileInputStream(new File(path));

int a= in.available();

WordExtractor extractor = null;

// 创建WordExtractor

extractor = new WordExtractor();

// 对doc文件进行提取

text = extractor.extractText(in);

System.out.println("解析得到的东西"+text);

} catch (FileNotFoundException e) {

e.printStackTrace();

} catch (Exception e) {

e.printStackTrace();

}

if (text == null) {

text = "解析文件出现问题";

}

return text;

}

}

public static String readXLS(String path) {

String str = "";

try {

Workbook workbook = null;

workbook = Workbook.getWorkbook(new File(path));

Sheet sheet = workbook.getSheet(0);

Cell cell = null;

int columnCount = sheet.getColumns();

int rowCount = sheet.getRows();

for (int i = 0; i < rowCount; i++) {

for (int j = 0; j < columnCount; j++) {

cell = sheet.getCell(j, i);

String temp2 = "";

if (cell.getType() == CellType.NUMBER) {

temp2 = ((NumberCell) cell).getValue() + "";

} else if (cell.getType() == CellType.DATE) {

temp2 = "" + ((DateCell) cell).getDate();

} else {

temp2 = "" + cell.getContents();

}

str = str + "  " + temp2;

}

str += "n";

}

workbook.close();

} catch (Exception e) {

}

if (str == null) {

str = "解析文件出现问题";

}

return str;

}

public static String readDOCX(String path) {

String river = "";

try {

ZipFile xlsxFile = new ZipFile(new File(path));

ZipEntry sharedStringXML = xlsxFile.getEntry("word/document.xml");

InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);

XmlPullParser xmlParser = Xml.newPullParser();

xmlParser.setInput(inputStream, "utf-8");

int evtType = xmlParser.getEventType();

while (evtType != XmlPullParser.END_DOCUMENT) {

switch (evtType) {

case XmlPullParser.START_TAG:

String tag = xmlParser.getName();

System.out.println(tag);

if (tag.equalsIgnoreCase("t")) {

river += xmlParser.nextText() + "n";

}

break;

case XmlPullParser.END_TAG:

break;

default:

break;

}

evtType = xmlParser.next();

}

} catch (ZipException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

} catch (XmlPullParserException e) {

e.printStackTrace();

}

if (river == null) {

river = "解析文件出现问题";

}

            return river;
    }</pre>解析xlsx<pre>public static String readXLSX(String path) {
            String str = &quot;&quot;;
            String v = null;
            boolean flat = false;
            List&lt;String&gt; ls = new ArrayList&lt;String&gt;();
            try {
                    ZipFile xlsxFile = new ZipFile(new File(path));
                    ZipEntry sharedStringXML = xlsxFile
                                    .getEntry(&quot;xl/sharedStrings.xml&quot;);
                    InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);
                    XmlPullParser xmlParser = Xml.newPullParser();
                    xmlParser.setInput(inputStream, &quot;utf-8&quot;);
                    int evtType = xmlParser.getEventType();
                    while (evtType != XmlPullParser.END_DOCUMENT) {
                            switch (evtType) {
                            case XmlPullParser.START_TAG:
                                    String tag = xmlParser.getName();
                                    if (tag.equalsIgnoreCase(&quot;t&quot;)) {
                                            ls.add(xmlParser.nextText());
                                    }
                                    break;
                            case XmlPullParser.END_TAG:
                                    break;
                            default:
                                    break;
                            }
                            evtType = xmlParser.next();
                    }
                    ZipEntry sheetXML = xlsxFile.getEntry(&quot;xl/worksheets/sheet1.xml&quot;);
                    InputStream inputStreamsheet = xlsxFile.getInputStream(sheetXML);
                    XmlPullParser xmlParsersheet = Xml.newPullParser();
                    xmlParsersheet.setInput(inputStreamsheet, &quot;utf-8&quot;);
                    int evtTypesheet = xmlParsersheet.getEventType();
                    while (evtTypesheet != XmlPullParser.END_DOCUMENT) {
                            switch (evtTypesheet) {
                            case XmlPullParser.START_TAG:
                                    String tag = xmlParsersheet.getName();
                                    if (tag.equalsIgnoreCase(&quot;row&quot;)) {
                                    } else if (tag.equalsIgnoreCase(&quot;c&quot;)) {
                                            String t = xmlParsersheet.getAttributeValue(null, &quot;t&quot;);
                                            if (t != null) {
                                                    flat = true;
                                                    System.out.println(flat + &quot;有&quot;);
                                            } else {
                                                    System.out.println(flat + &quot;没有&quot;);
                                                    flat = false;
                                            }
                                    } else if (tag.equalsIgnoreCase(&quot;v&quot;)) {
                                            v = xmlParsersheet.nextText();
                                            if (v != null) {
                                                    if (flat) {
                                                            str += ls.get(Integer.parseInt(v)) + &quot;  &quot;;
                                                    } else {
                                                            str += v + &quot;  &quot;;
                                                    }
                                            }
                                    }
                                    break;
                            case XmlPullParser.END_TAG:
                                    if (xmlParsersheet.getName().equalsIgnoreCase(&quot;row&quot;)
                                                    &amp;&amp; v != null) {
                                            str += &quot;n&quot;;
                                    }
                                    break;
                            }
                            evtTypesheet = xmlParsersheet.next();
                    }
                    System.out.println(str);
            } catch (ZipException e) {
                    e.printStackTrace();
            } catch (IOException e) {
                    e.printStackTrace();
            } catch (XmlPullParserException e) {
                    e.printStackTrace();
            }
            if (str == null) {
                    str = &quot;解析文件出现问题&quot;;
            }

            return str;
    }</pre><br />