- 引用POI包讀取word文檔內容
poi.jar 下載地址
http://apache.freelamp.com/poi/release/bin/poi-bin-3.6-20091214.zip
http://apache.etoak.com/poi/release/bin/poi-bin-3.6-20091214.zip
http://labs.renren.com/apache-mirror/poi/release/bin/poi-bin-3.6-20091214.zip
2.引用jxl包讀取excel文檔的內容
Jxl.jar下載地址
http://nchc.dl.sourceforge.net/project/jexcelapi/CSharpJExcel/CSharpJExcel.zip
3.引用PDFBox讀取pdf文檔的內容
Pdfbox.jar下載地址
http://labs.renren.com/apache-mirror/pdfbox/1.1.0/pdfbox-1.1.0.jar
http://apache.etoak.com/pdfbox/1.1.0/pdfbox-1.1.0.jar
http://apache.freelamp.com/pdfbox/1.1.0/pdfbox-1.1.0.jar
Fontbox.jar下載地址
http://apache.etoak.com/pdfbox/1.1.0/fontbox-1.1.0.jar
http://labs.renren.com/apache-mirror/pdfbox/1.1.0/fontbox-1.1.0.jar
http://apache.freelamp.com/pdfbox/1.1.0/fontbox-1.1.0.jar
Jempbox.jar下載地址
http://labs.renren.com/apache-mirror/pdfbox/1.1.0/jempbox-1.1.0.jar
http://apache.etoak.com/pdfbox/1.1.0/jempbox-1.1.0.jar
http://apache.freelamp.com/pdfbox/1.1.0/jempbox-1.1.0.jar
下面我們就來簡單看一下這些jar包的對文檔的讀取的應用實例:
pom座標爲:
.....
<properties>
<poi.version>3.13</poi.version>
<pdf.version>1.8.10</pdf.version>
</properties>
....
<!-- 3個jar版本必須統一 -->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>${poi.version}</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>${poi.version}</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>${poi.version}</version>
</dependency>
<!-- pdf -->
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>${pdf.version}</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>fontbox</artifactId>
<version>${pdf.version}</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>jempbox</artifactId>
<version>${pdf.version}</version>
</dependency>
<dependency>
<groupId>net.sourceforge.jexcelapi</groupId>
<artifactId>jxl</artifactId>
<version>2.6.12</version>
</dependency>
讀取內容代碼
public static String getPDFContent(File file) {
String context = null;
InputStream f = null;
try {
f = new FileInputStream(file);
PDFParser p = new PDFParser(f);
p.parse();
PDDocument pdd = p.getPDDocument();
PDFTextStripper ts = new PDFTextStripper();
context = ts.getText(pdd);
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
f.close();
} catch (IOException e) {
e.printStackTrace();
}
}
return context == null ? "" : context;
}
public static String getXLSContent(File file) {
StringBuilder sb = new StringBuilder();
InputStream f = null;
try {
f = new FileInputStream(file);
jxl.Workbook rwb = Workbook.getWorkbook(f);
Sheet[] sheet = rwb.getSheets();
for (int i = 0; i < sheet.length; i++) {
Sheet rs = rwb.getSheet(i);
for (int j = 0; j < rs.getRows(); j++) {
Cell[] cells = rs.getRow(j);
for (int k = 0; k < cells.length; k++)
sb.append(cells[k].getContents());
}
}
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
f.close();
} catch (IOException e) {
e.printStackTrace();
}
}
return sb.toString() == null ? null : sb.toString();
}
public static String getWord2003(File file) {
String word2003 = null;
InputStream f = null;
try {
f = new FileInputStream(file);
WordExtractor ex = new WordExtractor(f);
word2003 = ex.getText();
} catch (IOException e) {
e.printStackTrace();
} finally {
try {
f.close();
} catch (IOException e) {
e.printStackTrace();
}
}
return word2003;
}
public static String getWord2007(File file) {
String word2007 = null;
try {
OPCPackage opcPackage = POIXMLDocument
.openPackage(file.getParent());
POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
word2007 = extractor.getText();
} catch (Exception e) {
e.printStackTrace();
}
return word2007;
}
另外 我把獲取文件的MIME方法也寫上吧
public static String getFileMime(File file) {
if (!file.exists()) {
System.err.println("文件不存在");
return null;
}
MagicMatch match = null;
try {
match = Magic.getMagicMatch(file, false);
} catch (Exception e) {
e.printStackTrace();
}
return match.getMimeType();
}
版權所有,轉載請標註