会python真的可以为所欲为0(回)
369天前
这里还有人吗1(回)
554天前这里还有人吗0(回)
554天前
每天面对着电脑屏幕，敲打键盘。我所面对的并不只是代码，而是一种生活方式。0(回)
779天前到处都是羊，不想上班0(回)
859天前
鸽子
0(回)
863天前package poi; |
import java.io.ByteArrayOutputStream; |
import java.io.File; |
import java.io.FileInputStream; |
import java.io.FileNotFoundException; |
import java.io.FileOutputStream; |
import java.io.InputStream; |
import java.util.List; |
import javax.xml.parsers.DocumentBuilderFactory; |
import javax.xml.transform.OutputKeys; |
import javax.xml.transform.Transformer; |
import javax.xml.transform.TransformerFactory; |
import javax.xml.transform.dom.DOMSource; |
import javax.xml.transform.stream.StreamResult; |
import org.apache.commons.io.FileUtils; |
import org.apache.poi.hwpf.HWPFDocument; |
import org.apache.poi.hwpf.converter.PicturesManager; |
import org.apache.poi.hwpf.converter.WordToHtmlConverter; |
import org.apache.poi.hwpf.usermodel.Picture; |
import org.apache.poi.hwpf.usermodel.PictureType; |
import org.w3c.dom.Document; |
public class PoiWordToHtml { |
public static void main (String[] args) throws Throwable { |
final String path = "c:/"; |
final String file = "test.doc"; |
InputStream input = new FileInputStream (path + file); |
HWPFDocument wordDocument = new HWPFDocument (input); |
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter (DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument() ); |
wordToHtmlConverter.setPicturesManager (new PicturesManager() { |
public String savePicture (byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) { |
return suggestedName; |
} |
}); |
wordToHtmlConverter.processDocument (wordDocument); |
List pics = wordDocument.getPicturesTable().getAllPictures(); |
if (pics != null) { |
for (int i = 0; i < pics.size(); i++) { |
Picture pic = (Picture) pics.get (i); |
try { |
pic.writeImageContent (new FileOutputStream (path + pic.suggestFullFileName() ) ); |
} catch (FileNotFoundException e) { |
e.printStackTrace(); |
} |
} |
} |
Document htmlDocument = wordToHtmlConverter.getDocument(); |
ByteArrayOutputStream outStream = new ByteArrayOutputStream(); |
DOMSource domSource = new DOMSource (htmlDocument); |
StreamResult streamResult = new StreamResult (outStream); |
TransformerFactory tf = TransformerFactory.newInstance(); |
Transformer serializer = tf.newTransformer(); |
serializer.setOutputProperty (OutputKeys.ENCODING, "utf-8"); |
serializer.setOutputProperty (OutputKeys.INDENT, "yes"); |
serializer.setOutputProperty (OutputKeys.METHOD, "html"); |
serializer.transform (domSource, streamResult); |
outStream.close(); |
String content = new String (outStream.toByteArray() ); |
FileUtils.write (new File (path, "1.html"), content, "utf-8"); |
} |
} |
