java 提取 word 中的文本和图片-k8凯发天生赢家

本文展示如何使用spire.doc for java提取word文档中的文本和图片。

提取文本

import com.spire.doc.document;
import java.io.filewriter;
import java.io.ioexception;
public class extracttext {
    public static void main(string[] args) throws ioexception {
        //加载word文档
        document document = new document();
        document.loadfromfile("c:\\users\\administrator\\desktop\\sample.docx");
        //获取文档中的文本保存为string
        string text=document.gettext();
        //将string写入txt文件
        writestringtotxt(text,"extractedtext.txt");
    }
    public static void writestringtotxt(string content, string txtfilename) throws ioexception {
        filewriter fwriter= new filewriter(txtfilename,true);
        try {
            fwriter.write(content);
        }catch(ioexception ex){
            ex.printstacktrace();
        }finally{
            try{
                fwriter.flush();
                fwriter.close();
            } catch (ioexception ex) {
                ex.printstacktrace();
            }
        }
    }
}

提取图片

import com.spire.doc.document;
import com.spire.doc.documents.documentobjecttype;
import com.spire.doc.fields.docpicture;
import com.spire.doc.interfaces.icompositeobject;
import com.spire.doc.interfaces.idocumentobject;
import javax.imageio.imageio;
import java.awt.image.bufferedimage;
import java.io.file;
import java.io.ioexception;
import java.util.arraylist;
import java.util.linkedlist;
import java.util.list;
import java.util.queue;
public class extractimages {
    public static void main(string[] args) throws ioexception {
        //加载word文档
        document document = new document();
        document.loadfromfile("c:\\users\\administrator\\desktop\\sample.docx");
        //创建queue对象
        queue nodes = new linkedlist();
        nodes.add(document);
        //创建list对象
        list images = new arraylist();
        //遍历文档中的子对象
        while (nodes.size() > 0) {
            icompositeobject node = nodes.poll();
            for (int i = 0; i < node.getchildobjects().getcount(); i  ) {
                idocumentobject child = node.getchildobjects().get(i);
                if (child instanceof icompositeobject) {
                    nodes.add((icompositeobject) child);
                    //获取图片并添加到list
                    if (child.getdocumentobjecttype() == documentobjecttype.picture) {
                        docpicture picture = (docpicture) child;
                        images.add(picture.getimage());
                    }
                }
            }
        }
        //将图片保存为png格式文件
        for (int i = 0; i < images.size(); i  ) {
            file file = new file(string.format("output/图片-%d.png", i));
            imageio.write(images.get(i), "png", file);
        }
    }
}