zoukankan      html  css  js  c++  java
  • .net 下word 中的图片与文字分离

    最近在做一个项目要求word 中的图片与文字分离 ,找了好久终于找到一个完美的方法

    c#实现word中的图文分离

     

    part 1: class define

    publicclass WordSeparator:IDisposable
    {
    #region Constructor
    public WordSeparator()
    {
    WordApp
    =new Microsoft.Office.Interop.Word.Application();
    }
    #endregion

    #region Fields
    private Microsoft.Office.Interop.Word.Application WordApp;
    privateobject missing = System.Reflection.Missing.Value;
    privateobject yes =true;
    privateobject no =false;
    private Microsoft.Office.Interop.Word.Document d;
    privateobject filename =@"C:example.rtf";
    #endregion

    #region Methods
    publicvoid UpdateDoc()
    {
    d
    = WordApp.Documents.Open(ref filename, ref missing, ref no, ref missing,
    ref missing, ref missing, ref missing, ref missing, ref missing,
    ref missing, ref missing, ref yes, ref missing, ref missing, ref missing, ref missing);
    List
    <Microsoft.Office.Interop.Word.Range> ranges =
    new List<Microsoft.Office.Interop.Word.Range>();
    foreach (Microsoft.Office.Interop.Word.InlineShape s in d.InlineShapes)
    {
    if (s.Type ==
    Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapePicture)
    {
    ranges.Add(s.Range);
    s.Delete();
    }
    }
    foreach (Microsoft.Office.Interop.Word.Range r in ranges)
    {
    r.InlineShapes.AddPicture(
    @"c:PathToNewImageImage.jpg", ref missing, ref missing, ref missing);
    }
    WordApp.Quit(
    ref yes, ref missing, ref missing);
    }
    publicvoid SeparateImageText()
    {
    //初始化程序
    d = WordApp.Documents.Open(ref filename, ref missing, ref no, ref missing,
    ref missing, ref missing, ref missing, ref missing, ref missing,
    ref missing, ref missing, ref yes, ref missing, ref missing, ref missing, ref missing);
    List
    <Microsoft.Office.Interop.Word.Range> ranges =
    new List<Microsoft.Office.Interop.Word.Range>();
    List
    <string> files =new List<string>();
    foreach (Microsoft.Office.Interop.Word.InlineShape s in d.InlineShapes)
    {
    if (s.Type == Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapePicture
    || s.Type ==
    Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapeEmbeddedOLEObject)
    {
    //获取图片数据
    byte[] imgData = (byte[])s.Range.EnhMetaFileBits;
    string file =string.Concat(Guid.NewGuid().ToString(), ".gif");
    files.Add(file);
    //构造图形
    MemoryStream mStream =new MemoryStream(imgData);
    Bitmap bmp
    =new Bitmap(mStream);
    //保存到磁盘
    bmp.Save(file);
    mStream.Dispose();
    bmp.Dispose();

    ranges.Add(s.Range);
    s.Delete();
    }
    }
    for (int i =0; i < ranges.Count; i ++ )
    {
    Microsoft.Office.Interop.Word.Range r
    = ranges[i];
    //替换图片
    r.InsertBefore("<img src='"+ files[i] +"'>");
    r.InsertAfter(
    "</img>");
    }
    //退出程序
    WordApp.Quit(ref yes, ref missing, ref missing);
    }
    ///<summary>
    /// 替换word中的图片
    ///</summary>
    ///<param name="serverPath">图片文件的存储物理路径</param>
    ///<param name="virtualPath">图片文件的标签虚拟路径</param>
    publicvoid SeparateImageText(string serverPath, string virtualPath)
    {
    //初始化程序
    d = WordApp.Documents.Open(ref filename, ref missing, ref no, ref missing,
    ref missing, ref missing, ref missing, ref missing, ref missing,
    ref missing, ref missing, ref yes, ref missing, ref missing, ref missing, ref missing);
    List
    <Microsoft.Office.Interop.Word.Range> ranges =new List<Microsoft.Office.Interop.Word.Range>();
    List
    <string> files =new List<string>();
    foreach (Microsoft.Office.Interop.Word.InlineShape s in d.InlineShapes)
    {
    if (s.Type == Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapePicture
    || s.Type == Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapeEmbeddedOLEObject)
    {
    //获取图片数据
    byte[] imgData = (byte[])s.Range.EnhMetaFileBits;
    string file =string.Concat(Guid.NewGuid().ToString(), ".gif");
    files.Add(file);
    //构造图形
    MemoryStream mStream =new MemoryStream(imgData);
    Bitmap bmp
    =new Bitmap(mStream);
    //保存到磁盘
    bmp.Save(string.Concat(serverPath, "\", file));
    mStream.Dispose();
    bmp.Dispose();

    ranges.Add(s.Range);
    s.Delete();
    }
    }
    for (int i =0; i < ranges.Count; i++)
    {
    Microsoft.Office.Interop.Word.Range r
    = ranges[i];
    //替换图片
    r.InsertBefore("<img src='"+string.Concat(virtualPath,"//",files[i]) +"'>");
    r.InsertAfter(
    "</img>");
    }
    //退出程序
    WordApp.Quit(ref yes, ref missing, ref missing);
    }
    ///<summary>
    /// 替换word中的图片
    ///</summary>
    ///<param name="targetFile">目标文件</param>
    ///<param name="serverPath">图片文件的存储物理路径</param>
    ///<param name="virtualPath">图片文件的标签虚拟路径</param>
    publicvoid SeparateImageText(string targetFile,string serverPath, string virtualPath)
    {
    filename
    = targetFile;
    //初始化程序
    d = WordApp.Documents.Open(ref filename, ref missing, ref no, ref missing,
    ref missing, ref missing, ref missing, ref missing, ref missing,
    ref missing, ref missing, ref yes, ref missing, ref missing, ref missing, ref missing);
    List
    <Microsoft.Office.Interop.Word.Range> ranges =new List<Microsoft.Office.Interop.Word.Range>();
    List
    <string> files =new List<string>();
    foreach (Microsoft.Office.Interop.Word.InlineShape s in d.InlineShapes)
    {
    if (s.Type == Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapePicture
    || s.Type == Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapeEmbeddedOLEObject)
    {
    //获取图片数据
    byte[] imgData = (byte[])s.Range.EnhMetaFileBits;
    string file =string.Concat(Guid.NewGuid().ToString(), ".gif");
    files.Add(file);
    //构造图形
    MemoryStream mStream =new MemoryStream(imgData);
    Bitmap bmp
    =new Bitmap(mStream);
    //保存到磁盘
    bmp.Save(string.Concat(serverPath, "\", file));
    mStream.Dispose();
    bmp.Dispose();

    ranges.Add(s.Range);
    s.Delete();
    }
    }
    for (int i =0; i < ranges.Count; i++)
    {
    Microsoft.Office.Interop.Word.Range r
    = ranges[i];
    //替换图片
    r.InsertBefore("<img src='"+string.Concat(virtualPath, "//", files[i]) +"'>");
    r.InsertAfter(
    "</img>");
    }
    //退出程序
    WordApp.Quit(ref yes, ref missing, ref missing);
    }
    #endregion

    #region IDisposable 成员

    publicvoid Dispose()
    {
    if (d !=null)
    {
    System.Runtime.InteropServices.Marshal.ReleaseComObject(d);
    d
    =null;
    }
    if (WordApp !=null)
    {
    System.Runtime.InteropServices.Marshal.ReleaseComObject(WordApp);
    WordApp
    =null;
    }
    }

    #endregion
    }

     part 2: usage code:

    WordSeparator w =new WordSeparator();
    w.SeparateImageText();
     
     
     
    Shape 对象代表文档中的图形对象,
    InlineShape 代表文档中的嵌入式图形对象,
    但是我又遇到了另外一种问题,word 中的图片除了InlineShape  的图片外还有  Shape 
     如果将 Shape  转化为  InlineShape  就会报错
     对于shape 还是没法做到完全分离,希望大神指点一二
     
    学习永无止境
  • 相关阅读:
    spring mvc+ELK从头开始搭建日志平台
    java分布式系统开关功能设计(服务升降级)
    可伸缩性架构常用技术
    大众点评订单系统分库分表实践
    分布式缓存--系列1 -- Hash环/一致性Hash原理
    Netty原理剖析
    一个轻量级分布式 RPC 框架 — NettyRpc
    HDU 2583 permutation
    HDU 2573 Typing
    c语言中逗号运算符和逗号表达式
  • 原文地址:https://www.cnblogs.com/6922276zfj/p/4076861.html
Copyright © 2011-2022 走看看