zoukankan      html  css  js  c++  java
  • C#读取word,ppt,excel,txt,pdf文件内容

    一、读取文件内容

    (1)word

     /// <summary>

            /// 读取doc、docx

            /// </summary>

            /// <param name="filepath">文件路径</param>

            /// <returns>字符串</returns>

            protected string contentdoc(string filepath)

            {

                Microsoft.Office.Interop.Word.Application app = new Microsoft.Office.Interop.Word.Application();

                Document doc = null;

                object unknow = Type.Missing;

                app.Visible = true;

                string str = filepath;

                object file = str;

                doc = app.Documents.Open(ref file,

                    ref unknow, ref unknow, ref unknow, ref unknow,

                    ref unknow, ref unknow, ref unknow, ref unknow,

                    ref unknow, ref unknow, ref unknow, ref unknow,

                    ref unknow, ref unknow, ref unknow);

                //string temp = doc.Paragraphs[1].Range.Text.Trim();//分段读取

                string temp = doc.Content.Text;

                return temp;

            }

    说明:1: 对项目添加引用,Microsoft Word 11.0 Object Library
    2: 在程序中添加 using Word = Microsoft.Office.Interop.Word;
    3: 程序中添加
    Word.Application app = new Microsoft.Office.Interop.Word.Application(); //可以打开word程序
    Word.Document doc = null; //一会要记录word打开的文档

    参考网址:http://www.cnblogs.com/no7dw/archive/2009/08/14/1546367.html

    (2)Ppt

        /// <summary>

            /// 读取ppt内容

            /// </summary>

            /// <param name="filepath"></param>

            /// <returns></returns>

            protected string contentppt(string filepath)

            {

                Microsoft.Office.Interop.PowerPoint.Application pa = new Microsoft.Office.Interop.PowerPoint.Application();

                Microsoft.Office.Interop.PowerPoint.Presentation pp = pa.Presentations.Open(filepath,

                                Microsoft.Office.Core.MsoTriState.msoTrue,

                                Microsoft.Office.Core.MsoTriState.msoFalse,

                                Microsoft.Office.Core.MsoTriState.msoFalse);

                string pps = "";

                foreach (Microsoft.Office.Interop.PowerPoint.Slide slide in pp.Slides)

                {

                    foreach (Microsoft.Office.Interop.PowerPoint.Shape shape in slide.Shapes)

                     pps += shape.TextFrame.TextRange.Text.ToString();

                }

                return pps;

            }

    说明:: 对项目添加引用,Microsoft Word 11.0 Object Library
    2: 在程序中添加 using Word = Microsoft.Office.Interop.Powerpoint;
    3: 程序中添加
    Word.Application app = new Microsoft.Office.Interop.Powerpoint.Application(); //可以打开ppt程序

    参考网址:http://blog.sina.com.cn/s/blog_651ff6920100oi9u.html

    (3)Pdf

    /// <summary>

            /// 读取含有文本的pdf

            /// </summary>

            /// <param name="filepath">文件路径</param>

            /// <returns>字符串</returns>

            protected string contentpdf(string filepath)

            {

                StringBuilder text = new StringBuilder();

                string fileName = filepath;

                if (System.IO.File.Exists(fileName))

                {

                    PdfReader pdfReader = new PdfReader(fileName);

                    for (int page = 1; page <= pdfReader.NumberOfPages; page++)

                    {

                        ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();

                        string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);

                        currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));

                        text.Append(currentText);

                    }

                    pdfReader.Close();

                }

                return text.ToString();

            }

    说明:引用iTextSharp.dll.等三个dll.

    using iTextSharp.text.pdf;

    using iTextSharp.text.pdf.parser;

    参考网址:http://www.codeproject.com/Tips/387327/Convert-PDF-file-content-into-string-using-Csharp

    (4)t'x't

    /// <summary>

            /// 读取txt

            /// </summary>

            /// <param name="filepath">文件路径</param>

            /// <returns>字符串</returns>

            protected string contenttxt(string filepath)

            {

                StringBuilder sb = new StringBuilder();

                //Open the stream and read it back.

                using (FileStream fs = new FileStream(filepath, FileMode.Open))

                {

                    byte[] b = new byte[fs.Length];

                    fs.Read(b, 0, b.Length);//把文件读进byte[]里面

                    sb.Append(Encoding.GetEncoding("gb2312").GetString(b));//从byte[]里面把数据转成字符放到sb里面

                }

                return sb.ToString();

            }

    (5)excel

    详细参考:http://www.cnblogs.com/Tsong/archive/2013/02/21/2920941.html

  • 相关阅读:
    struts2 批量上传.
    jsoup html解析器 实现对博客园博文标题链接抓取
    赶鸭子上架的cdq分治
    RE:从零开始的莫比乌斯反演
    我永远无法学会的dp
    gym 101915
    2017-2018 ACM-ICPC Latin American Regional Programming Contest GYM101889
    网络流24T
    re:从零开始的数位dp
    Codeforces Round 504
  • 原文地址:https://www.cnblogs.com/mydotnetforyou/p/3551905.html
Copyright © 2011-2022 走看看