C# 用 iTextSharp 将 PDF 转成文本

using System;
using System.IO;
using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
 
public class ParsingPDF {
  
    static string PDF;
    static string TEXT2;
  
    /**
     * Parses the PDF using PRTokeniser
     * @param src  the path to the original PDF file
     * @param dest the path to the resulting text file
     */
    public void parsePdf(String src, String dest)
    {
        PdfReader reader = new PdfReader(src);
        StreamWriter output = new StreamWriter(new FileStream(dest, FileMode.Create));
        int pageCount = reader.NumberOfPages;
        for (int pg = 1; pg <= pageCount; pg++)
        {
            // we can inspect the syntax of the imported page
            byte[] streamBytes = reader.GetPageContent(pg);
            PRTokeniser tokenizer = new PRTokeniser(streamBytes);
            while (tokenizer.NextToken())
            {
                if (tokenizer.TokenType == PRTokeniser.TokType.STRING)
                {
                    output.WriteLine(tokenizer.StringValue);
                }
            }
        }
        output.Flush();
        output.Close();
    }
  
    /**
     * Main method.
     */
    static void Main(string[] args)
    {
        if (args.Length < 1 || args.Length > 2)
        {
            Console.WriteLine("USAGE: ParsePDF infile.pdf <outfile.txt>");
            return;
        }
        else if (args.Length == 1)
        {
            PDF = args[0];
            TEXT2 = Path.GetFileNameWithoutExtension(PDF) + ".txt";
        }
        else
        {
            PDF = args[0];
            TEXT2 = args[1];
        }
 
        try
        {
            DateTime t1 = DateTime.Now;
 
            ParsingPDF example = new ParsingPDF();
            example.parsePdf(PDF, TEXT2);
 
            DateTime t2 = DateTime.Now;
            TimeSpan ts = t2 - t1;
            Console.WriteLine("Parsing completed in {0:0.00} seconds.", ts.TotalSeconds);
        }
        catch (Exception ex)
        {
            Console.WriteLine("ERROR: " + ex.Message);
        }
    } // class
 
    public class MyTextRenderListener : IRenderListener
    {
        /** The print writer to which the information will be written. */
        protected StreamWriter output;
 
        /**
         * Creates a RenderListener that will look for text.
         */
        public MyTextRenderListener(StreamWriter output)
        {
            this.output = output;
        }
 
        public void BeginTextBlock()
        {
            output.Write("<");
        }
 
        public void EndTextBlock()
        {
            output.WriteLine(">");
        }
 
        public void RenderImage(ImageRenderInfo renderInfo)
        {
        }
 
        public void RenderText(TextRenderInfo renderInfo)
        {
            output.Write("<");
            output.Write(renderInfo.GetText());
            output.Write(">");
        }
    } // class
} // namespace  

标签：

版权申明：本站文章部分自网络，如有侵权，请联系：west999com@outlook.com
特别注意：本站所有转载文章言论不代表本站观点！
本站所提供的图片等素材，版权归原作者所有，如需使用，请与原作者联系。