抽取PDF文本

下载iTextSharp的dll，链接：

http://cdnetworks-kr-2.dl.sourceforge.net/project/itextsharp/itextsharp/iTextSharp-5.0.4/itextsharp-5.0.4-dll.zip

示例代码

using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;

namespace ReadPdfDemo
{
     class Program
    {
         static void Main( string[] args)
        {
             string str = GetAllText( @"C:\Users\dc\Desktop\20101098504717.pdf");
        }

         static public string GetAllText( string filePath)
        {
             string text = string.Empty;
             PdfReader reader = new PdfReader(filePath);
             for ( int i = 1; i <= reader.NumberOfPages; i++)
            {
                text += GetTextFromPage(reader, i);
            }
             return text;
        }

         static public string GetTextFromPage( PdfReader reader, int pageNum)
        {
             ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
             return PdfTextExtractor.GetTextFromPage(reader, pageNum, strategy);
        }
    }
}

转载于:https://www.cnblogs.com/dc10101/archive/2010/10/11/1847810.html