在VB.NET或C#中使用itextsharp dll阅读PDF内容

如何使用Pdfreader类读取带有itextsharp的PDF内容。我的PDF可以包括纯文本或文本的图像。

using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using System.IO;

public string ReadPdfFile(string fileName)
{
    StringBuilder text = new StringBuilder();

    if (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();
}

原文地址：https://www.jb51.cc/vb/256559.html