开发语言 使用C#读取PDF中所有文本内容

先安装如下包

using iTextSharp.text.pdf;

using System;

using System.Collections.Generic;

using System.IO;

using System.Linq;

using System.Text;

namespace ReadPdfText

{

class Program

{

static void Main(string[] args)

{

string path = "0017_审判流程管理信息表2.pdf";

var text = ReadPFD2(path);

Console.WriteLine(text);

Console.ReadKey();

}

public static string OnCreated(string filepath)

{

try

{

string pdffilename = filepath;

PdfReader pdfReader = new PdfReader(pdffilename);

int numberOfPages = pdfReader.NumberOfPages;

string text = string.Empty;

for (int i = 1; i <= numberOfPages; ++i)

{

iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();

text += iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfReader, i, strategy);

}

pdfReader.Close();

return text;

}

catch (Exception ex)

{

throw ex;

//StreamWriter wlog = File.AppendText(System.AppDomain.CurrentDomain.SetupInformation.ApplicationBase + "\\mylog.log");

//wlog.WriteLine("出错文件：" + ex.FullPath + "原因：" + ex.ToString());

//wlog.Flush();

//wlog.Close(); return null;

}

}

public static string ReadPFD2(string path)

{

// string path = path;// @"D:\ydfile\d4bab8ff-26ff-4ddf-a602-872f6988db86_.pdf";

string text = string.Empty;

try

{

string pdffilename = path;

StringBuilder buffer = new StringBuilder();

//Create a pdf document.

using (Spire.Pdf.PdfDocument doc = new Spire.Pdf.PdfDocument())

{

// Load the PDF Document

doc.LoadFromFile(pdffilename);

// String for hold the extracted text

foreach (Spire.Pdf.PdfPageBase page in doc.Pages)

{

buffer.Append(page.ExtractText());

}

doc.Close();

}

//save text

text = buffer.ToString();

return text;

}

catch (Exception ex)

{

//DHC.EAS.Common.LogInfo.Debug("读取PDF文件返回=" + text);

//DHC.EAS.Common.LogInfo.Debug("读取PDF文件错误", ex);

return null;

}

}

}

}

参考文章