C# 使用itextsharp 读取pdf中文字坐标

 

程序调用：

using iTextSharp.text.pdf;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading.Tasks;

namespace TestIText
{
    class Program
    {
        static void Main(string[] args)
        {
           PdfReader readerTemp = new PdfReader(@"D:\_Number position.pdf");

            PdfHelper.LocationTextExtractionStrategyEx pz = new PdfHelper.LocationTextExtractionStrategyEx();

            iTextSharp.text.pdf.parser.PdfReaderContentParser p = new iTextSharp.text.pdf.parser.PdfReaderContentParser(readerTemp);
            p.ProcessContent<PdfHelper.LocationTextExtractionStrategyEx>(1, pz);

            Console.WriteLine(pz.GetResultantText());//文字坐标信息等
            Console.ReadLine();


        }
    }
}

 

 

PdfHelper帮助类：

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;

using iTextSharp.text.pdf.parser;

namespace PdfHelper
{
    /// <summary>
    /// Taken from http://www.java-frameworks.com/java/itext/com/itextpdf/text/pdf/parser/LocationTextExtractionStrategy.java.html
    /// </summary>
    class LocationTextExtractionStrategyEx : LocationTextExtractionStrategy
    {
        private List<TextChunk> m_locationResult = new List<TextChunk>();
        private List<TextInfo> m_TextLocationInfo = new List<TextInfo>();
        public List<TextChunk> LocationResult
        {
            get { return m_locationResult; }
        }
        public List<TextInfo> TextLocationInfo
        {
            get { return m_TextLocationInfo; }
        }

        /// <summary>
        /// Creates a new LocationTextExtracationStrategyEx
        /// </summary>
        public LocationTextExtractionStrategyEx()
        {
        }

        /// <summary>
        /// Returns the result so far
        /// </summary>
        /// <returns>a String with the resulting text</returns>
        public override String GetResultantText()
        {
            m_locationResult.Sort();

            StringBuilder sb =