Find a string and location in PDF file using iText

问题:

I am trying to find a string and it's location in a PDF using iTextSharp in Asp.net C# for editing. But so far with the help available on Google I am unable to do it. This is the current code but it does read text chunk by chunk but couldn't find the required text. Need help Thanks

public class RectAndText
    {
        public iTextSharp.text.Rectangle Rect;
        public String Text;
        public RectAndText(iTextSharp.text.Rectangle rect, String text)
        {
            this.Rect = rect;
            this.Text = text;
        }
    }

    public class MyLocationTextExtractionStrategy : LocationTextExtractionStrategy
    {
        public List<RectAndText> myPoints = new List<RectAndText>();
        public String TextToSearchFor { get; set; }
        public System.Globalization.CompareOptions CompareOptions { get; set; }

        public MyLocationTextExtractionStrategy(String textToSearchFor, System.Globalization.CompareOptions compareOptions = System.Globalization.CompareOptions.None)
        {
            this.TextToSearchFor = textToSearchFor;
            this.CompareOptions = compareOptions;
        }
        public override void RenderText(TextRenderInfo renderInfo)
        {
            base.RenderText(renderInfo);
            var startPosition = System.Globalization.CultureInfo.CurrentCulture.CompareInfo.IndexOf(renderInfo.GetText(), this.TextToSearchFor, this.CompareOptions);
            if (startPosition < 0)
            {
                return;
            }
            var chars = renderInfo.GetCharacterRenderInfos().Skip(startPosition).Take(this.TextToSearchFor.Length).ToList();
            var firstChar = chars.First();
            var lastChar = chars.Last();

            var bottomLeft = firstChar.GetDescentLine().GetStartPoint();
            var topRight = lastChar.GetAscentLine().GetEndPoint();
            var rect = new iTextSharp.text.Rectangle(
                                                    bottomLeft[Vector.I1],
                                                    bottomLeft[Vector.I2],
                                                    topRight[Vector.I1],
                                                    topRight[Vector.I2]
                                                    );

            this.myPoints.Add(new RectAndText(rect, this.TextToSearchFor));
        }
    }

Call function

string thisDir = System.Web.Hosting.HostingEnvironment.MapPath("~/");
var testFile = thisDir + "example.pdf";
var t = new MyLocationTextExtractionStrategy("searchstring"); //need to search this searchstring 

using (var r = new PdfReader(testFile))
{
   var ex = PdfTextExtractor.GetTextFromPage(r, 1, t);
}

foreach (var p in t.myPoints)
{
   Console.WriteLine(string.Format("Found text {0} at {1}x{2}", p.Text, p.Rect.Left, p.Rect.Bottom));
}

回答1:

This can easily be managed (in iText7) using RegexBasedLocationExtractionStrategy. This class can be constructed using a regular expression and pushes out the locations of the text matching the expression. Even if you can not switch to iText7, you can still have a look at the source code and see how we implemented it.