Question

我正在尝试使用Asp.net C＃中的iTextSharp在PDF中查找字符串及其位置以进行编辑。但到目前为止，借助Google提供的帮助，我无法做到。这是当前的代码，但它确实通过块读取文本块，但无法找到所需的文本。需要帮助谢谢

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));
        }
    }

通话功能

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));
}

Answer 1

使用RegexBasedLocationExtractionStrategy可以轻松管理（在iText7中）。可以使用正则表达式构造此类，并推出与表达式匹配的文本的位置。即使您无法切换到iText7，您仍然可以查看源代码，看看我们是如何实现的。

使用ASP.Net C＃使用iTextSharp在PDF文件中查找字符串和位置

1 个答案: