Question

我正在尝试在pdf文件中搜索文本，并在文本存在时返回坐标。我正在研究网络并发现可以使用itextsharp库来完成。

我找到了这段代码，我正在尝试修改它以满足我的要求。如何将我的文件传递给这个类。

class Program
{
    static void Main(string[] args)
    {
        var testFile = @"test.pdf";
        //Create an instance of our strategy
        var t = new MyLocationTextExtractionStrategy("test");

        //Parse page 1 of the document above
        using (var r = new PdfReader(testFile))
        {
            var ex = PdfTextExtractor.GetTextFromPage(r, 1, t);
        }

        //Loop through each chunk found
        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));
        }

        Console.Read();
    }
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
    {
        //Hold each coordinate
        public List<RectAndText> myPoints = new List<RectAndText>();

        //The string that we're searching for
        public String TextToSearchFor { get; set; }

        //How to compare strings
        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;
        }

        //Automatically called for each chunk of text in the PDF
        public override void RenderText(TextRenderInfo renderInfo)
        {
            base.RenderText(renderInfo);

            //See if the current chunk contains the text
            var startPosition = System.Globalization.CultureInfo.CurrentCulture.CompareInfo.IndexOf(renderInfo.GetText(), this.TextToSearchFor, this.CompareOptions);

            //If not found bail
            if (startPosition < 0)
            {
                return;
            }

            //Grab the individual characters
            var chars = renderInfo.GetCharacterRenderInfos().Skip(startPosition).Take(this.TextToSearchFor.Length).ToList();

            //Grab the first and last character
            var firstChar = chars.First();
            var lastChar = chars.Last();


            //Get the bounding box for the chunk of text
            var bottomLeft = firstChar.GetDescentLine().GetStartPoint();
            var topRight = lastChar.GetAscentLine().GetEndPoint();

            //Create a rectangle from it
            var rect = new iTextSharp.text.Rectangle(
                                                    bottomLeft[Vector.I1],
                                                    bottomLeft[Vector.I2],
                                                    topRight[Vector.I1],
                                                    topRight[Vector.I2]
                                                    );

            //Add this to our main collection
            this.myPoints.Add(new RectAndText(rect, this.TextToSearchFor));
        }
    }

Answer 1

在我看来，PdfReader接受一个字符串，该字符串是您要读取的文件的路径。所以只需改变

{{1}}

指向您要使用的文件。（如果它不在应用程序的工作文件夹中，您可能必须添加完整路径）

Answer 2

OMG！你的代码对于那个任务来说太大了。我可以推荐很简单的解决方案。请看下面的

//Open PDF document
using (var doc = PdfDocument.Load(@"d:\0\test_big.pdf"))
{
    //Enumerate pages
    foreach(var page in doc.Pages)
    {
        var found = page.Text.Find("text for search", FindFlags.MatchWholeWord, 0);
        if (found == null)
            return; //nothing found
        do
        {
            var textInfo = found.FindedText;
            foreach(var rect in textInfo.Rects)
            {
                float x = rect.left;
                float y = rect.top;
                //...
            }
        } while (found.FindNext());

        page.Dispose();
    }
}

在pdf文件中搜索文本，如果文本存在则返回坐标

2 个答案: