如何使用 itextsharp 库仅从 pdf 中复制突出显示的文本？答案

【问题标题】：How to copy only hilighted text from pdf using itextsharp library?如何使用 itextsharp 库仅从 pdf 中复制突出显示的文本？
【发布时间】：2016-05-15 21:55:11
【问题描述】：

我有一个问题，无法从 PDF 文件中提取突出显示的文本。 str 变量始终为空。任何人都可以帮助我吗？

我的代码：

private static string GetPdfHighlighText(string file, int page) {
    string nv = "";
    PdfReader reader = new PdfReader(file);
    for (int x = 1; x < reader.NumberOfPages; x++)
    {
        PdfDictionary pageDict = reader.GetPageN(x);
        PdfArray annots = pageDict.GetAsArray(PdfName.ANNOTS);
        if (annots != null)
        {

            for (int i = 1; i <= annots.Size; ++i)
            {
                PdfDictionary annotationDic = (PdfDictionary)PdfReader.GetPdfObject(annots[i]);
                PdfName subType = (PdfName)annotationDic.Get(PdfName.SUBTYPE);
                if (subType.Equals(PdfName.HIGHLIGHT))
                {

                    PdfString str = annots.GetAsString(i);

                    nv = nv + str;

                }
            }
        }
    }

    return nv; }

我正在使用 ITextSharp 库。 PFLibrary 是 iTextSharp.text.pdf 命名空间。

我想从 pdf 中扫描所有页面并提取所有突出显示的文本，它是 245 页，但我会每页放置过滤器。我可以识别突出显示的注释，但没有返回突出显示文本的字符串

【问题讨论】：

标签： c# pdf itextsharp

【解决方案1】：

我设法用以下代码解决了我的问题：

    public string GetPdfLinks(string file,  int pgIni, int pgFim)
    {
        Progresso = 0;
        //Open our reader
        PdfReader R = new PdfReader(file);
        List<string> Ret = new List<string>();

        for (int i = pgIni; i <= pgFim; i++)
        {

            //Get the current page
            PdfDictionary PageDictionary = R.GetPageN(i);

            //Get all of the annotations for the current page
            PdfArray Annots = PageDictionary.GetAsArray(PdfName.ANNOTS);

            //Make sure we have something
            if ((Annots == null) || (Annots.Length == 0))
                return null;

             //kjkjjj

            //Loop through each annotation
            foreach (PdfObject A in Annots.ArrayList)
            {
                //Convert the itext-specific object as a generic PDF object
                PdfDictionary AnnotationDictionary = (PdfDictionary)PdfReader.GetPdfObject(A);

                //Make sure this annotation has a link
                if (!AnnotationDictionary.Get(PdfName.SUBTYPE).Equals(PdfName.LINK))
                    continue;

                //Make sure this annotation has an ACTION
                if (AnnotationDictionary.Get(PdfName.A) == null)
                    continue;

                //Get the ACTION for the current annotation
                PdfDictionary AnnotationAction = (PdfDictionary)AnnotationDictionary.Get(PdfName.A);

                //Test if it is a URI action (There are tons of other types of actions, some of which might mimic URI, such as JavaScript, but those need to be handled seperately)
                if (AnnotationAction.Get(PdfName.S).Equals(PdfName.URI))
                {
                    PdfString Destination = AnnotationAction.GetAsString(PdfName.URI);
                    if (Destination != null)
                        Ret.Add(Destination.ToString());
                }
            }

            Progresso++;
        }

        foreach (string link in Ret)
        {
            resultado = resultado + link + "\n ";
        }

        return resultado;

    }

【讨论】：