如何使用 iTextSharp 获取文本格式

Question

我正在使用 iTextSharp 从 PDF 中读取文本内容。我也能读懂。但是我丢失了字体、颜色等文本格式。有没有办法也可以得到这种格式。

下面是我用来精确文本的代码段 -

PdfReader reader = new PdfReader("F:\\EBooks\\AspectsOfAjax.pdf");
textBox1.Text = ExtractTextFromPDFBytes(reader.GetPageContent(1));

private string ExtractTextFromPDFBytes(byte[] input)
{
    if (input == null || input.Length == 0) return "";
    try
    {
        string resultString = "";
        // Flag showing if we are we currently inside a text object
        bool inTextObject = false;
        // Flag showing if the next character is literal  e.g. '\\' to get a '\' character or '\(' to get '('
        bool nextLiteral = false;
        // () Bracket nesting level. Text appears inside ()
        int bracketDepth = 0;
        // Keep previous chars to get extract numbers etc.:
        char[] previousCharacters = new char[_numberOfCharsToKeep];
        for (int j = 0; j < _numberOfCharsToKeep; j++) previousCharacters[j] = ' ';
        for (int i = 0; i < input.Length; i++)
        {
            char c = (char)input[i];
            if (inTextObject)
            {
                // Position the text
                if (bracketDepth == 0)
                {
                    if (CheckToken(new string[] { "TD", "Td" }, previousCharacters))
                    {
                        resultString += "\n\r";
                    }
                    else
                    {
                        if (CheckToken(new string[] {"'", "T*", "\""}, previousCharacters))
                        {
                            resultString += "\n";
                        }
                        else
                        {
                            if (CheckToken(new string[] { "Tj" }, previousCharacters))
                            {
                                resultString += " ";
                            }
                        }
                    }
                }
                // End of a text object, also go to a new line.
                if (bracketDepth == 0 && CheckToken( new string[]{"ET"}, previousCharacters))
                {
                    inTextObject = false;
                    resultString += " ";
                }
                else
                {
                    // Start outputting text
                    if ((c == '(') && (bracketDepth == 0) && (!nextLiteral))
                    {
                        bracketDepth = 1;
                    }
                    else
                    {
                        // Stop outputting text
                        if ((c == ')') && (bracketDepth == 1) && (!nextLiteral))
                        {
                            bracketDepth = 0;
                        }
                        else
                        {
                            // Just a normal text character:
                            if (bracketDepth == 1)
                            {
                                // Only print out next character no matter what. 
                                // Do not interpret.
                                if (c == '\\' && !nextLiteral)
                                {
                                    nextLiteral = true;
                                }
                                else
                                {
                                    if (((c >= ' ') && (c <= '~')) || ((c >= 128) && (c < 255)))
                                    {
                                        resultString += c.ToString();
                                    }
                                    nextLiteral = false;
                                }
                            }
                        }
                    }
                }
            }
            // Store the recent characters for when we have to go back for a checking
            for (int j = 0; j < _numberOfCharsToKeep - 1; j++)
            {
                previousCharacters[j] = previousCharacters[j + 1];
            }
            previousCharacters[_numberOfCharsToKeep - 1] = c;

            // Start of a text object
            if (!inTextObject && CheckToken(new string[]{"BT"}, previousCharacters))
            {
                inTextObject = true;
            }
        }
        return resultString;
    }
    catch
    {
        return "";
    }
}

private bool CheckToken(string[] tokens, char[] recent)
{
    foreach(string token in tokens)
    {
        if ((recent[_numberOfCharsToKeep - 3] == token[0]) &&
            (recent[_numberOfCharsToKeep - 2] == token[1]) &&
            ((recent[_numberOfCharsToKeep - 1] == ' ') ||
            (recent[_numberOfCharsToKeep - 1] == 0x0d) ||
            (recent[_numberOfCharsToKeep - 1] == 0x0a)) &&
            ((recent[_numberOfCharsToKeep - 4] == ' ') ||
            (recent[_numberOfCharsToKeep - 4] == 0x0d) ||
            (recent[_numberOfCharsToKeep - 4] == 0x0a))
            )
        {
            return true;
        }
    }
    return false;
}

Answer 1

让我试着为你指出一个不同的方向。 iTextSharp 有一个非常漂亮和简单的文本提取系统，可以处理一些基本的标记。不幸的是，它不处理颜色信息，而是according to @Mark Storer it might not be too hard to implement yourself。

开始编辑

我开始着手实现颜色信息。有关详细信息，请参阅my blog post here。 （抱歉格式不好，马上去吃饭。）

结束编辑

下面的代码结合了这里的几个问题和答案，包括this one to get the font height（虽然它不准确）以及另一个（对于我的一生，我似乎再也找不到了），它显示了如何检测虚假粗体。

PostscriptFontName 在字体名称前返回一些额外的字符，我认为这与您嵌入字体子集时有关。

下面是一个完整的 WinForms 应用程序，它以 iTextSharp 5.1.1.0 为目标并将文本提取为 HTML。

示例 PDF 的屏幕截图

提取为 HTML 的示例文本

<span style="font-family:NJNSWD+Papyrus-Regular;font-size:11.61407">Hello </span>
<span style="font-family:NJNSWD+Papyrus-Regular-Bold;font-size:11.61407">w</span>
<span style="font-family:NJNSWD+Papyrus-Regular-Bold;font-size:37.87201">o</span>
<span style="font-family:NJNSWD+Papyrus-Regular-Bold;font-size:11.61407">rl</span>
<span style="font-family:NJNSWD+Papyrus-Regular;font-size:11.61407">d </span>
<br />
<span style="font-family:NJNSWD+Papyrus-Regular;font-size:11.61407">Test </span>

代码

using System;
using System.Collections.Generic;
using System.Text;
using System.Windows.Forms;
using iTextSharp.text.pdf.parser;
using iTextSharp.text.pdf;

namespace WindowsFormsApplication2
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            PdfReader reader = new PdfReader(System.IO.Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Desktop), "Document.pdf"));
            TextWithFontExtractionStategy S = new TextWithFontExtractionStategy();
            string F = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, 1, S);
            Console.WriteLine(F);

            this.Close();
        }

        public class TextWithFontExtractionStategy : iTextSharp.text.pdf.parser.ITextExtractionStrategy
        {
            //HTML buffer
            private StringBuilder result = new StringBuilder();

            //Store last used properties
            private Vector lastBaseLine;
            private string lastFont;
            private float lastFontSize;

            //http://api.itextpdf.com/itext/com/itextpdf/text/pdf/parser/TextRenderInfo.html
            private enum TextRenderMode
            {
                FillText = 0,
                StrokeText = 1,
                FillThenStrokeText = 2,
                Invisible = 3,
                FillTextAndAddToPathForClipping = 4,
                StrokeTextAndAddToPathForClipping = 5,
                FillThenStrokeTextAndAddToPathForClipping = 6,
                AddTextToPaddForClipping = 7
            }



            public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
            {
                string curFont = renderInfo.GetFont().PostscriptFontName;
                //Check if faux bold is used
                if ((renderInfo.GetTextRenderMode() == (int)TextRenderMode.FillThenStrokeText))
                {
                    curFont += "-Bold";
                }

                //This code assumes that if the baseline changes then we're on a newline
                Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
                Vector topRight = renderInfo.GetAscentLine().GetEndPoint();
                iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
                Single curFontSize = rect.Height;

                //See if something has changed, either the baseline, the font or the font size
                if ((this.lastBaseLine == null) || (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]) || (curFontSize != lastFontSize) || (curFont != lastFont))
                {
                    //if we've put down at least one span tag close it
                    if ((this.lastBaseLine != null))
                    {
                        this.result.AppendLine("</span>");
                    }
                    //If the baseline has changed then insert a line break
                    if ((this.lastBaseLine != null) && curBaseline[Vector.I2] != lastBaseLine[Vector.I2])
                    {
                        this.result.AppendLine("<br />");
                    }
                    //Create an HTML tag with appropriate styles
                    this.result.AppendFormat("<span style=\"font-family:{0};font-size:{1}\">", curFont, curFontSize);
                }

                //Append the current text
                this.result.Append(renderInfo.GetText());

                //Set currently used properties
                this.lastBaseLine = curBaseline;
                this.lastFontSize = curFontSize;
                this.lastFont = curFont;
            }

            public string GetResultantText()
            {
                //If we wrote anything then we'll always have a missing closing tag so close it here
                if (result.Length > 0)
                {
                    result.Append("</span>");
                }
                return result.ToString();
            }

            //Not needed
            public void BeginTextBlock() { }
            public void EndTextBlock() { }
            public void RenderImage(ImageRenderInfo renderInfo) { }
        }
    }
}

Answer 2

如果有人在寻找它，我将@Chris 代码转换为 Java

import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.parser.ImageRenderInfo;
import com.itextpdf.text.pdf.parser.TextExtractionStrategy;
import com.itextpdf.text.pdf.parser.TextRenderInfo;
import com.itextpdf.text.pdf.parser.Vector;

public class TextWithFontExtractionStategy implements TextExtractionStrategy {
//HTML buffer
private StringBuilder result = new StringBuilder();

//Store last used properties
private Vector lastBaseLine;
private String lastFont;
private float lastFontSize;

//http://api.itextpdf.com/itext/com/itextpdf/text/pdf/parser/TextRenderInfo.html
private enum TextRenderMode
{
    FillText(0),
    StrokeText(1),
    FillThenStrokeText(2),
    Invisible(3),
    FillTextAndAddToPathForClipping(4),
    StrokeTextAndAddToPathForClipping(5),
    FillThenStrokeTextAndAddToPathForClipping(6),
    AddTextToPaddForClipping(7);

    private int value;

    TextRenderMode(int value) {
        this.value = value;
    }

    public int getValue() {
        return value;
    }
}

    public void renderText(TextRenderInfo renderInfo)
    {
        String curFont = renderInfo.getFont().getPostscriptFontName();
        //Check if faux bold is used
        if ((renderInfo.getTextRenderMode() == TextRenderMode.FillThenStrokeText.getValue()))
        {
            curFont += "-Bold";
        }

        //This code assumes that if the baseline changes then we're on a newline
        Vector curBaseline = renderInfo.getBaseline().getStartPoint();
        Vector topRight = renderInfo.getAscentLine().getEndPoint();
        Rectangle rect = new Rectangle(curBaseline.get(Vector.I1), curBaseline.get(Vector.I2), topRight.get(Vector.I1), topRight.get(Vector.I2));
        float curFontSize = rect.getHeight();

        //See if something has changed, either the baseline, the font or the font size
        if ((this.lastBaseLine == null) || (curBaseline.get(Vector.I2) != lastBaseLine.get(Vector.I2)) || (curFontSize != lastFontSize) || (curFont != lastFont))
        {
            //if we've put down at least one span tag close it
            if ((this.lastBaseLine != null))
            {
                this.result.append("</span>").append("\n");
            }
            //If the baseline has changed then insert a line break
            if ((this.lastBaseLine != null) && curBaseline.get(Vector.I2) != lastBaseLine.get(Vector.I2))
            {
                this.result.append("<br />").append("\n");
            }
            //Create an HTML tag with appropriate styles
            this.result.append(String.format("<span style=\"font-family:{%s};font-size:{%s}\">", curFont, curFontSize));
        }

        //Append the current text
        this.result.append(renderInfo.getText() + " ");

        //Set currently used properties
        this.lastBaseLine = curBaseline;
        this.lastFontSize = curFontSize;
        this.lastFont = curFont;
    }

    public String getResultantText()
    {
        //If we wrote anything then we'll always have a missing closing tag so close it here
        if (result.length() > 0)
        {
            result.append("</span>");
        }
        return result.toString();
    }

    //Not needed
    public void beginTextBlock() { }
    public void endTextBlock() { }
    public void renderImage(ImageRenderInfo renderInfo) { }

}