Identify rgb and cmyk color from pdf

问题

I have a PDF that consists of different color text and background color. How do I identify which colors are used in the PDF with CMYK or RGB format?

StringBuilder sb_Sourcepdf = new StringBuilder();
PdfReader reader_FirstPdf = new PdfReader(pdf_of_FirstFile);

Document document = new Document();

PDFParser parser = new PDFParser(new FileInputStream(pdf_of_FirstFile));
parser.parse();
PDDocument docum = parser.getPDDocument();

PDFStreamEngine engine = new PDFStreamEngine();

PDPage page = (PDPage)docum.getDocumentCatalog().getAllPages().get(0);

engine.processStream(page, page.findResources(), page.getContents().getStream());
PDGraphicsState graphicState = engine.getGraphicsState();
string colorname = graphicState.getStrokingColor().getColorSpace().getName();
graphicState.getTextState().getFont();
int r = graphicState.getNonStrokingColor().getJavaColor().getRed();
int g = graphicState.getNonStrokingColor().getJavaColor().getGreen();
int b = graphicState.getNonStrokingColor().getJavaColor().getBlue();
int rgb = graphicState.getNonStrokingColor().getJavaColor().getRGB();
float[] cosp = graphicState.getNonStrokingColor().getColorSpaceValue();
PDColorSpace pd = graphicState.getNonStrokingColor().getColorSpace();

string re = graphicState.getStrokingColor().toString();
int rgbcolor = graphicState.getStrokingColor().getJavaColor().getRGB();

float[] components = { java.awt.Color.black.getRed(), java.awt.Color.black.getGreen(), java.awt.Color.black.getBlue() };

float[] colorSpaceValues = graphicState.getStrokingColor().getColorSpaceValue();


foreach (float c in colorSpaceValues)
{
    Debug.WriteLine(c * 255.00);
}

I used pdfbox but I am getting value as 0.0

回答1:

 PdfReader reader_FirstPdf = new PdfReader(pdf_of_FirstFile);


            for (int i = 1; i <= reader_FirstPdf.NumberOfPages; i++)
            {
 TextWithFont_SourcePdf Sourcepdf = new TextWithFont_SourcePdf();
}
                text_First_File = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader_FirstPdf, i, Sourcepdf);


            public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
            {
 int r = renderInfo.GetColorNonStroke().R;
                  int g = renderInfo.GetColorNonStroke().G;
                   int b = renderInfo.GetColorNonStroke().B;

}

来源：https://stackoverflow.com/questions/16076748/identify-rgb-and-cmyk-color-from-pdf

标签

pdfbox