标签归档:PDF

C#实现自动打印PDF

采用PDFRender4NET

//打印机设置
PrinterSettings settings = new PrinterSettings();
settings.PrinterName = printername;
settings.PrintToFile = false;
settings.Copies = 1;
settings.PrintRange = PrintRange.AllPages;
//设置纸张大小(可以不设置取,取默认设置)
PaperSize ps = new PaperSize("Your Paper Name",595,842);
ps.RawKind = 9; //如果是自定义纸张,就要大于118

//打印设置
PDFRender.Printing.PDFPrintSettings pdfPrintSettings = new PDFRender.Printing.PDFPrintSettings(settings);
pdfPrintSettings.AutoRotate = false;            //自动旋转
pdfPrintSettings.BitmapPrintResolution = 560;   //图片打印精度                    
pdfPrintSettings.PaperSize = ps;                //纸张尺寸
pdfPrintSettings.PageScaling = PDFRender.Printing.PageScaling.FitToPrinterMarginsProportional;

pdfFile.Print(pdfPrintSettings);

代码详见: https://github.com/HiRaygo/DocumentPrint/blob/master/PdfPrint.cs

采用SumatraPDF或Acrobat Reader方案

 public static PrintEngine SumatraPDF = new PrintEngine("Sumatra PDF Reader",
            ((printerName, filePath, documentName) => 
            {
                string app = Path.Combine(Program.localPath, "SumatraPDF.exe");
                string args = string.Format("-silent -exit-on-print -print-to \"{0}\" \"{1}\"", printerName, filePath);

                Process p = new Process();
                p.StartInfo = new ProcessStartInfo()
                {
                    CreateNoWindow = true,
                    WindowStyle = ProcessWindowStyle.Hidden,
                    FileName = app,
                    Arguments = args
                };
                //if (User.isNetworkService())
                //{
                //    p.StartInfo.UserName = Program.config.serviceLogin;
                //    p.StartInfo.Password = tools.secureString(tools.Decrypt(Program.config.servicePass));
                //    p.StartInfo.Domain = Program.config.serviceDomain;
                //    p.StartInfo.LoadUserProfile = true;
                //    p.StartInfo.UseShellExecute = false;
                //}
                p.Start();

            })){};

        /// <summary>
        /// Print via external programm Acrobat Reader
        /// </summary>
        public static PrintEngine AcrobatReader = new PrintEngine("Acrobat Reader",
            ((printerName, filePath, documentName) =>
            {                
                string app = Registry.LocalMachine.OpenSubKey(
                        @"SOFTWARE\Microsoft\Windows\CurrentVersion" +
                        @"\App Paths\AcroRd32.exe"
                    ).GetValue("").ToString()
                ;
                string args = string.Format("/h /t \"{0}\" \"{1}\"", filePath, printerName);

                Process p = new Process();
                p.StartInfo = new ProcessStartInfo()
                {
                    CreateNoWindow = true,
                    WindowStyle = ProcessWindowStyle.Hidden,
                    FileName = app,
                    Arguments = args
                };
                //if (User.isNetworkService())
                //{

                //    p.StartInfo.UserName = Program.config.serviceLogin;
                //    p.StartInfo.Password = tools.secureString(tools.Decrypt(Program.config.servicePass));
                //    p.StartInfo.Domain = Program.config.serviceDomain;
                //    p.StartInfo.LoadUserProfile = true;
                //    p.StartInfo.UseShellExecute = false;
                //}
                p.Start();

})){};

代码详见: https://github.com/RepairShopr/AutoPrintr-win/blob/master/AutoPrintr/modules/PrintEngines.cs

使用pdfbox给pdf去背景图片

前面采用了Python写的pdfrw做的,发现用acrobat不能编辑。

用pdfbox工具查看发现missing xobject。

java -jar pdfbox-app-2.0.13.jar PDFDebugger out.pdf

所以改用java的pdfbox库来写

package com.c4ys;

import org.apache.pdfbox.contentstream.PDContentStream;
import org.apache.pdfbox.contentstream.operator.Operator;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdfparser.PDFStreamParser;
import org.apache.pdfbox.pdfwriter.ContentStreamWriter;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.common.PDStream;
import org.apache.pdfbox.pdmodel.graphics.PDXObject;
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
import org.apache.pdfbox.pdmodel.graphics.pattern.PDAbstractPattern;
import org.apache.pdfbox.pdmodel.graphics.pattern.PDTilingPattern;

import java.io.File;
import java.io.IOException;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.List;

public class Main {

    public static void main(String[] args) throws IOException {
        if (args.length != 3) {
            usage();
        } else {
            PDDocument doc = PDDocument.load(new File(args[0]));
            if (doc.isEncrypted()) {
                System.err.println(
                        "Error: Encrypted documents are not supported .");
                System.exit(1);
            }

            for (PDPage page : doc.getPages()) {
                List<Object> newTokens = createTokensWithoutImage(page, args[2]);
                PDStream newContents = new PDStream(doc);
                writeTokensToStream(newContents, newTokens);
                page.setContents(newContents);
                processResources(page.getResources(), args[2]);
            }

            doc.save(args[1]);
            doc.close();
        }
    }

    private static List<Object> createTokensWithoutImage(PDContentStream contentStream, String im) throws IOException {
        PDFStreamParser parser = new PDFStreamParser(contentStream);
        Object token = parser.parseNextToken();
        List<Object> newTokens = new ArrayList<Object>();
        while (token != null) {
            if (token instanceof Operator) {
                Operator op = (Operator) token;
                if (op.getName().equalsIgnoreCase("do")) {
                    COSName previous = (COSName) newTokens.get(newTokens.size() - 1);
                    System.out.println(previous.getName());
                    if (previous.getName().equalsIgnoreCase(im)) {
                        // remove the argument to this operator
                        newTokens.remove(newTokens.size() - 1);
                        token = parser.parseNextToken();
                        continue;
                    }
                }
            }
            newTokens.add(token);
            token = parser.parseNextToken();
        }
        return newTokens;
    }


    private static void processResources(PDResources resources, String im) throws IOException {
        for (COSName name : resources.getXObjectNames()) {
            PDXObject xobject = resources.getXObject(name);
            if (xobject instanceof PDFormXObject) {
                PDFormXObject formXObject = (PDFormXObject) xobject;
                writeTokensToStream(formXObject.getContentStream(),
                        createTokensWithoutImage(formXObject, im));
                processResources(formXObject.getResources(), im);
            }
        }
        for (COSName name : resources.getPatternNames()) {
            PDAbstractPattern pattern = resources.getPattern(name);
            if (pattern instanceof PDTilingPattern) {
                PDTilingPattern tilingPattern = (PDTilingPattern) pattern;
                writeTokensToStream(tilingPattern.getContentStream(),
                        createTokensWithoutImage(tilingPattern, im));
                processResources(tilingPattern.getResources(), im);
            }
        }
    }

    private static void writeTokensToStream(PDStream newContents, List<Object> newTokens) throws IOException {
        OutputStream out = newContents.createOutputStream(COSName.FLATE_DECODE);
        ContentStreamWriter writer = new ContentStreamWriter(out);
        writer.writeTokens(newTokens);
        out.close();
    }


    /**
     * This will print the usage for this document.
     */
    private static void usage() {
        System.err.println("Usage: java " + Main.class.getName() + " <input-pdf> <output-pdf> <image-object-name>");
    }
}

Python 修改PDF文档尺寸以及去除水印图片

# -*- coding: UTF-8 -*-

import sys
import os

from pdfrw import PageMerge, PdfReader, PdfWriter, IndirectPdfDict
import fitz


# resize
def adjust(page):
    info = PageMerge().add(page)
    x1, y1, x2, y2 = info.xobj_box
    viewrect = ((x2 - 421) / 2, (y2 - 595) / 2, 421, 595)
    page = PageMerge().add(page, viewrect=viewrect)
    return page.render()

fin, = sys.argv[1:]
fout = 'mid.' + os.path.basename(fin)
reader = PdfReader(fin)
writer = PdfWriter(fout)
for p in reader.pages:
    writer.addpage(adjust(p))
writer.trailer.Info = IndirectPdfDict(reader.Info or {})
writer.write()

# trip backgroud images
doc = fitz.open(fout)
for i in range(len(doc)):
    imglist = doc.getPageImageList(i)
    for img in imglist:
        xref = img[0]
        if xref==51:
            doc._deleteObject(xref)
        print(img)
doc.save('new.' + os.path.basename(fin))