参考:
分类目录归档:Java
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>");
}
}