itext将html转为pdf,图片标签为base64的处理

2019独角兽企业重金招聘Python工程师标准>>>

在http://my.oschina.net/yifanxiang/blog/678139中。修改了一下代码如下：

/**
	 * 生成单页pdf
	 * @param ctx
	 * @return
	 * @throws DocumentException
	 * @throws IOException
	 */
	public static byte[] buildPdf(String ctx) throws DocumentException, IOException{
		ByteArrayOutputStream baos=new ByteArrayOutputStream(1024);
		Document document = new Document();
		PdfWriter writer = PdfWriter.getInstance(document, baos);
	    writer.setInitialLeading(12);//文字间距
	    document.open();
	    HtmlToPdfUtil.MyFontsProvider fontProvider = new HtmlToPdfUtil.MyFontsProvider();
        fontProvider.addFontSubstitute("lowagie", "garamond");
        fontProvider.setUseUnicode(true);
        CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
        HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
        DefaultTagProcessorFactory tpf=(DefaultTagProcessorFactory)Tags.getHtmlTagProcessorFactory();
        tpf.addProcessor(Tag.IMG, Image.class.getName());//默认是com.itextpdf.tool.xml.html.Image|自个定义一个image的处理类
        htmlContext.setTagFactory(tpf);
        CSSResolver cssResolver = XMLWorkerHelper.getInstance().getDefaultCssResolver(true);
        Pipeline<?> pipeline = new CssResolverPipeline(cssResolver,new HtmlPipeline(htmlContext, new PdfWriterPipeline(document,writer)));
        XMLWorker worker = new XMLWorker(pipeline, true);
        XMLParser p = new XMLParser(worker);
        ByteArrayInputStream bais=new ByteArrayInputStream(ctx.getBytes());
    	p.parse(new InputStreamReader(bais));
    	p.flush();

        document.close();
		byte[] result=baos.toByteArray();
		baos.flush();
		baos.close();
		return result;
	}

主要就是以下两句：

 DefaultTagProcessorFactory tpf=(DefaultTagProcessorFactory)Tags.getHtmlTagProcessorFactory();
 tpf.addProcessor(Tag.IMG, Image.class.getName());//默认是com.itextpdf.tool.xml.html.Image|自个定义一个image的处理类（这个Image是我自个定义的image）

自定义的Image类：

package com.junziqian.common.convert;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.apache.commons.codec.binary.Base64;

import com.itextpdf.text.BadElementException;
import com.itextpdf.text.Chunk;
import com.itextpdf.text.Element;
import com.itextpdf.text.log.Level;
import com.itextpdf.text.log.Logger;
import com.itextpdf.text.log.LoggerFactory;
import com.itextpdf.text.pdf.PdfName;
import com.itextpdf.text.pdf.PdfString;
import com.itextpdf.text.xml.XMLUtil;
import com.itextpdf.tool.xml.NoCustomContextException;
import com.itextpdf.tool.xml.Tag;
import com.itextpdf.tool.xml.WorkerContext;
import com.itextpdf.tool.xml.css.CssUtils;
import com.itextpdf.tool.xml.exceptions.LocaleMessages;
import com.itextpdf.tool.xml.exceptions.RuntimeWorkerException;
import com.itextpdf.tool.xml.html.AbstractTagProcessor;
import com.itextpdf.tool.xml.html.HTML;
import com.itextpdf.tool.xml.net.ImageRetrieve;
import com.itextpdf.tool.xml.net.exc.NoImageException;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;

public class Image extends AbstractTagProcessor {
	
	private final CssUtils utils = CssUtils.getInstance();
	private static final Logger logger = LoggerFactory.getLogger(Image.class);
	
	
	/*
	 * (non-Javadoc)
	 *
	 * @see
	 * com.itextpdf.tool.xml.TagProcessor#endElement(com.itextpdf.tool.xml.Tag,
	 * java.util.List, com.itextpdf.text.Document)
	 */
	@Override
	public List<Element> end(final WorkerContext ctx, final Tag tag, final List<Element> currentContent) {
		Map<String, String> attributes = tag.getAttributes();
		String src = attributes.get(HTML.Attribute.SRC);
		com.itextpdf.text.Image img = null;
		List<Element> l = new ArrayList<Element>(1);
		if (null !