使用iText将html转换为pdf

时间：2013-11-27 07:26:00

标签： java itext

我想使用iText将带有图像的html文件转换为pdf。我在这里提供我的来源。

这是我的HTML文件...... 

 <html>

 <body>
 <img src='data:image/png;base64,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' width='62' height='80' style='float: left; margin-right: 28px;' alt="" /> 
<!-- <img src="add.png" alt="" /> -->  
</body>
</html>

我想将此html文件转换为pdf ...

使用以下java代码... 

 import java.io.DataOutputStream;
 import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.StringReader;
import java.net.URL;
import java.nio.charset.Charset;

import org.apache.commons.io.IOUtils;
import org.apache.pdfbox.encoding.Encoding;
import org.jsoup.Jsoup;
import org.jsoup.safety.Whitelist;
import org.jsoup.select.Elements;
import org.w3c.tidy.Tidy;

import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Image;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.tool.xml.Pipeline;
import com.itextpdf.tool.xml.XMLWorker; 
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import com.itextpdf.tool.xml.css.CssFilesImpl;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.HTML;
import com.itextpdf.tool.xml.html.TagProcessor;
import com.itextpdf.tool.xml.html.TagProcessorFactory;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;
import com.itextpdf.tool.xml.pipeline.html.ImageProvider;
import com.pdfcrowd.Client;

public class App
{


  public static void main( String[] args ) throws DocumentException, IOException
   {

    // step 1
    Document document = new Document();
    document.newPage();
    // step 2
    PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream("pdf.pdf"));
    // step 3
    document.open();
    // step 4
    XMLWorkerHelper.getInstance().parseXHtml(writer, document,
            new FileInputStream("index.html"));
    //step 5
     document.close();
     System.out.println( "PDF Created!" );
  }
}

我收到以下错误... 

Exception in thread "main" ExceptionConverter: java.io.IOException: The document has no pages.
at com.itextpdf.text.pdf.PdfPages.writePageTree(PdfPages.java:113)
at com.itextpdf.text.pdf.PdfWriter.close(PdfWriter.java:1243)
at com.itextpdf.text.pdf.PdfDocument.close(PdfDocument.java:849)
at com.itextpdf.text.Document.close(Document.java:416)
at App.main(App.java:64)

请帮帮我如何使用itext将带图像的html文件转换为pdf。如果我没有图像或者我硬编码图像路径，我能够转换该html文件。提前致谢

2 个答案:

答案 0 :(得分：5)

您需要实现自定义图像标记处理器来处理嵌入在html中的图像：

package com.example.itext.processor;

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

import com.itextpdf.text.Chunk;
import com.itextpdf.text.Element;
import com.itextpdf.text.Image;
import com.itextpdf.text.log.Level;
import com.itextpdf.text.log.Logger;
import com.itextpdf.text.log.LoggerFactory;
import com.itextpdf.text.pdf.codec.Base64;
import com.itextpdf.tool.xml.NoCustomContextException;
import com.itextpdf.tool.xml.Tag;
import com.itextpdf.tool.xml.WorkerContext;
import com.itextpdf.tool.xml.exceptions.LocaleMessages;
import com.itextpdf.tool.xml.exceptions.RuntimeWorkerException;
import com.itextpdf.tool.xml.html.HTML;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;

public class ImageTagProcessor extends com.itextpdf.tool.xml.html.Image {

private final Logger logger = LoggerFactory.getLogger(getClass());

/*
 * (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) {
    final Map<String, String> attributes = tag.getAttributes();
    String src = attributes.get(HTML.Attribute.SRC);
    List<Element> elements = new ArrayList<Element>(1);
    if (null != src && src.length() > 0) {
        Image img = null;
        if (src.startsWith("data:image/")) {
            final String base64Data = src.substring(src.indexOf(",") + 1);
            try {
                img = Image.getInstance(Base64.decode(base64Data));
            } catch (Exception e) {
                if (logger.isLogging(Level.ERROR)) {
                    logger.error(String.format(LocaleMessages.getInstance().getMessage(LocaleMessages.HTML_IMG_RETRIEVE_FAIL), src), e);
                }
            }
            if (img != null) {
                try {
                    final HtmlPipelineContext htmlPipelineContext = getHtmlPipelineContext(ctx);
                    elements.add(getCssAppliers().apply(new Chunk((com.itextpdf.text.Image) getCssAppliers().apply(img, tag, htmlPipelineContext), 0, 0, true), tag,
                        htmlPipelineContext));
                } catch (NoCustomContextException e) {
                    throw new RuntimeWorkerException(e);
                }
            }
        }

        if (img == null) {
            elements = super.end(ctx, tag, currentContent);
        }
    }
    return elements;
}
}

以下代码段注册自定义图片代码处理器并将HTML文档转换为PDF 

public static void main(String[] args) {
    convertHtmlToPdf();

}

private static void convertHtmlToPdf() {
    try {
        final OutputStream file = new FileOutputStream(new File("C:\\Test.pdf"));
        final Document document = new Document();
        final PdfWriter writer = PdfWriter.getInstance(document, file);
        document.open();
        final TagProcessorFactory tagProcessorFactory = Tags.getHtmlTagProcessorFactory();
        tagProcessorFactory.removeProcessor(HTML.Tag.IMG);
        tagProcessorFactory.addProcessor(new ImageTagProcessor(), HTML.Tag.IMG);

        final CssFilesImpl cssFiles = new CssFilesImpl();
        cssFiles.add(XMLWorkerHelper.getInstance().getDefaultCSS());
        final StyleAttrCSSResolver cssResolver = new StyleAttrCSSResolver(cssFiles);
        final HtmlPipelineContext hpc = new HtmlPipelineContext(new CssAppliersImpl(new XMLWorkerFontProvider()));
        hpc.setAcceptUnknown(true).autoBookmark(true).setTagFactory(tagProcessorFactory);
        final HtmlPipeline htmlPipeline = new HtmlPipeline(hpc, new PdfWriterPipeline(document, writer));
        final Pipeline<?> pipeline = new CssResolverPipeline(cssResolver, htmlPipeline);
        final XMLWorker worker = new XMLWorker(pipeline, true);
        final Charset charset = Charset.forName("UTF-8");
        final XMLParser xmlParser = new XMLParser(true, worker, charset);
        final InputStream is = new FileInputStream("C:\\test.html");
        xmlParser.parse(is, charset);

        is.close();
        document.close();
        file.close();
    } catch (Exception e) {
        e.printStackTrace();
        // TODO
    }
}

答案 1 :(得分：0)

如果您的pdf页面中没有内容，则会发生此异常。 尝试传递InputStream这样的

String str="<html>

 <body>
 <img src='data:image/png;base64,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' width='62' height='80' style='float: left; margin-right: 28px;' alt="" /> 
<!-- <img src="add.png" alt="" /> -->  
</body>
</html>"

InputStream is = new ByteArrayInputStream(str.getBytes());
XMLWorkerHelper.getInstance().parseXHtml(writer, document, is);
相关问题
最新问题