java itext html转PDF解决中文无法显示以及base64图片处理

一、添加maven依赖

      <dependency>
			<groupId>com.itextpdf</groupId>
			<artifactId>itextpdf</artifactId>
			<version>5.5.11</version>
		</dependency>
		<dependency>
			<groupId>com.itextpdf.tool</groupId>
			<artifactId>xmlworker</artifactId>
			<version>5.5.11</version>
		</dependency>
		<dependency>
			<groupId>com.itextpdf</groupId>
			<artifactId>itext-asian</artifactId>
			<version>5.2.0</version>
		</dependency>

二、处理中文不显示问题

核心代码如下：

import com.itextpdf.text.Font;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import org.springframework.core.io.DefaultResourceLoader;

import java.io.File;


public class AsianFontProvider extends XMLWorkerFontProvider {
    @Override
    public Font getFont(String fontname, String encoding, float size, final int style) {
        try {
            File file = new DefaultResourceLoader().getResource("").getFile();
            //字体文件绝对路径
            String path =file.toString()+File.separator+"templates"+File.separator+"simfang.ttf";
            BaseFont bfChinese =BaseFont.createFont( path , BaseFont.IDENTITY_H, BaseFont.EMBEDDED);
            return new Font(bfChinese, size, style);
        } catch (Exception e) {
          
        }
        return super.getFont(fontname, encoding, size, style);
    }
}

这里我使用的是仿宋字体，字体文件放在了项目的 templates 目录。

避坑：

开发阶段使用的是spring boot内置的tomcat，导出的PDF没有什么问题，发布到服务器后，发现导出的PDF中文字体还是没办法显示。经过调试发现，当使用中文字体的时候，下面这个方法的fontname变量是乱码。

 public Font getFont(String fontname, String encoding, float size, final int style)

原因就是tomcat中文乱码导致的。在tomcat的bin目录catalina.bat或catalina.sh 添加如下配置，解决tomcat中文乱码问题

set "JAVA_OPTS=%JAVA_OPTS% %JSSE_OPTS% -Dfile.encoding=UTF-8"

三、处理HTML文件中Base64格式图片不显示问题

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.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.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 {
    @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) {
                    throw new RuntimeException(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;
    }
}

四、封装工具类

import com.itextpdf.text.Document;
import com.itextpdf.text.PageSize;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.tool.xml.Pipeline;
import com.itextpdf.tool.xml.XMLWorker;
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.TagProcessorFactory;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
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 java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.io.OutputStream;
import java.nio.charset.Charset;


public class PdfUtils {

    /**
     *  HTML TO PDF 到指定目录
     * @param html  html内容
     * @param os  PDF文件生成目录
     */
    public static void writeStringToOutputStreamAsPDF(String html, OutputStream os) {
        writeToOutputStreamAsPDF(new ByteArrayInputStream(html.getBytes()), os);
    }

    /**
     * HTML TO PDF 到指定目录
     * @param html  html内容
     * @param os PDF文件生成目录
     */
    public static void writeToOutputStreamAsPDF(InputStream html, OutputStream os) {
        try {
            Document document = new Document(PageSize.A4,36, 36, 36, 36);
            PdfWriter pdfWriter = PdfWriter.getInstance(document, os);
            document.open();
            //BASE64图片处理
            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 AsianFontProvider()));
            hpc.setAcceptUnknown(true).autoBookmark(true).setTagFactory(tagProcessorFactory);
            final HtmlPipeline htmlPipeline = new HtmlPipeline(hpc, new PdfWriterPipeline(document, pdfWriter));
            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);

            xmlParser.parse(html,charset);

            document.close();
        } catch (Exception e) {
        }
    }
}