Html 转图片或转 PDF 碰到的问题及个人解决方式

很少写博客，可能心思有点杂，很少沉淀下来。但是偶尔看到很久前写的博文对一些小伙伴有帮助，还是比较开心的。几年前写过一篇 itext 转 pdf 富文本编辑器 想着的一些问题，发现留言还不少，刚巧后面有时间，也有些问题需要处理的时候，重新弄了一遍。这里贴一下，方便回顾，也方便有需要的小伙伴解决问题。以下是 html 转 png 的例子，实际上不管是转 pdf 还是转 png，要解决的还是 html 渲染过程中，html 规范导致的各类问题。

前例直通车

<dependency>
			<groupId>net.sf.jtidy</groupId>
			<artifactId>jtidy</artifactId>
			<version>r938</version>
		</dependency>
		<dependency>
			<groupId>org.xhtmlrenderer</groupId>
			<artifactId>core-renderer</artifactId>
			<version>R8</version>
		</dependency>

以上是本次所依赖的包。

import org.w3c.dom.Document;
import org.w3c.tidy.Tidy;
import org.xhtmlrenderer.swing.Java2DRenderer;
import org.xhtmlrenderer.util.FSImageWriter;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

import javax.imageio.ImageWriteParam;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.Date;
import java.util.Properties;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class HtmlToImageUtils {


    public static String convertToImage(String html, String path, String name, int width) throws IOException {
        //输出标准 html
        html = htmlCovertTohtml(html);
        //过滤换行和 html 空格 （ 非标准 html）
        html = fixSpace(html);
        //闭合标签
        html = fixEndTag(html);
        //过滤特殊 unicode 字符
        html = stripNonValidXMLCharacters(html);
        DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance();
        documentBuilderFactory.setNamespaceAware(true);
        Document document = null;
        try {
            DocumentBuilder documentBuilder = documentBuilderFactory.newDocumentBuilder();
            StringReader reader = new StringReader(html);
            InputSource inputSource = new InputSource(reader);
            document = documentBuilder.parse(inputSource);
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        }

        String date = DateUtil.dateToString(new Date(), "yyyy/MM/dd");
        String fullDirPath = path.concat("/").concat(date);
        File dir = new File(fullDirPath);
        if (!dir.exists()) {
            if (!dir.mkdirs()) {
                dir.mkdir();
            }
        }
        String filePath = fullDirPath.concat("/").concat(name).concat(".png");

        final Java2DRenderer renderer = new Java2DRenderer(document, width, -1);
        renderer.setBufferedImageType(BufferedImage.TYPE_INT_RGB);
        final BufferedImage img = renderer.getImage();
        final FSImageWriter imageWriter = new FSImageWriter();
        imageWriter.setWriteCompressionQuality(1f);
        imageWriter.setWriteCompressionMode(ImageWriteParam.MODE_COPY_FROM_METADATA);
        //        imageWriter.setWriteCompressionType();
        imageWriter.write(img, filePath);

        return filePath;
    }

    private static String htmlCovertTohtml(String str) {
        Tidy tidy = new Tidy();
        tidy.setXmlOut(true);
        tidy.setQuiet(true);
        tidy.setShowWarnings(false);
        tidy.setShowErrors(0);
        tidy.setEncloseBlockText(true);
        tidy.setInputEncoding("UTF-8");
        tidy.setOutputEncoding("UTF-8");
        Properties prop = new Properties();
        prop.put("new-blocklevel-tags", "canvas");
        tidy.getConfiguration().addProps(prop);

        StringReader reader;
        StringWriter writer;
        try {
            reader = new StringReader(str);
            writer = new StringWriter();
            // 输出的文件

            tidy.parse(reader, writer);
            String result = writer.toString();
            // 转换完成关闭输入输出流
            writer.close();
            reader.close();
            return result;
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    //过滤无效字符
    public static String stripNonValidXMLCharacters(String in) {
        StringBuffer out = new StringBuffer(); // Used to hold the output.
        char current; // Used to reference the current character.

        if (in == null || ("".equals(in)))
            return ""; // vacancy test.
        for (int i = 0; i < in.length(); i++) {
            current = in.charAt(i); // NOTE: No IndexOutOfBoundsException caught
            // here; it should not happen.
            if ((current == 0x9) || (current == 0xA) || (current == 0xD)
                    || ((current >= 0x20) && (current <= 0xD7FF))
                    || ((current >= 0xE000) && (current <= 0xFFFD))
                    || ((current >= 0x10000) && (current <= 0x10FFFF)))
                out.append(current);
        }
        return out.toString();
    }

    public static String fixEndTag(String html) {
        Pattern pattern = Pattern.compile("<(\\s+)/[a-zA-Z]+>");
        Matcher matcher = pattern.matcher(html);
        StringBuffer sb = new StringBuffer();
        while (matcher.find()) {
            String group = matcher.group(0);
            String result = group.replaceAll("\\s", "");
            matcher.appendReplacement(sb, result);
        }
        matcher.appendTail(sb);
        return sb.toString();
    }

    public static String fixSpace(String html) {
        final String pattern = "&(\\s*)nbsp;|\\n";
        return html.replaceAll(pattern, " ");
    }

    
}

html = fixEndTag(html);

这句的闭合标签，并不是将没有闭合的标签闭合，而是上一行中过滤了空格导致的例如</   div>的问题，在处理完 html 之后，我发现有的闭合标签换行显示了，导致在合并行的时候，标签中间出现了空格。所以这里的闭合标签，可以理解为过滤闭合标签中间的多余空格。

有问题欢迎沟通提问~