Java实现富文本转markdown

实现富文本即html语法转md，要求是尽可能展示效果一样，可以有少许误差，另外只实现了html中的body转md，其他标签如head等未实现。

大致思路是：通过jsoup工具获取html节点，再穷举替换。前提是熟悉html以及md语法

依赖如下：

        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.16.1</version>
        </dependency>

代码如下：

import lombok.Data;
import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
 
编程import Java.util.ArrayList;
import java.util.List;
 
public class Html2MarkdownUtil {
 
    public static void main(String[] args) {
        String html = "<p style=\"padding: 0; margin: 10px 0; line-height: 1.5; font-size: 16px;\"><b style=\"padding: 0; margin: 0;\">Hello<font color=\"#c24f4a\" style=\"padding: 0; margin: 0;\">world</font></p>";
        System.out.println(parseHtml2Markdown(html));
    }
 
    /**
     * 解析html2md
     *
     * @param html html
     * @return {@link String}
     */
    public static String parseHtml2Markdown(String html) {
        Document doc = Jsoup.parse(html);
        StringBuilder sb = new StringBuilder();
        for (Element element : doc.body().children()) {
            HtmlElement htmlElement = new HtmlElement(element);
            sb.append(htmlElement.getMarkdownText());
        }
        return sb.toString();
    }
 
    /**
     * 标记文本
     *
     * @param element 要素
     * @return {@link String}
     */
    public static String toMarkdownText(Element element) {
        StringBuilder sb = new StringBuilder();
        String tagName = element.tagName().toLowerCase();
        String text = element.ownText();
        switch (tagName) {
            case "h1":
                sb.append("# ").append(text);
                break;
            case "h2":
        www.devze.com        sb.append("## ").append(text);
                break;
            case "h3":
                sb.append("### ").append(text);
                break;
            case "h4":
                sb.append("#### ").append(text);
                break;
            case "h5":
                sb.append("##### ").append(text);
                break;
            case "h6":
                sb.append("###### ").append(text);
                break;
            case "p":
            case "font":
            case "b":
            case "span":
                sb.append(text);
                break;
            case "ul":
                for (Element child : element.children()) {
                    sb.append("* ").append(child.text().trim()).append("\n");
                }
                break;
            case "ol":
                int index = 1;
                for (Element child : element.children()) {
                    sb.append(index).append(". ").append(child.text().trim()).append("\n");
                    index++;
                }
                break;
            case "a":
                sb.append("[").append(text).append("](").append(element.attr("href")).append(")");
                break;
            case "strong":
                sb.append("**").append(text).append("**");
                break;
            case "em":
                sb.append("_").append(text).append("_");
                break;
            case "blockquote":
                sb.append("> ").append(text);
                break;
            case "img":
                sb.append("![");
                if (element.hasAttr("alt")) {
                    sb.append(element.attr("alt"));
                }
                sb.append("](").append(element.attr("src")).append(")");
                break;
            default:
                break;
        }
        return sb.toString();
    }
 
    @Data
    public static class HtmlElement {
 
        private Element element;
        private String tagName;
        private String ownText;
        private boolean isNewline;
        priwww.devze.comvate List<HtmlElement> children;
 
        public HtmlElement(Element element) {
            this.element vojpi= element;
            this.tagName = element.tagName().toLowerCase();
            this.ownText = element.ownText();
            this.isNewline = isNewline();
            if (!StringUtils.equalsAny(this.tagName, "ul", "ol")) {
                Elements children = element.children();
                if (children.size() > 0) {
                    this.children = new ArrayList<>();
                    for (Element child : 编程客栈children) {
                        this.children.add(new HtmlElement(child));
                    }
                }
            }
        }
 
        public boolean isNewline() {
            return StringUtils.equalsAny(tagName, "h1", "h2", "h3", "h4", "h5", "h6", "p", "ul", "ol", "blockquote");
        }
 
        public String getMarkdownText() {
            StringBuilder sb = new StringBuilder();
            sb.append(toMarkdownText(element));
            if (children != null && children.size() > 0) {
                for (HtmlElement child : children) {
                    sb.append(child.getMarkdownText());
                }
            }
            if (isNewline) {
                sb.append("\n");
            }
            return sb.toString();
        }
    }
}

到此这篇关于Java实现富文本转markdown的文章就介绍到这了,更多相关Java富文本转markdown内容请搜索编程客栈(www.devze.com)以前的文章或继续浏览下面的相关文章希望大家以后多多支持编程客栈(www.devze.com)！