使用Jsoup提取文章大纲

public static List<ArticleOutline> getLinkNodesNew(String html) {
	if (StringUtils.isBlank(html)) {
	    return new ArrayList<>();
	}
	//解析html
	Document document = Jsoup.parseBodyFragment(html);
	// 提取出h标签
	Elements hTags = document.select("h1,h2,h3,h4,h5,h6");
	//提取大纲信息返回
	return getLinkNodes(hTags);
}

public static List<ArticleOutline> getLinkNodes(Elements allTag) {
    List<ArticleOutline> result = new ArrayList<>();
    for (int i = 0; i < allTag.size(); i++) {
        Element elementI = allTag.get(i);
        Integer hTagNumI = getHTagNum(elementI.tagName());
        //获取子区间集合
        Elements childrenElements = new Elements();
        for (int j = i + 1; j < allTag.size(); j++) {
            Element elementJ = allTag.get(j);
            if (getHTagNum(allTag.get(j).tagName()) <= hTagNumI) {
                break;
            }
            i = j;
            childrenElements.add(elementJ);
        }
        ArticleOutline linkDto = new ArticleOutline(elementI.text(), elementI.id(), elementI.tagName(), new ArrayList<>());
        if (childrenElements.isEmpty()) {
            result.add(linkDto);
            continue;
        } else {
            //递归获取子节点
            linkDto.setChildren(getLinkNodes(childrenElements));
        }
        result.add(linkDto);
    }
    return result;
}

public static Integer getHTagNum(String tagName) {
	return Integer.valueOf(tagName.replace("h", ""));
}

@Data
@AllArgsConstructor
@NoArgsConstructor
public class ArticleOutline implements Serializable {

    //标题
    private String label;
    //路径
    private String id;
    //类型(h1,h2,h3...)
    private String type;
    //子节点
    private List<ArticleOutline> children;

}