记录篇-不是原创

替换html标签，保留空格，之前有这样的一个需求，通过百度找到一个方法，很好用，记录下来。

/**
 * 替换html标签
 * @param html
 * @return
 */
public static String convert(String html)
{
    if (StringUtils.isEmpty(html))
    {
        return "";
    }

    Document document = Jsoup.parse(html);
    Document.OutputSettings outputSettings = new Document.OutputSettings().prettyPrint(false);
    document.outputSettings(outputSettings);
    document.select("br").append("\\n");
    document.select("p").prepend("\\n");
    document.select("p").append("\\n");
    String newHtml = document.html().replaceAll("\\\\n", "\n");
    String plainText = Jsoup.clean(newHtml, "", Whitelist.none(), outputSettings);
    String result = StringEscapeUtils.unescapeHtml(plainText.trim());
    return result;
}

导入两个jar包
        <dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.11.3</version>
</dependency>
    <dependency>
        <groupId>commons-lang</groupId>
        <artifactId>commons-lang</artifactId>
        <version>2.6</version>
    </dependency>
</dependencies>