HtmlUtil.java

package com.anthony.library.utils;

import java.net.HttpURLConnection;
import java.net.URL;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;


public class HtmlUtil {

    //css样式,隐藏header
    private static final String HIDE_HEADER_STYLE = "<style>div.headline{display:none;}</style>";

    //css style tag,需要格式化
    private static final String NEEDED_FORMAT_CSS_TAG = "<link rel=\"stylesheet\" type=\"text/css\" href=\"%s\"/>";

    // js script tag,需要格式化
    private static final String NEEDED_FORMAT_JS_TAG = "<script src=\"%s\"></script>";

    public static final String MIME_TYPE = "text/html; charset=utf-8";

    public static final String ENCODING = "utf-8";

    private HtmlUtil() {

    }

    /**
     * 根据css链接生成Link标签
     *
     * @param url String
     * @return String
     */
    public static String createCssTag(String url) {

        return String.format(NEEDED_FORMAT_CSS_TAG, url);
    }

    /**
     * 根据多个css链接生成Link标签
     *
     * @param urls List<String>
     * @return String
     */
    public static String createCssTag(List<String> urls) {

        final StringBuilder sb = new StringBuilder();
        for (String url : urls) {
            sb.append(createCssTag(url));
        }
        return sb.toString();
    }

    /**
     * 根据js链接生成Script标签
     *
     * @param url String
     * @return String
     */
    public static String createJsTag(String url) {

        return String.format(NEEDED_FORMAT_JS_TAG, url);
    }

    /**
     * 根据多个js链接生成Script标签
     *
     * @param urls List<String>
     * @return String
     */
    public static String createJsTag(List<String> urls) {

        final StringBuilder sb = new StringBuilder();
        for (String url : urls) {
            sb.append(createJsTag(url));
        }
        return sb.toString();
    }

    /**
     * 根据样式标签,html字符串,js标签
     * 生成完整的HTML文档
     */

    public static String createHtmlData(String html, List<String> cssList, List<String> jsList) {
        final String css = HtmlUtil.createCssTag(cssList);
        final String js = HtmlUtil.createJsTag(jsList);
        return css.concat(HIDE_HEADER_STYLE).concat(html).concat(js);
    }

    /**
     * url is usable
     *
     * @param url
     * @return
     */
    public static boolean isUrlUsable(String url) {
        if (StringUtils.isEmpty(url)) {
            return false;
        }

        URL urlTemp = null;
        HttpURLConnection connt = null;
        try {
            urlTemp = new URL(url);
            connt = (HttpURLConnection) urlTemp.openConnection();
            connt.setRequestMethod("HEAD");
            int returnCode = connt.getResponseCode();
            if (returnCode == HttpURLConnection.HTTP_OK) {
                return true;
            }
        } catch (Exception e) {
            return false;
        } finally {
            connt.disconnect();
        }
        return false;
    }

    /**
     * is url
     *
     * @param url
     * @return
     */
    public static boolean isUrl(String url) {
        Pattern pattern = Pattern.compile("^([hH][tT]{2}[pP]://|[hH][tT]{2}[pP][sS]://)(([A-Za-z0-9-~]+).)+([A-Za-z0-9-~\\/])+$");
        return pattern.matcher(url).matches();
    }


    //替换html标签
    public static String delHTMLTag(String htmlStr) {
        String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; //定义script的正则表达式
        String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式
        String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式

        Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
        Matcher m_script = p_script.matcher(htmlStr);
        htmlStr = m_script.replaceAll(""); //过滤script标签

        Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
        Matcher m_style = p_style.matcher(htmlStr);
        htmlStr = m_style.replaceAll(""); //过滤style标签

        Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
        Matcher m_html = p_html.matcher(htmlStr);
        htmlStr = m_html.replaceAll(""); //过滤html标签

        return htmlStr.trim(); //返回文本字符串
    }
}