使用Jsoup.jar寫的工具類(java提取Html中的文本)

標籤：

package cn.anzhuoyue.jfinalBlog.util; import org.jsoup.Jsoup;import org.jsoup.nodes.Document;import org.jsoup.nodes.Element;import org.jsoup.safety.Whitelist;import com.jfinal.kit.StringKit; public class HtmlUtil {         // 只有純文字可以通過    public static String getText(String html) {        if (html == null)            return null;        return Jsoup.clean(html, Whitelist.none());    }         // 以下標籤可以通過    // b, em, i, strong, u. 純文字    public static String getSimpleHtml(String html) {        if (html == null)            return null;        return Jsoup.clean(html, Whitelist.simpleText());    }         // 以下標籤可以通過    //a, b, blockquote, br, cite, code, dd, dl, dt, em, i, li, ol, p, pre, q, small, strike, strong, sub, sup, u, ul    public static String getBasicHtml(String html) {        if (html == null)            return null;        return Jsoup.clean(html, Whitelist.basic());    }         //在basic基礎上  增加圖片通過    public static String getBasicHtmlandimage(String html) {        if (html == null)            return null;        return Jsoup.clean(html, Whitelist.basicWithImages());    }    // 以下標籤可以通過    //a, b, blockquote, br, caption, cite, code, col, colgroup, dd, dl, dt, em, h1, h2, h3, h4, h5, h6, i, img, li, ol, p, pre, q, small, strike, strong, sub, sup, table, tbody, td, tfoot, th, thead, tr, u, ul    public static String getFullHtml(String html) {        if (html == null)            return null;        return Jsoup.clean(html, Whitelist.relaxed());    }         //只允許指定的html標籤    public static String clearTags(String html, String ...tags) {        Whitelist wl = new Whitelist();        return Jsoup.clean(html, wl.addTags(tags));    }         // 對關鍵字加上顏色    public static String markKeywods (String keywords, String target) {        if (StringKit.notBlank(keywords)) {            String[] arr = keywords.split(" ");            for (String s : arr) {                if (StringKit.notBlank(s)) {                    String temp = "<span class=\"highlight\">" + s + "</span>";                    if(temp!=null)                        target = target.replaceAll(s, temp);                }            }        }        return target;    }     // 擷取文章中的img url    public static String getImgSrc(String html) {        if (html == null)            return null;        Document doc = Jsoup.parseBodyFragment(html);        Element image = doc.select("img").first();        return image == null ? null : image.attr("src");    }}

　　

使用Jsoup.jar寫的工具類(java提取Html中的文本)