Example usage for org.jsoup.parser Parser htmlParser

Introduction

In this page you can find the example usage for org.jsoup.parser Parser htmlParser.

Prototype

public static Parser htmlParser()

Source Link

Document

Create a new HTML parser.

Usage

From source file:dslab.crawler.pack.CrawlerPack.java

public org.jsoup.nodes.Document htmlToJsoupDoc(String html) {

    Document jsoupDoc = Jsoup.parse(html, "UTF-8", Parser.htmlParser());
    jsoupDoc.charset(StandardCharsets.UTF_8);

    return jsoupDoc;
}

From source file:com.github.abola.crawler.CrawlerPack.java

/**
 *  HTML  Jsoup Document /* www. j a  v a 2 s .  co m*/
 *
 * HTMLJsoup HTML Parser
 *
 * @param html Html document
 * @return org.jsoup.nodes.Document
 */
public org.jsoup.nodes.Document htmlToJsoupDoc(String html) {

    //  html(html/html5)  jsoup Document 
    Document jsoupDoc = Jsoup.parse(html, "UTF-8", Parser.htmlParser());
    jsoupDoc.charset(StandardCharsets.UTF_8);

    return jsoupDoc;
}

From source file:org.b3log.solo.plugin.list.ListHandler.java

@Override
public void action(final Event<JSONObject> event) throws EventException {
    final JSONObject data = event.getData();
    final JSONObject article = data.optJSONObject(Article.ARTICLE);

    String content = article.optString(Article.ARTICLE_CONTENT);

    final Document doc = Jsoup.parse(content, StringUtils.EMPTY, Parser.htmlParser());
    doc.outputSettings().prettyPrint(false);

    final StringBuilder listBuilder = new StringBuilder();

    listBuilder.append("<link rel=\"stylesheet\" type=\"text/css\" href=\"" + Latkes.getStaticServePath()
            + "/plugins/list/style.css\" />");

    final Elements hs = doc.select("h1, h2, h3, h4, h5");

    listBuilder.append("<ul class='b3-solo-list'>");
    for (int i = 0; i < hs.size(); i++) {
        final Element element = hs.get(i);
        final String tagName = element.tagName().toLowerCase();
        final String text = element.text();
        final String id = "b3_solo_" + tagName + "_" + i;

        element.before("<span id='" + id + "'></span>");

        listBuilder.append("<li class='b3-solo-list-").append(tagName).append("'><a href='#").append(id)
                .append("'>").append(text).append("</a></li>");
    }//from  w  w  w.j  a va 2 s.  c o m
    listBuilder.append("</ul>");

    final Element body = doc.getElementsByTag("body").get(0);

    content = listBuilder.toString() + body.html();

    article.put(Article.ARTICLE_CONTENT, content);
}

From source file:org.b3log.symphony.util.Markdowns.java

/**
 * Gets the safe HTML content of the specified content.
 *
 * @param content the specified content// w w w  . j a  v a  2 s  .com
 * @param baseURI the specified base URI, the relative path value of href will starts with this URL
 * @return safe HTML content
 */
public static String clean(final String content, final String baseURI) {
    final Document.OutputSettings outputSettings = new Document.OutputSettings();
    outputSettings.prettyPrint(false);

    final String tmp = Jsoup.clean(content, baseURI,
            Whitelist.relaxed().addAttributes(":all", "id", "target", "class")
                    .addTags("span", "hr", "kbd", "samp", "tt", "del", "s", "strike", "u")
                    .addAttributes("iframe", "src", "width", "height", "border", "marginwidth", "marginheight")
                    .addAttributes("audio", "controls", "src")
                    .addAttributes("video", "controls", "src", "width", "height")
                    .addAttributes("source", "src", "media", "type")
                    .addAttributes("object", "width", "height", "data", "type")
                    .addAttributes("param", "name", "value")
                    .addAttributes("input", "type", "disabled", "checked").addAttributes("embed", "src", "type",
                            "width", "height", "wmode", "allowNetworking"),
            outputSettings);
    final Document doc = Jsoup.parse(tmp, baseURI, Parser.htmlParser());

    final Elements ps = doc.getElementsByTag("p");
    for (final Element p : ps) {
        p.removeAttr("style");
    }

    final Elements iframes = doc.getElementsByTag("iframe");
    for (final Element iframe : iframes) {
        final String src = StringUtils.deleteWhitespace(iframe.attr("src"));
        if (StringUtils.startsWithIgnoreCase(src, "javascript")
                || StringUtils.startsWithIgnoreCase(src, "data:")) {
            iframe.remove();
        }
    }

    final Elements objs = doc.getElementsByTag("object");
    for (final Element obj : objs) {
        final String data = StringUtils.deleteWhitespace(obj.attr("data"));
        if (StringUtils.startsWithIgnoreCase(data, "data:")
                || StringUtils.startsWithIgnoreCase(data, "javascript")) {
            obj.remove();

            continue;
        }

        final String type = StringUtils.deleteWhitespace(obj.attr("type"));
        if (StringUtils.containsIgnoreCase(type, "script")) {
            obj.remove();
        }
    }

    final Elements embeds = doc.getElementsByTag("embed");
    for (final Element embed : embeds) {
        final String data = StringUtils.deleteWhitespace(embed.attr("src"));
        if (StringUtils.startsWithIgnoreCase(data, "data:")
                || StringUtils.startsWithIgnoreCase(data, "javascript")) {
            embed.remove();

            continue;
        }
    }

    final Elements as = doc.getElementsByTag("a");
    for (final Element a : as) {
        a.attr("rel", "nofollow");

        final String href = a.attr("href");
        if (href.startsWith(Latkes.getServePath())) {
            continue;
        }

        a.attr("target", "_blank");
    }

    final Elements audios = doc.getElementsByTag("audio");
    for (final Element audio : audios) {
        audio.attr("preload", "none");
    }

    final Elements videos = doc.getElementsByTag("video");
    for (final Element video : videos) {
        video.attr("preload", "none");
    }

    String ret = doc.body().html();
    ret = ret.replaceAll("(</?br\\s*/?>\\s*)+", "<br>"); // patch for Jsoup issue

    return ret;
}