Java Whitelist.addAttributes方法代碼示例

import org.jsoup.safety.Whitelist; //導入方法依賴的package包/類
/**
 * Cleans the html content leaving only the following tags: b, em, i, strong, u, br, cite, em, i, p, strong, img, li, ul, ol, sup, sub, s
 * @param content html content
 * @param extraTags any other tags that you may want to keep, e. g. "a"
 * @return
 */
public String cleanContent(String content, String ... extraTags) {
	Whitelist allowedTags = Whitelist.simpleText(); // This whitelist allows only simple text formatting: b, em, i, strong, u. All other HTML (tags and attributes) will be removed.
	allowedTags.addTags("br", "cite", "em", "i", "p", "strong", "img", "li", "ul", "ol", "sup", "sub", "s");
	allowedTags.addTags(extraTags);
	allowedTags.addAttributes("p", "style"); // Serve per l'allineamento a destra e sinistra
	allowedTags.addAttributes("img", "src", "style", "class"); 
	if (Arrays.asList(extraTags).contains("a")) {
		allowedTags.addAttributes("a", "href", "target"); 
	}
	Document dirty = Jsoup.parseBodyFragment(content, "");
	Cleaner cleaner = new Cleaner(allowedTags);
	Document clean = cleaner.clean(dirty);
	clean.outputSettings().escapeMode(EscapeMode.xhtml); // Non fa l'escape dei caratteri utf-8
	String safe = clean.body().html();
	return safe;
}
 

import org.jsoup.safety.Whitelist; //導入方法依賴的package包/類
@Override
public String process(String html) {
    // Parse str into a Document
    Document doc = Jsoup.parseBodyFragment(html);
    doc.select("nav").remove();
    doc.select("div#pdfurl").remove();

    // white list to clean html
    Whitelist wl = Whitelist.relaxed();
    wl.addTags("div", "span", "p", "h1", "h2", "h3", "ul", "ol", "li", "a", "img");
    wl.preserveRelativeLinks(true);
    wl.addAttributes("img", "src");
    wl.addAttributes("a", "href");

    // perform cleaning
    Document cleaned = new Cleaner(wl).clean(doc);
    cleaned.outputSettings().escapeMode(Entities.EscapeMode.xhtml);

    // Remove empty elements
    Set<String> removable = new HashSet<>(Arrays.asList("div", "span", "strong", "p", "h1", "h2", "h3", "ul", "ol", "li", "a"));
    cleaned.select("p:matchesOwn((?is) )").remove();
    // For each element in the cleaned document
    for (Element el : cleaned.getAllElements()) {
        if (el.children().isEmpty() && (!el.hasText() || el.text().replaceAll("\u00a0", "").trim().equals(""))) {
            // Element is empty, check if should be removed
            if (removable.contains(el.tagName())) el.remove();
        }
    }
    // return html for  display
    return cleaned.html();
}
 

import org.jsoup.safety.Whitelist; //導入方法依賴的package包/類
private static synchronized Whitelist buildWhiteList() {
	Whitelist whitelist = new Whitelist();
	whitelist.addTags("a", "b", "blockquote", "br", "caption", "cite", "code", "col", "colgroup", "dd", "div", "dl", "dt", "em", "h1",
			"h2", "h3", "h4", "h5", "h6", "i", "iframe", "img", "li", "ol", "p", "pre", "q", "small", "strike", "strong", "sub", "sup",
			"table", "tbody", "td", "tfoot", "th", "thead", "tr", "u", "ul");

	whitelist.addAttributes("div", "dir");
	whitelist.addAttributes("pre", "dir");
	whitelist.addAttributes("code", "dir");
	whitelist.addAttributes("table", "dir");
	whitelist.addAttributes("p", "dir");
	whitelist.addAttributes("a", "href", "title");
	whitelist.addAttributes("blockquote", "cite");
	whitelist.addAttributes("col", "span", "width");
	whitelist.addAttributes("colgroup", "span", "width");
	whitelist.addAttributes("iframe", "src", "height", "width", "allowfullscreen", "frameborder", "style");
	whitelist.addAttributes("img", "align", "alt", "height", "src", "title", "width", "style");
	whitelist.addAttributes("ol", "start", "type");
	whitelist.addAttributes("q", "cite");
	whitelist.addAttributes("table", "border", "bordercolor", "summary", "width");
	whitelist.addAttributes("td", "border", "bordercolor", "abbr", "axis", "colspan", "rowspan", "width");
	whitelist.addAttributes("th", "border", "bordercolor", "abbr", "axis", "colspan", "rowspan", "scope", "width");
	whitelist.addAttributes("ul", "type");

	whitelist.addProtocols("a", "href", "ftp", "http", "https", "magnet", "mailto");
	whitelist.addProtocols("blockquote", "cite", "http", "https");
	whitelist.addProtocols("img", "src", "http", "https");
	whitelist.addProtocols("q", "cite", "http", "https");

	whitelist.addEnforcedAttribute("a", "target", "_blank");
	whitelist.addEnforcedAttribute("a", "rel", "noreferrer");
	return whitelist;
}
 

import org.jsoup.safety.Whitelist; //導入方法依賴的package包/類
/**
 * Make the query to google and return the data.
 *
 * @param query
 *            textfield for google
 * @return webpage in Document format
 */
private Document getData(String query) throws CaptchaException, EmptyQueryException, UnsupportedEncodingException {
    if (this.query.isEmpty() || this.query == null) {
        throw new EmptyQueryException();
    }

    Connection conn = null;
    Document doc = null;

    String request = "https://www.google.com/search?q=" + URLEncoder.encode( stripXSS(query), "UTF-8");
    if(!tokenCookie.isEmpty()){
        request = request + "&google_abuse=" + URLEncoder.encode(tokenCookie, "UTF-8");
    }

    try {
        conn = Jsoup
                .connect(request)
                .method(Method.GET)
                .userAgent("Mozilla/5.0 (Windows NT 6.3; WOW64; rv:36.0) Gecko/20100101 Firefox/48.0")
                .header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
                .header("Cookie", tokenCookie)
                .header("Connection", "keep-alive")
                .ignoreHttpErrors(true)
                .timeout(5000);

        if(!referer.isEmpty()){
            conn.header("Referer", referer);
        }

        Connection.Response response = conn.execute();

        if (response.statusCode() == 503) {

            referer = response.url().toString();
            idCaptcha = getIDCaptcha(response.parse());

            getCaptcha("https://ipv4.google.com/sorry/image?id=" + idCaptcha + "&hl=es&" + referer.substring(referer.indexOf('?')+1));

            throw new CaptchaException();

        }

        doc = Jsoup.parse(response.body());

        // Clean the response
        Whitelist wl = new Whitelist().basic();
        wl.addAttributes("span", "class");
        Cleaner clean = new Cleaner(wl);
        doc = clean.clean(doc);
    } catch (IOException e) {
        //System.out.println(e.getMessage());
        e.printStackTrace();
    }

    return doc;
}