Example usage for org.jsoup.nodes Element text

Introduction

In this page you can find the example usage for org.jsoup.nodes Element text.

Prototype

public String text()

Source Link

Document

Gets the combined text of this element and all its children.

Usage

From source file:Main.java

public static void main(String[] args) throws Exception {
    String html = "<description>" + "..." + "</description>";

    Document doc = Jsoup.parse(html);
    for (Element desc : doc.select("description")) {
        String unescapedHtml = desc.text();
        String src = Jsoup.parse(unescapedHtml).select("img").first().attr("src");
        System.out.println(src);/*from  w w w.  j  ava  2s .co m*/
    }
    System.out.println("Done");
}

From source file:com.rest.samples.getTipoCambioBanxico.java

public static void main(String[] args) {
    String url = "http://www.banxico.org.mx/tipcamb/llenarTiposCambioAction.do?idioma=sp";
    try {/*  w  w w .  ja v  a2  s. c o  m*/
        HttpClient hc = HttpClientBuilder.create().build();
        HttpGet request = new HttpGet(url);
        request.setHeader("User-Agent", "Mozilla/5.0");
        request.setHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");

        HttpResponse res = hc.execute(request);
        if (res.getStatusLine().getStatusCode() != 200) {
            throw new RuntimeException("Failed : HTTP eror code: " + res.getStatusLine().getStatusCode());
        }

        BufferedReader rd = new BufferedReader(new InputStreamReader(res.getEntity().getContent()));
        StringBuffer result = new StringBuffer();
        String line = "";
        while ((line = rd.readLine()) != null) {
            result.append(line);
        }
        Document doc = Jsoup.parse(result.toString());
        Element tipoCambioFix = doc.getElementById("FIX_DATO");
        System.out.println(tipoCambioFix.text());

    } catch (IOException ex) {
        Logger.getLogger(SamplesUseHttpclient.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:com.mmj.app.common.util.SpiderHtmlUtils.java

public static String parserHtml(String html, String select) {
    if (StringUtils.isNotEmpty(html)) {
        Document doc = Jsoup.parse(html);
        Elements linksElements = doc.select(select);
        if (linksElements == null || linksElements.isEmpty()) {
            return null;
        }//from ww w . j a va 2  s  . c  o m
        for (Element ele : linksElements) {
            return ele.text();
        }
    }
    return null;
}

From source file:Main.java

public static void parseHtml(String html) {
    Document document = Jsoup.parse(html);
    Element linkElement = document.select("a").first();
    String linkHref = linkElement.attr("href"); // "http://sample.com"
    String linkText = linkElement.text(); // "This is sample"
    System.out.println(linkHref);
    System.out.println(linkText);
}

From source file:Main.java

public static String getScrapeText(Elements elements, String query) {
    String resultString = "";
    for (Element element : elements.select(query))
        if (element.hasText())
            resultString += element.text().trim() + "\n";
    return resultString.trim();
}

From source file:edu.ucla.cs.scai.swim.qa.ontology.dbpedia.tipicality.DbpediaCsvDownload.java

private static void download(Element e) throws MalformedURLException, IOException {
    for (Element c : e.children()) {
        String tagName = c.tag().getName();
        if (tagName.equals("small")) {
            for (Element c1 : c.children()) {
                if (c1.tag().getName().equals("a") && c1.text().equalsIgnoreCase("csv")) {
                    String href = c1.attr("href");
                    System.out.println("Downloading " + href);
                    try {
                        URL remoteFile = new URL(href);
                        ReadableByteChannel rbc = Channels.newChannel(remoteFile.openStream());
                        String[] s = href.split("\\/");
                        FileOutputStream fos = new FileOutputStream(
                                DBpediaOntology.DBPEDIA_CSV_FOLDER + s[s.length - 1]);
                        fos.getChannel().transferFrom(rbc, 0, Long.MAX_VALUE);
                    } catch (Exception ex) {
                        ex.printStackTrace();
                    }//from  www.jav  a 2 s  .  c o  m
                }
            }
        } else if (tagName.equals("ul")) {
            for (Element c1 : c.children()) {
                if (c1.tagName().equals("li")) {
                    download(c1);
                }
            }
        }
    }
}

From source file:Main.java

private static String parseCardContent(Document doc) {
    try {//  w w  w. j a  v  a 2 s . com
        Element summaryEl = doc.select("div[class=card-summary-content]").get(0);
        summaryEl.select("sup").remove();

        return summaryEl.text();
    } catch (Exception e) {
        e.printStackTrace();
    }
    return null;
}

From source file:io.seldon.importer.articles.AttributesImporterUtils.java

public static List<String> getTagsPartsFromMultipleElement(Elements tagsElements) {
    List<String> tagsParts = new ArrayList<String>();

    for (Element e : tagsElements) {
        String tag = e.text();
        tag = StringUtils.strip(tag);/*w ww . ja  va  2 s.  c  o  m*/
        tag = tag.toLowerCase();
        tagsParts.add(tag);
    }

    return tagsParts;
}

From source file:Main.java

public static String getText(final Element element) {
    Element textTag = element;

    while (!textTag.hasText() && textTag.children().size() > 0) {
        textTag = textTag.children().get(0);
    }/*from  w ww.j  a  v a  2  s  . c o m*/

    return textTag.text();
}

From source file:com.ignorelist.kassandra.steam.scraper.HtmlTagLoader.java

private static void copyText(Iterable<Element> elements, Set<String> target) {
    for (Element element : elements) {
        final String text = element.text();
        if (!Strings.isNullOrEmpty(text)) {
            target.add(text.trim());//from   w  ww .  j  a v a2  s  .  c  o  m
        }
    }
}