Example usage for org.jsoup.select Elements first

Introduction

In this page you can find the example usage for org.jsoup.select Elements first.

Prototype

public Element first()

Source Link

Document

Get the first matched element.

Usage

From source file:Search.DataManipulation.DataParser.java

public Map<String, String> getRatingData(Document dom) {
    Map<String, String> ratingData = new HashMap<>();

    Elements ratingClass = dom.getElementsByClass("score-container");
    Elements ratingDom = ratingClass.first().children();

    for (Element rating : ratingDom) {
        String item = rating.attr("itemprop");
        String content = rating.attr("content");

        if (item.equals("ratingValue")) {
            ratingData.put("rating", content);
        } else if (item.equals("ratingCount")) {
            ratingData.put(item, content);
        }/* w w w  .j  a  va2 s .  co  m*/
    }
    return ratingData;
}

From source file:solarrecorder.SolarRecorder.java

private void getProdData() throws IOException {
    org.jsoup.nodes.Document doc = Jsoup.connect("http://envoy/production").get();

    Element h1 = doc.getElementsByTag("h1").first();
    Element table = h1.nextElementSibling();
    Elements alltr = table.getElementsByTag("tbody").first().getElementsByTag("tr");
    for (Element tr : alltr) {
        Elements alltd = tr.getElementsByTag("td");

        if (alltd.size() == 2) {
            String name = alltd.first().text();
            String value = alltd.last().text();
            switch (name) {
            case "Currently":
            case "Today":
                envoyData.add(new EnvoyData(name, value));
                break;
            }/*from   w  ww  . ja  v  a 2s.c o  m*/
        }
    }
}

From source file:solarrecorder.SolarRecorder.java

private void getSysData() throws IOException {
    org.jsoup.nodes.Document doc = Jsoup.connect("http://envoy").get();

    Elements allh2 = doc.getElementsByTag("h2");
    for (Element h2 : allh2) {
        if (h2.text().equals("System Statistics")) {
            Elements tables = h2.parent().getElementsByTag("table");
            Elements alltr = tables.first().getElementsByTag("tbody").first().getElementsByTag("tr");
            for (Element tr : alltr) {
                Elements alltd = tr.getElementsByTag("td");
                String name = alltd.first().text();
                String value = alltd.last().text();
                if (name.equals("Number of Microinverters Online")) {
                    envoyData.add(new EnvoyData(name, value));
                }// ww w . j av a 2  s.c o  m
            }
        }
    }
}

From source file:wherehows.common.utils.GitUtil.java

/**
 * Crawlling the project page to get list of repositories, only works for Gitorious
 * @param projectUrl the project url e.g. https://git.example.com/project
 * @return List of path of repositories e.g. project/repo
 * @throws IOException/*w  w w.  ja  v a  2 s  .  c o m*/
 */
public static Map<String, String> getRepoListFromProject(String projectUrl) throws IOException {

    Map<String, String> repoList = new HashMap<>();
    Document doc = Jsoup.connect(projectUrl).data("format", "xml").get();
    Elements repos = doc.getElementsByTag("repositories");
    Elements mainlines = repos.first().getElementsByTag("mainlines");
    Elements repo = mainlines.first().getElementsByTag("repository");

    for (Element e : repo) {
        String repoName = e.getElementsByTag("name").first().text();
        String repoUrl = e.getElementsByTag("clone_url").first().text();
        repoList.put(repoName.trim(), repoUrl.trim());
    }

    return repoList;
}

From source file:xxx.web.comments.debates.impl.ProConOrgParser.java

@Override
public Debate parseDebate(InputStream inputStream) throws IOException {
    Debate result = new Debate();

    Document doc = Jsoup.parse(inputStream, "UTF-8", "http://www.procon.org/");

    // Set the Url of the doc

    // title/*from w w  w .  j a  v a2s  .c  om*/
    Element body = doc.body();
    Elements debateTitleElements = body.select("h2");
    //        Elements debateTitleElements = body.select("p[class=title]").select("p[style]");

    if (debateTitleElements.first() == null) {
        // not a debate
        return null;
    }

    String title = Utils.normalize(debateTitleElements.first().text());
    result.setTitle(title);

    Elements proConTr = body.select("tr > td > b:contains(PRO \\(yes\\))");

    if (proConTr == null || proConTr.parents() == null || proConTr.parents().first() == null
            || proConTr.parents().first().parents() == null
            || proConTr.parents().first().parents().first() == null
            || proConTr.parents().first().parents().first().nextElementSibling() == null) {
        // not a pro-con debate
        return null;
    }

    Element trAnswers = proConTr.parents().first().parents().first().nextElementSibling();

    // the PRO side
    Element proTd = trAnswers.select("td").get(0);
    Element conTd = trAnswers.select("td").get(1);

    //        System.out.println(proTd.select("blockquote").size());
    //        System.out.println(conTd.select("blockquote").size());

    for (Element text : proTd.select("blockquote > div[class=editortext]")) {
        Argument argument = new Argument();
        argument.setStance("pro");
        argument.setText(extractPlainTextFromTextElement(text));
        argument.setOriginalHTML(text.html());

        // set ID
        idCounter++;
        argument.setId("pcq_" + idCounter);

        if (!argument.getText().isEmpty()) {
            result.getArgumentList().add(argument);
        } else {
            System.err.println("Failed to extract text from " + text.html());
        }
    }

    for (Element text : conTd.select("blockquote > div[class=editortext]")) {
        Argument argument = new Argument();
        argument.setStance("con");
        argument.setText(extractPlainTextFromTextElement(text));
        argument.setOriginalHTML(text.html());

        idCounter++;
        argument.setId("pcq_" + idCounter);

        if (!argument.getText().isEmpty()) {
            result.getArgumentList().add(argument);
        } else {
            System.err.println("Failed to extract text from " + text.html());
        }
    }

    // show some stats:
    Map<String, Integer> map = new HashMap<>();
    map.put("pro", 0);
    map.put("con", 0);
    for (Argument argument : result.getArgumentList()) {
        map.put(argument.getStance(), map.get(argument.getStance()) + 1);
    }
    System.out.println(map);

    return result;
}