Example usage for org.jsoup.nodes Element html

List of usage examples for org.jsoup.nodes Element html

  1. HOME
  2. Java
  3. org.jsoup
  4. org.jsoup.nodes.*
  5. Element
  6. html

Introduction

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

Prototype

public String html()

Source Link

Document

Retrieves the element's inner HTML.

Usage

From source file:com.normalexception.app.rx8club.fragment.thread.ThreadFragment.java

/**
 * Grab contents from the forum that the user clicked on
 * @param doc   The document parsed from the link
 * @param id   The id number of the link
 * @return      An arraylist of forum contents
 *//*from  w  ww .  ja va  2 s. c o  m*/
public void getThreadContents(Document doc) {
    // Update pagination
    try {
        Elements pageNumbers = doc.select("div[class=pagenav]");
        if (pageNumbers.first() != null) {
            Elements pageLinks = pageNumbers.first().select("td[class^=vbmenu_control]");
            thisPage = pageLinks.text().split(" ")[1];
            finalPage = pageLinks.text().split(" ")[3];
            Log.d(TAG, String.format("This Page: %s, Final Page: %s", thisPage, finalPage));
        } else {
            Log.d(TAG, "Thread only contains one page");
        }
    } catch (Exception e) {
        Log.e(TAG, "We had an error with pagination", e);
    }

    // Is user thread admin??
    Elements threadTools = doc.select("div[id=threadtools_menu] > form > table");
    if (threadTools.text().contains(MODERATION_TOOLS)) {
        Log.d(TAG, "<><> User has administrative rights here! <><>");
    } else {
        //adminContent.setVisibility(View.GONE);
        lv.removeHeaderView(adminContent);
    }

    // Get the user's actual ID, there is a chance they never got it
    // before
    UserProfile.getInstance().setUserId(HtmlFormUtils.getInputElementValueByName(doc, "loggedinuser"));

    // Get Post Number and security token
    securityToken = HtmlFormUtils.getInputElementValueByName(doc, "securitytoken");

    Elements pNumber = doc.select("a[href^=http://www.rx8club.com/newreply.php?do=newreply&noquote=1&p=]");
    String pNumberHref = pNumber.attr("href");
    postNumber = pNumberHref.substring(pNumberHref.lastIndexOf("=") + 1);
    threadNumber = doc.select("input[name=searchthreadid]").attr("value");

    Elements posts = doc.select("div[id=posts]").select("div[id^=edit]");
    Log.v(TAG, String.format("Parsing through %d posts", posts.size()));
    for (Element post : posts) {
        try {
            Elements innerPost = post.select("table[id^=post]");

            // User Control Panel
            Elements userCp = innerPost.select("td[class=alt2]");
            Elements userDetail = userCp.select("div[class=smallfont]");
            Elements userSubDetail = userDetail.last().select("div");
            Elements userAvatar = userDetail.select("img[alt$=Avatar]");

            // User Information
            PostModel pv = new PostModel();
            pv.setUserName(userCp.select("div[id^=postmenu]").text());
            pv.setIsLoggedInUser(LoginFactory.getInstance().isLoggedIn()
                    ? UserProfile.getInstance().getUsername().equals(pv.getUserName())
                    : false);
            pv.setUserTitle(userDetail.first().text());
            pv.setUserImageUrl(userAvatar.attr("src"));
            pv.setPostDate(innerPost.select("td[class=thead]").first().text());
            pv.setPostId(Utils.parseInts(post.attr("id")));
            pv.setRootThreadUrl(currentPageLink);

            // get Likes if any exist
            Elements eLikes = innerPost.select("div[class*=vbseo_liked] > a");
            List<String> likes = new ArrayList<String>();
            for (Element eLike : eLikes)
                likes.add(eLike.text());
            pv.setLikes(likes);

            Iterator<Element> itr = userSubDetail.listIterator();
            while (itr.hasNext()) {
                String txt = itr.next().text();
                if (txt.contains("Location:"))
                    pv.setUserLocation(txt);
                else if (txt.contains("Posts:"))
                    pv.setUserPostCount(txt);
                else if (txt.contains("Join Date:"))
                    pv.setJoinDate(txt);
            }

            // User Post Content
            pv.setUserPost(formatUserPost(innerPost));

            // User signature
            try {
                Element userSig = innerPost.select("div[class=konafilter]").first();
                pv.setUserSignature(userSig.html());
            } catch (NullPointerException npe) {
            }

            Elements postAttachments = innerPost.select("a[id^=attachment]");
            if (postAttachments != null && !postAttachments.isEmpty()) {
                ArrayList<String> attachments = new ArrayList<String>();
                for (Element postAttachment : postAttachments) {
                    attachments.add(postAttachment.attr("href"));
                }
                pv.setAttachments(attachments);
            }

            pv.setSecurityToken(securityToken);

            // Make sure we aren't adding a blank user post
            if (pv.getUserPost() != null)
                postlist.add(pv);
        } catch (Exception e) {
            Log.w(TAG, "Error Parsing Post...Probably Deleted");
        }
    }
}

From source file:com.normalexception.app.rx8club.fragment.thread.ThreadFragment.java

/**
 * Format the user post by removing the vb style quotes and the 
 * duplicate youtube links//  w w w .ja v  a 2s .  com
 * @param innerPost   The element that contains the inner post
 * @return         The formatted string
 */
private String formatUserPost(Elements innerPost) {
    try {
        Element ipost = innerPost.select("td[class=alt1]").select("div[id^=post_message]").first();

        // Only if there is a post to key off of
        if (ipost != null) {
            // Remove the duplicate youtube links (this is caused by a plugin on 
            // the forum that embeds youtube videos automatically)
            for (Element embedded : ipost.select("div[id^=ame_doshow_post_]"))
                embedded.remove();

            // Remove the vbulletin quotes
            return Utils.reformatQuotes(ipost.html());
        } else {
            return null;
        }
    } catch (Exception e) {
        Log.e(TAG, "Error Parsing Post", e);
        return null;
    }
}

From source file:com.semfapp.adamdilger.semf.protectPlanActivity.java

public void createPdf() {
    Document documentTemplate = null;
    Element body = null;

    try {/*from   ww w  .  ja va  2s  .c  o  m*/
        documentTemplate = Pdf.getTemplate(getApplicationContext(), null);

        body = Jsoup.parse(getAssets().open("protectPlan.html"), "utf-8", "http://www.example.com");

        Elements lists = body.select(".list_box"); //Lists html Elements
        ArrayList<String[]> arrayList = data.getArray(); //editText string arrays

        //for each Element in lists, add each bullet from arrayList.string[] as a <p>
        for (int x = 0; x < lists.size(); x++) {
            String f = "";

            for (String bullet : arrayList.get(x)) {
                f += "<p>" + bullet + "</p>";
            }

            lists.get(x).html(f);
        }
    } catch (Exception e) {
        System.out.println("ERROR: " + e.toString());
    }

    documentTemplate.getElementById("main").html(body.html());

    String filePath = MainActivity.pdf.createFilePath(this, "Protect Plan");

    MainActivity.pdf.createPdfToFile(this, documentTemplate.html(), filePath, null);

    pdfAttatchment = new File(filePath);

}

From source file:net.meiolania.apps.habrahabr.fragments.companies.loader.CompaniesShowLoader.java

@Override
public CompanyFullData loadInBackground() {
    CompanyFullData company = new CompanyFullData();

    try {/*from   ww  w. ja v  a2 s .  co m*/
        Log.i(TAG, "Loading a page: " + url);

        Document document = Jsoup.connect(url).get();

        Elements datas = document.select("div.company_profile > dl");

        int i = 0;
        for (Element data : datas) {
            switch (i) {
            case INFO_DATE:
                company.setDate(data.getElementsByTag("dd").first().text());
                break;
            case INFO_SITE:
                company.setCompanyUrl(data.getElementsByTag("dd").first().text());
                break;
            case INFO_INDUSTRIES:
                company.setIndustries(data.getElementsByTag("dd").first().text());
                break;
            case INFO_LOCATION:
                company.setLocation(data.getElementsByTag("dd").first().text());
                break;
            case INFO_QUANTITY:
                company.setQuantity(data.getElementsByTag("dd").first().text());
                break;
            case INFO_SUMMARY:
                company.setSummary(data.select("dd.summary").first().html());
                break;
            case INFO_MANAGEMENT:

                // TODO: think of a new algorithm
                Elements managers = data.getElementsByTag("dd");
                StringBuilder managerContent = new StringBuilder();

                for (Element manager : managers)
                    managerContent.append(manager.html());
                company.setManagement(managerContent.toString());

                break;
            case INFO_DEVELOPMENT_STAGES:

                Elements stages = data.getElementsByTag("dd");
                StringBuilder stagesContent = new StringBuilder();

                for (Element stage : stages)
                    stagesContent.append(stage.html());
                company.setDevelopmentStages(stagesContent.toString());

                break;
            }
            i++;
        }
    } catch (IOException e) {
    }

    return company;
}

From source file:net.meiolania.apps.habrahabr.fragments.posts.loader.PostShowLoader.java

@Override
public PostsFullData loadInBackground() {
    PostsFullData data = new PostsFullData();

    try {/*  w w w. jav  a 2 s. c  om*/
        Document document = Jsoup.connect(url).get();

        Element title = document.select("span.post_title").first();
        Element hubs = document.select("div.hubs").first();
        Element content = document.select("div.content").first();
        Element date = document.select("div.published").first();
        Element author = document.select("div.author > a").first();

        if (title != null) {
            data.setUrl(url);
            data.setTitle(title.text());
            data.setHubs(hubs.text());
            data.setContent(content.html());
            data.setDate(date.text());
            data.setAuthor(author.text());
        } else
            data.setContent(context.getString(R.string.error_404));
    } catch (IOException e) {
    }

    return data;
}

From source file:net.meiolania.apps.habrahabr.fragments.qa.loader.QaShowLoader.java

@Override
public QaFullData loadInBackground() {
    QaFullData data = new QaFullData();

    try {//from   w  w  w . j  a  va2  s.c om
        Log.i(TAG, "Loading a page: " + url);

        Document document = Jsoup.connect(url).get();

        Element title = document.select("span.post_title").first();
        Element hubs = document.select("div.hubs").first();
        Element content = document.select("div.content").first();
        Element tags = document.select("ul.tags").first();
        Element date = document.select("div.published").first();
        Element author = document.select("div.author > a").first();
        Element answers = document.select("span#comments_count").first();

        data.setTitle(title.text());
        data.setHubs(hubs.text());
        data.setContent(content.html());
        data.setTags(tags.text());
        data.setDate(date.text());
        data.setAuthor(author.text());
        data.setAnswers(answers.text());
    } catch (IOException e) {
    }

    return data;
}

From source file:org.apache.nifi.GetHTMLElement.java

/**
 * Extracts the HTML value based on the configuration values.
 *
 * @return value from the parsed HTML element
 */// w w  w .  ja v a2 s.  c om
private String extractElementValue(String prependValue, final String outputType, String appendValue,
        final Element ele, final String attrKey) {
    if (StringUtils.isEmpty(prependValue)) {
        prependValue = "";
    }
    if (StringUtils.isEmpty(appendValue)) {
        appendValue = "";
    }

    switch (outputType) {
    case ELEMENT_HTML:
        return prependValue + ele.html() + appendValue;
    case ELEMENT_TEXT:
        return prependValue + ele.text() + appendValue;
    case ELEMENT_DATA:
        return prependValue + ele.data() + appendValue;
    case ELEMENT_ATTRIBUTE:
        return prependValue + ele.attr(attrKey) + appendValue;
    default:
        return prependValue + ele.html() + appendValue;
    }
}

From source file:org.apache.nifi.TestModifyHTMLElement.java

@Test
public void testModifyHTML() throws Exception {
    final String MOD_VALUE = "Newly modified HTML to replace " + GDR_WEATHER_TEXT;
    testRunner.setProperty(ModifyHTMLElement.CSS_SELECTOR, "#" + GDR_ID);
    testRunner.setProperty(ModifyHTMLElement.OUTPUT_TYPE, ModifyHTMLElement.ELEMENT_HTML);
    testRunner.setProperty(ModifyHTMLElement.MODIFIED_VALUE, MOD_VALUE);

    testRunner.enqueue(new File("src/test/resources/Weather.html").toPath());
    testRunner.run();/*from w w w .j a  va  2s . c  om*/

    testRunner.assertTransferCount(ModifyHTMLElement.REL_SUCCESS, 1);
    testRunner.assertTransferCount(ModifyHTMLElement.REL_INVALID_HTML, 0);
    testRunner.assertTransferCount(ModifyHTMLElement.REL_ORIGINAL, 1);
    testRunner.assertTransferCount(ModifyHTMLElement.REL_NOT_FOUND, 0);

    List<MockFlowFile> ffs = testRunner.getFlowFilesForRelationship(ModifyHTMLElement.REL_SUCCESS);
    assertTrue(ffs.size() == 1);
    String data = new String(testRunner.getContentAsByteArray(ffs.get(0)));

    //Contents will be the entire HTML doc. So lets use Jsoup again just the grab the element we want.
    Document doc = Jsoup.parse(data);
    Elements eles = doc.select("#" + GDR_ID);
    Element ele = eles.get(0);

    assertTrue(StringUtils.equals(MOD_VALUE, ele.html()));
}

From source file:org.apache.nifi.TestModifyHTMLElement.java

@Test
public void testModifyValueContainsHTMLCharacters() throws Exception {
    final String MOD_VALUE = "Text that contains > and < characters";
    testRunner.setProperty(ModifyHTMLElement.CSS_SELECTOR, "#" + GDR_ID);
    testRunner.setProperty(ModifyHTMLElement.OUTPUT_TYPE, ModifyHTMLElement.ELEMENT_HTML);
    testRunner.setProperty(ModifyHTMLElement.MODIFIED_VALUE, MOD_VALUE);

    testRunner.enqueue(new File("src/test/resources/Weather.html").toPath());
    testRunner.run();//from w w w .  j  a  v a2 s. com

    testRunner.assertTransferCount(ModifyHTMLElement.REL_SUCCESS, 1);
    testRunner.assertTransferCount(ModifyHTMLElement.REL_INVALID_HTML, 0);
    testRunner.assertTransferCount(ModifyHTMLElement.REL_ORIGINAL, 1);
    testRunner.assertTransferCount(ModifyHTMLElement.REL_NOT_FOUND, 0);

    List<MockFlowFile> ffs = testRunner.getFlowFilesForRelationship(ModifyHTMLElement.REL_SUCCESS);
    assertTrue(ffs.size() == 1);
    String data = new String(testRunner.getContentAsByteArray(ffs.get(0)));

    //Contents will be the entire HTML doc. So lets use Jsoup again just the grab the element we want.
    Document doc = Jsoup.parse(data);
    Elements eles = doc.select("#" + GDR_ID);
    Element ele = eles.get(0);

    assertTrue(StringUtils.equals(MOD_VALUE, ele.text()));
    assertTrue(StringUtils.equals(MOD_VALUE.replace(">", "&gt;").replace("<", "&lt;"), ele.html()));
}

From source file:org.apache.nifi.TestPutHTMLElement.java

@Test
public void testAddNewElementToRoot() throws Exception {
    final String MOD_VALUE = "<p>modified value</p>";
    testRunner.setProperty(PutHTMLElement.CSS_SELECTOR, "body");
    testRunner.setProperty(PutHTMLElement.PUT_LOCATION_TYPE, PutHTMLElement.PREPEND_ELEMENT);
    testRunner.setProperty(PutHTMLElement.PUT_VALUE, MOD_VALUE);

    testRunner.enqueue(new File("src/test/resources/Weather.html").toPath());
    testRunner.run();//from ww w.j  av a2 s.  c  o m

    testRunner.assertTransferCount(PutHTMLElement.REL_SUCCESS, 1);
    testRunner.assertTransferCount(PutHTMLElement.REL_INVALID_HTML, 0);
    testRunner.assertTransferCount(PutHTMLElement.REL_ORIGINAL, 1);
    testRunner.assertTransferCount(PutHTMLElement.REL_NOT_FOUND, 0);

    List<MockFlowFile> ffs = testRunner.getFlowFilesForRelationship(PutHTMLElement.REL_SUCCESS);
    assertTrue(ffs.size() == 1);
    String data = new String(testRunner.getContentAsByteArray(ffs.get(0)));

    //Contents will be the entire HTML doc. So lets use Jsoup again just the grab the element we want.
    Document doc = Jsoup.parse(data);
    Elements eles = doc.select("body > p");
    Element ele = eles.get(0);

    assertTrue(StringUtils.equals(MOD_VALUE.replace("<p>", "").replace("</p>", ""), ele.html()));
}