Java Code Examples for org.jsoup.nodes.Element#append()

public static void main(String[] args) {
    
    String d = "<span><div>test</div></span>";
    Document doc = Jsoup.parse(d);
    Element div = doc.select("div").first(); // <div></div>
    div.html("<p>lorem ipsum</p>"); // <div><p>lorem ipsum</p></div>
    div.prepend("<p>First</p>");
    div.append("<p>Last</p>");
    // now: <div><p>First</p><p>lorem ipsum</p><p>Last</p></div>
    div.appendElement(d);
    Element span = doc.select("span").first(); // <span>One</span>
    span.wrap("<li><a href='http://example.com/'></a></li>");
    // now: <li><a href="http://example.com"><span>One</span></a></li>
    System.out.println(doc.html());
    
    String s = Jsoup.clean(doc.html(), "", Whitelist.relaxed(), new OutputSettings().prettyPrint(false));
    
    System.out.println(s);
}
 

@Override
protected void writeBody(JCas jCas, Element body) {
  // Entities
  Map<Integer, String> insertPositions = getEntityInsertPositions(jCas);

  Element div = body.appendElement("div");
  div.attr("style", "white-space: pre-line");

  String text = jCas.getDocumentText();
  Integer offset = 0;
  for (Entry<Integer, String> pos : insertPositions.entrySet()) {
    String insert = pos.getValue();
    text =
        text.substring(0, pos.getKey() + offset) + insert + text.substring(pos.getKey() + offset);
    offset += insert.length();
  }

  div.append(text);
}
 

/**
 * 处理mpvoice音频节点
 * @param voiceElement
 */
public void parseVoiceElement(Element voiceElement) {
    String voiceURL = WxCrawlerConstant.VOICE_URL + voiceElement.attr("voice_encode_fileid");
    ResultBase<String> newURL = getOssValue(voiceURL);
    if (newURL.isSuccess()) {
        voiceElement.append("<audio src=\"" + newURL + "\">您的浏览器不支持audio标签</audio>");
    } else {
        log.info("Failed to voice resourceTranslation, voiceURL={}", voiceURL);
    }
}
 

private static void createTestcaseFiles() throws IOException {
    File srcDir = new File(RGAA3_TESTCASE_PATH);
    for (File file : srcDir.listFiles()) {
        String fileName = file.getName().replace("Rgaa30Rule", "").replace(".java", "");
        String theme = fileName.substring(0, 2);
        String crit = fileName.substring(2, 4);
        String test = fileName.substring(4, 6);
        String testKey = Integer.valueOf(theme).toString()+"-"+Integer.valueOf(crit).toString()+"-"+Integer.valueOf(test).toString();
        String wrongKey = theme+"."+crit+"."+test;
        for (File testcase : file.listFiles()) {
            if (testcase.isFile() && testcase.getName().contains("html")) {
                Document doc = Jsoup.parse(FileUtils.readFileToString(testcase));
                Element detail = doc.select(".test-detail").first();
                if (detail == null) {
                    System.out.println(doc.outerHtml());
                } else {
                    detail.tagName("div");
                    detail.text("");
                    for (Element el : detail.children()) {
                        el.remove();
                    }
                    if (!detail.hasAttr("lang")) {
                        detail.attr("lang", "fr");
                    }
                    detail.append("\n"+RGAA3.get(testKey).ruleRawHtml+"\n");
                    doc.outputSettings().escapeMode(Entities.EscapeMode.xhtml);
                    doc.outputSettings().outline(false);
                    doc.outputSettings().indentAmount(4);
                    String outputHtml = doc.outerHtml();
                    if (outputHtml.contains(wrongKey)) {
                        outputHtml = outputHtml.replaceAll(wrongKey, RGAA3.get(testKey).getRuleDot());
                    }
                    FileUtils.writeStringToFile(testcase, outputHtml);
                }
            }
        }
    }
}
 

/**
 * Add the supplied HTML to the end of each matched element's inner HTML.
 * @param html HTML to add inside each element, after the existing HTML
 * @return this, for chaining
 * @see Element#append(String)
 */
public Elements append(String html) {
    for (Element element : this) {
        element.append(html);
    }
    return this;
}
 

/**
 * Add the supplied HTML to the end of each matched element's inner HTML.
 * @param html HTML to add inside each element, after the existing HTML
 * @return this, for chaining
 * @see Element#append(String)
 */
public Elements append(String html) {
    for (Element element : this) {
        element.append(html);
    }
    return this;
}
 

/**
 * Add the supplied HTML to the end of each matched element's inner HTML.
 * @param html HTML to add inside each element, after the existing HTML
 * @return this, for chaining
 * @see Element#append(String)
 */
public Elements append(String html) {
    for (Element element : this) {
        element.append(html);
    }
    return this;
}
 

private static String[] downloadTrends() throws Exception
{
    String query = constructQuery();
    InputStream is = new URL(query).openStream();
    try
    {
        StringWriter writer = new StringWriter();
        IOUtils.copy(is, writer);
        JSONObject json = new JSONObject(writer.toString());
        json = json.getJSONObject("responseData");
        json = json.getJSONObject("feed");

        JSONArray arr = json.getJSONArray("entries");
        List<String> res = new ArrayList();
        for (int i = 0; i < arr.length(); i++)
        {
            JSONObject tmp = arr.getJSONObject(i);
            String en = tmp.getString("content");

            Document doc = Jsoup.parse(en);
            for (Element t : doc.select("a"))
                t.append(".");
            
            en = doc.text();
            res.addAll(Arrays.asList(en.split("\\.")));
        }

        return getNonEmptyTrends(res);
    }
    finally
    {
        is.close();
    }
}
 

public void createSite(ExplorerResult result) throws IOException {
    InputStream inputStream = getClass()
            .getClassLoader()
            .getResourceAsStream("template.html");

    Document document = Jsoup.parse(inputStream, "UTF-8", URI);
    Element contentList = document.body().getElementById("content-list");
    Element details = document.body().getElementById("details");


    List<TypeInfo> typeInfos = result.getTypeInfos();
    for (TypeInfo typeInfo : typeInfos) {
        StringBuilder listEntry = createListEntry(typeInfo);
        contentList.append(listEntry.toString());

        String detailView = createDetailView(typeInfo);
        details.append(detailView);
    }

    rewriteRelativeUrls(document);

    File file = new File("_site/index.html");
    BufferedWriter htmlWriter = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file), "UTF-8"));
    htmlWriter.write(document.toString());
    htmlWriter.flush();
    htmlWriter.close();
}
 

/**
 * Add the supplied HTML to the end of each matched element's inner HTML.
 * @param html HTML to add inside each element, after the existing HTML
 * @return this, for chaining
 * @see Element#append(String)
 */
public Elements append(String html) {
    for (Element element : contents) {
        element.append(html);
    }
    return this;
}
 

@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
    final FlowFile flowFile = session.get();
    if (flowFile == null) {
        return;
    }

    final Document doc;
    final Elements eles;
    try {
        doc = parseHTMLDocumentFromFlowfile(flowFile, context, session);
        eles = doc.select(context.getProperty(CSS_SELECTOR).evaluateAttributeExpressions().getValue());
    } catch (Exception ex) {
        getLogger().error("Failed to extract HTML from {} due to {}; routing to {}", new Object[] {flowFile, ex.toString(), REL_INVALID_HTML.getName()}, ex);
        session.transfer(flowFile, REL_INVALID_HTML);
        return;
    }


    if (eles == null || eles.isEmpty()) {
        // No element found
        session.transfer(flowFile, REL_NOT_FOUND);
    } else {
        final String putValue = context.getProperty(PUT_VALUE).evaluateAttributeExpressions(flowFile).getValue();

        for (final Element ele : eles) {
            switch (context.getProperty(PUT_LOCATION_TYPE).getValue()) {
                case APPEND_ELEMENT:
                    ele.append(putValue);
                    break;
                case PREPEND_ELEMENT:
                    ele.prepend(putValue);
                    break;
            }
        }

        FlowFile ff = session.write(session.create(flowFile), new StreamCallback() {
            @Override
            public void process(final InputStream in, final OutputStream out) throws IOException {
                out.write(doc.html().getBytes(StandardCharsets.UTF_8));
            }
        });

        session.transfer(ff, REL_SUCCESS);

        // Transfer the original HTML
        session.transfer(flowFile, REL_ORIGINAL);
    }
}
 

@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
    final FlowFile flowFile = session.get();
    if (flowFile == null) {
        return;
    }

    final Document doc;
    final Elements eles;
    try {
        doc = parseHTMLDocumentFromFlowfile(flowFile, context, session);
        eles = doc.select(context.getProperty(CSS_SELECTOR).evaluateAttributeExpressions(flowFile).getValue());
    } catch (Exception ex) {
        getLogger().error("Failed to extract HTML from {} due to {}; routing to {}", new Object[] {flowFile, ex.toString(), REL_INVALID_HTML.getName()}, ex);
        session.transfer(flowFile, REL_INVALID_HTML);
        return;
    }


    if (eles == null || eles.isEmpty()) {
        // No element found
        session.transfer(flowFile, REL_NOT_FOUND);
    } else {
        final String putValue = context.getProperty(PUT_VALUE).evaluateAttributeExpressions(flowFile).getValue();

        for (final Element ele : eles) {
            switch (context.getProperty(PUT_LOCATION_TYPE).getValue()) {
                case APPEND_ELEMENT:
                    ele.append(putValue);
                    break;
                case PREPEND_ELEMENT:
                    ele.prepend(putValue);
                    break;
            }
        }

        FlowFile ff = session.write(session.create(flowFile), new StreamCallback() {
            @Override
            public void process(final InputStream in, final OutputStream out) throws IOException {
                out.write(doc.html().getBytes(StandardCharsets.UTF_8));
            }
        });

        session.transfer(ff, REL_SUCCESS);

        // Transfer the original HTML
        session.transfer(flowFile, REL_ORIGINAL);
    }
}
 

@Override
public String process(Document document, String output) {
    
    String copyright  = "Copyright Acme, Inc.";
    
    if(document.isBasebackend("html")) {
        org.jsoup.nodes.Document doc = Jsoup.parse(output, "UTF-8");

        Element contentElement = doc.getElementById("footer-text");
        contentElement.append(copyright);
        
        output = doc.html();
        
    }

    
    return output;
}
 

/**
 * 解析图文格式
 *
 * @param figcaptionText
 * @return
 */
protected Element buildFigcaption(String figcaptionText) {
    final Element figcaption = new Element(Tag.valueOf("figcaption"), "");
    figcaption.append(figcaptionText);
    return figcaption;
}
 

/**
 * 解析段落块格式
 *
 * @param blockquote
 * @param articleBody
 */
protected void buildBlockquote(String blockquote, Element articleBody) {
    final Element blockquoteEl = new Element(Tag.valueOf("blockquote"), "");
    blockquoteEl.append(blockquote);
    articleBody.appendChild(blockquoteEl);
}