Java Utililty Methods HTML Parse Jsoup

List of utility methods to do HTML Parse Jsoup

  1. HOME
  2. Java
  3. H
  4. HTML Parse Jsoup

Description

The list of methods to do HTML Parse Jsoup are organized into topic(s).

Method

Elementparse(String html)
parse 
return Jsoup.parse(html);
Documentparse(URL url, int timeout)
parse 
Document doc = null;
final int LIMIT = 10;
final int LIMIT_SLEEP = 2;
int iteration = 0;
while (null == doc) {
    try {
        doc = Jsoup.connect(url.toString()).timeout(timeout).referrer("http://www.google.com/search")
                .userAgent(
...
DocumentparseByteData(ByteBuffer byteData, String charsetName, String baseUri, Parser parser)
parse Byte Data 
String docData;
Document doc = null;
if (charsetName == null) { 
    docData = Charset.forName(defaultCharset).decode(byteData).toString();
    doc = parser.parseInput(docData, baseUri);
    Element meta = doc.select("meta[http-equiv=content-type], meta[charset]").first();
    if (meta != null) { 
        String foundCharset;
...
StringparseEmail(String content)
parse Email 
StringBuffer sb = new StringBuffer();
Document document = Jsoup.parse(content.toString());
Elements div = document.getElementsByTag("span");
for (Element e : div) {
    sb.append(e.text());
return sb.toString();
DocumentparseFile(String filePath)
parse File 
File inputFile = new File(filePath);
return Jsoup.parse(inputFile, "UTF-8");
voidparseInfoBody(Element element)
parse Info Body 
element.getElementById("mf-section-0").remove();
Elements tabs = element.select("h2");
for (int i = 0, total = tabs.size(); i < total; i++) {
    Element item = tabs.get(i);
    System.err.println(item.text());
    Elements mf_section = element.getElementsByClass("mf-section-" + (i + 1));
    System.err.println(mf_section.text());
System.err.println(tabs.size());
voidparseInfoHeader(Element element)
parse Info Header 
Element infotemplatebox = element.getElementsByClass("infotemplatebox").first();
if (infotemplatebox != null) {
    parseTemplate1_1(element);
    return;
infotemplatebox = element.select("table").first();
if (infotemplatebox != null) {
    parseTemplate1_2(element);
...
MapparsePropertyTable(Element table)
parse Property Table 
Map<String, String> ret = new HashMap<String, String>();
Elements tr = table.select("tr");
for (Element element : tr) {
    addProperty(ret, element);
return ret;
ArrayListparseTable2ArrayList(Document doc, String selectorRow, String selectorCol)
parse Table Array List 
Elements rows = doc.select(selectorRow);
ArrayList<String[]> arrayList = new ArrayList<String[]>();
for (Element row : rows) {
    Elements cols = row.select(selectorCol);
    String[] array = new String[cols.size()];
    for (int i = 0; i < cols.size(); i++) {
        array[i] = cols.get(i).html();
    arrayList.add(array);
return arrayList;
voidparseTemplate1_1(Element element)
parse Templat_ 
JSONObject jsonObject = new JSONObject();
JSONObject jsonItem = new JSONObject();
Element infotemplatebox = element.getElementsByClass("infotemplatebox").first();
Elements elements = infotemplatebox.select("tr");
for (int i = 0, total = elements.size(); i < total; i++) {
    Element item = elements.get(i);
    if (i == 0) {
        jsonObject.put("cover", item.select("img").attr("src"));
...