org.jsoup.nodes.Element Java Examples
The following examples show how to use
org.jsoup.nodes.Element.
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: JsoupSuperSubClassListExtractor.java From wandora with GNU General Public License v3.0 | 8 votes |
private void parseTopic(Element classElement, Topic classTopic) throws TopicMapException { String name = classElement.text().trim(); if(name.length() == 0) return; Topic t = getOrCreateTopic(tm, null , name); if(classTopic == null) classTopic = wandoraClass; makeSubclassOf(tm, t, classTopic); // See if the next element is a list (of instances) Element listWrapper = classElement.nextElementSibling(); if(listWrapper != null && !listWrapper.children().isEmpty()) { for(Element listCandidate: listWrapper.children()){ if(listCandidate.tagName().equals("ul")) parseList(listCandidate, t); } } }
Example #2
Source File: ZenPostModel.java From zen4android with MIT License | 6 votes |
public void UpdateSign() { try { mTime = ""; mSign = ""; String token = ZenUtils.getToken(); if (token != null) { ZenURLConnection connection = new ZenURLConnection(ZEN_UPDATE_SIGN_URL + mFid); connection.addRequestHeader("Cookie", "u=" + URLEncoder.encode(token, "utf-8") + ";"); connection.addRequestHeader("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0"); String response = connection.startSychronous(); if (response != null) { Document doc = Jsoup.parse(response); Element signEle = doc.select("input[name=sign]").first(); mSign = signEle.attr("value"); Element timeEle = doc.select("input[name=time]").first(); mTime = timeEle.attr("value"); System.out.println("time: " + mTime + " sign: " + mSign); } } } catch (Exception e) { e.printStackTrace(); } }
Example #3
Source File: RssLoader.java From android-opensource-library-56 with Apache License 2.0 | 6 votes |
private void parseCssSelector(Document document) { Elements elements = document.select("item"); for (Element element : elements) { Item item = new Item(); Elements title = element.select("title"); Elements link = element.select("link"); if (!title.isEmpty()) { item.title = title.get(0).text(); } if (!link.isEmpty()) { item.url = link.get(0).text(); } if (mList == null) { mList = new RssList(); } mList.addItem(item); } }
Example #4
Source File: Aw22Rule05081.java From Asqatasun with GNU Affero General Public License v3.0 | 6 votes |
/** * * @param sspHandler * @param elementHandler * @param elementHandlerWithoutDataTableMarkup */ private void extractTableWithDataTableMarkup( ElementHandler<Element> elementHandler, ElementHandler<Element> elementHandlerWithoutDataTableMarkup) { Elements elementsWithMarkup = new Elements(); for (Element el : elementHandler.get()) { if (el.select(DATA_TABLE_MARKUP_CSS_LIKE_QUERY).size() > 0) { elementsWithMarkup.add(el); } else if (elementHandlerWithoutDataTableMarkup != null) { elementHandlerWithoutDataTableMarkup.add(el); } } elementHandler.clean().addAll(elementsWithMarkup); }
Example #5
Source File: NcepHtmlScraper.java From netcdf-java with BSD 3-Clause "New" or "Revised" License | 6 votes |
private void writeTableAXml(String name, String source, String filename, List<Stuff> stuff) throws IOException { org.jdom2.Element rootElem = new org.jdom2.Element("tableA"); org.jdom2.Document doc = new org.jdom2.Document(rootElem); rootElem.addContent(new org.jdom2.Element("title").setText(name)); rootElem.addContent(new org.jdom2.Element("source").setText(source)); for (Stuff p : stuff) { org.jdom2.Element paramElem = new org.jdom2.Element("parameter"); paramElem.setAttribute("code", Integer.toString(p.no)); paramElem.addContent(new org.jdom2.Element("description").setText(p.desc)); rootElem.addContent(paramElem); } XMLOutputter fmt = new XMLOutputter(Format.getPrettyFormat()); String x = fmt.outputString(doc); try (FileOutputStream fout = new FileOutputStream(dirOut + filename)) { fout.write(x.getBytes(StandardCharsets.UTF_8)); } if (show) System.out.printf("%s%n", x); }
Example #6
Source File: ArticleTextExtractor.java From Xndroid with GNU General Public License v3.0 | 6 votes |
/** * Weights current element. By matching it with positive candidates and * weighting child nodes. Since it's impossible to predict which exactly * names, ids or class names will be used in HTML, major role is played by * child nodes * * @param e Element to weight, along with child nodes */ private int getWeight(Element e, boolean checkextra) { int weight = calcWeight(e); int ownTextWeight = (int) Math.round(e.ownText().length() / 100.0 * 10); weight += ownTextWeight; int childrenWeight = weightChildNodes(e); weight += childrenWeight; // add additional weight using possible 'extragravityscore' attribute if (checkextra) { Element xelem = e.select("[extragravityscore]").first(); if (xelem != null) { // System.out.println("HERE found one: " + xelem.toString()); weight += Integer.parseInt(xelem.attr("extragravityscore")); // System.out.println("WITH WEIGHT: " + xelem.attr("extragravityscore")); } } return weight; }
Example #7
Source File: OutputFormatter.java From JumpGo with Mozilla Public License 2.0 | 6 votes |
private void appendTextSkipHidden(Element e, StringBuilder accum, int indent) { for (Node child : e.childNodes()) { if (unlikely(child)) { continue; } if (child instanceof TextNode) { TextNode textNode = (TextNode) child; String txt = textNode.text(); accum.append(txt); } else if (child instanceof Element) { Element element = (Element) child; if (accum.length() > 0 && element.isBlock() && !lastCharIsWhitespace(accum)) accum.append(' '); else if (element.tagName().equals("br")) accum.append(' '); appendTextSkipHidden(element, accum, indent + 1); } } }
Example #8
Source File: Rgaa30Rule060304.java From Asqatasun with GNU Affero General Public License v3.0 | 6 votes |
@Override protected void check( SSPHandler sspHandler, TestSolutionHandler testSolutionHandler) { if (getLinkElementSelector().isEmpty()) { testSolutionHandler.addTestSolution(TestSolution.NOT_APPLICABLE); return; } prs = sspHandler.getProcessRemarkService(); setServicesToChecker(titlePertinenceElementChecker); if (! getLinkElementSelector().getDecidableElements().isEmpty()) { setServicesToChecker(getDecidableElementsChecker()); for (Element el : getLinkElementSelector().getDecidableElements().get()) { testSolutionHandler.addTestSolution(testLink(sspHandler, el)); } } // reset service and aggregate all the remarks collected locally // for further save prs.resetService(); prs.getRemarkList().addAll(remarks); }
Example #9
Source File: M66ipProxyListPageParser.java From ProxyPool with Apache License 2.0 | 6 votes |
@Override public List<Proxy> parse(String html) { Document document = Jsoup.parse(html); Elements elements = document.select("table tr:gt(1)"); List<Proxy> proxyList = new ArrayList<>(elements.size()); for (Element element : elements){ String ip = element.select("td:eq(0)").first().text(); String port = element.select("td:eq(1)").first().text(); String isAnonymous = element.select("td:eq(3)").first().text(); log.debug("parse result = http://"+ip+":"+port+" "+isAnonymous); if(!anonymousFlag || isAnonymous.contains("匿")){ proxyList.add(new Proxy(ip, Integer.valueOf(port), "http", Constant.TIME_INTERVAL)); } } return proxyList; }
Example #10
Source File: M2DocHTMLParser.java From M2Doc with Eclipse Public License 1.0 | 6 votes |
/** * Sets the unordered list numbering. * * @param context * the {@link Context} * @param element * the ol {@link Element} */ private void setUnorderedListNumbering(Context context, Element element) { final String symbol; if (element.hasAttr(TYPE_ATTR)) { final String type = element.attr(TYPE_ATTR); if ("disc".equals(type)) { symbol = DISC_SYMBOL; } else if ("square".equals(type)) { symbol = SQUARE_SYMBOL; } else if ("circle".equals(type)) { symbol = CIRCLE_SYMBOL; } else { symbol = DISC_SYMBOL; } } else { symbol = DISC_SYMBOL; } if (context.numbering == null) { createNumbering(context); } context.numberingLevel = incrementNumberingLevel(context.numbering, context.numberingLevel, STNumberFormat.BULLET, 1, symbol, false); }
Example #11
Source File: FuckBroDomain.java From TrackRay with GNU General Public License v3.0 | 6 votes |
public Map<String,String> aizhanIcp(String domain){ HashMap<String, String> map = new HashMap<>(); HttpClient httpClient = new HttpClient(); String url = "https://icp.aizhan.com/%s/"; try { ResponseStatus responseStatus = httpClient.get(String.format(url, domain)); String html = responseStatus.getContent(); if (!html.contains("未找到") && html.contains("该单位备案网站") && html.contains("缓存于")) { Document doc = Jsoup.parse(html); Elements trs = doc.select("div#company .table-s1 tbody tr"); for (Element tr : trs) { String title = tr.select("td").get(1).text(); String dom = tr.select("td").get(2).text(); map.put(dom,title); } } } catch (Exception e) { task.getExceptions().add(e); } SysLog.info("ICP反查结束"); return map; }
Example #12
Source File: Rgaa32016Rule100102.java From Asqatasun with GNU Affero General Public License v3.0 | 5 votes |
@Override protected void select(SSPHandler sspHandler) { totalNumberOfElements = sspHandler.getTotalNumberOfElements(); // retrieve element from the nomenclature Nomenclature deprecatedHtmlAttr = nomenclatureLoaderService. loadByCode(PRESENTATION_ATTR_NOM); for (String deprecatedAttr : deprecatedHtmlAttr.getValueList()) { SimpleElementSelector sec = new SimpleElementSelector(buildQuery(deprecatedAttr)); ElementHandler<Element> eh = new ElementHandlerImpl(); sec.selectElements(sspHandler, eh); attrElementHandlerMap.put(deprecatedAttr, eh); } // elements with width attribute that are not img SimpleElementSelector secWidthAttrNotImg = new SimpleElementSelector(ELEMENT_WITH_WITDH_ATTR_NOT_IMG_V2); ElementHandler<Element> ehWithAttrNotImg = new ElementHandlerImpl(); secWidthAttrNotImg.selectElements(sspHandler, ehWithAttrNotImg); attrElementHandlerMap.put(WIDTH_ATTR, ehWithAttrNotImg); // elements with width attribute that are not img SimpleElementSelector secHeightAttrNotImg = new SimpleElementSelector(ELEMENT_WITH_HEIGHT_ATTR_NOT_IMG_V2); ElementHandler<Element> ehHeightAttrNotImg = new ElementHandlerImpl(); secHeightAttrNotImg.selectElements(sspHandler, ehHeightAttrNotImg); attrElementHandlerMap.put(HEIGHT_ATTR, ehHeightAttrNotImg); }
Example #13
Source File: TemplateDataAnalyzer.java From flow with Apache License 2.0 | 5 votes |
private boolean isInsideTemplate(org.jsoup.nodes.Element element, org.jsoup.nodes.Element templateRoot) { if (element == templateRoot) { return false; } if ("template".equalsIgnoreCase(element.tagName())) { return true; } return isInsideTemplate(element.parent(), templateRoot); }
Example #14
Source File: StructuralEvaluator.java From jsoup-learning with MIT License | 5 votes |
public boolean matches(Element root, Element element) { if (root == element) return false; Element prev = element.previousElementSibling(); while (prev != null) { if (evaluator.matches(root, prev)) return true; prev = prev.previousElementSibling(); } return false; }
Example #15
Source File: MotherlessRipper.java From ripme with MIT License | 5 votes |
@Override protected List<String> getURLsFromPage(Document page) { List<String> pageURLs = new ArrayList<>(); for (Element thumb : page.select("div.thumb-container a.img-container")) { if (isStopped()) { break; } String thumbURL = thumb.attr("href"); if (thumbURL.contains("pornmd.com")) { continue; } String url; if (!thumbURL.startsWith("http")) { url = "https://" + DOMAIN + thumbURL; } else { url = thumbURL; } pageURLs.add(url); if (isThisATest()) { break; } } return pageURLs; }
Example #16
Source File: ContestsListFragment.java From fridge with MIT License | 5 votes |
public void parseContests(String html) { Document doc = Jsoup.parse(html); Elements h3 = doc.select("h3"); Elements tables = doc.select(".dataTable"); int flag = 0; contestArrayList.clear(); for (Element table : tables) { Elements tbody = table.getElementsByTag("tbody"); Elements contests = tbody.get(0).children(); for (Element contest : contests) { Element code = contest.child(0); Element name = contest.child(1); Element startDate = contest.child(2); Element endDate = contest.child(3); String cCode = code.text(); String cName = name.text(); String sDate = startDate.text(); String eDate = endDate.text(); Contest contest1 = new Contest(cCode, cName, sDate, eDate, flag); contestArrayList.add(contest1); } flag++; } contestsListAdapter = new ContestsListAdapter(contestArrayList, getActivity()); recyclerView.swapAdapter(contestsListAdapter, false); if (filter != null) contestsListAdapter.setFilter(filter); if (contestArrayList == null || contestArrayList.isEmpty()) { recyclerView.setVisibility(View.GONE); contestsPlaceholder.setVisibility(View.VISIBLE); } else { recyclerView.setVisibility(View.VISIBLE); contestsPlaceholder.setVisibility(View.GONE); } }
Example #17
Source File: ParseEnroll.java From schedge with MIT License | 5 votes |
public static void parseRegistrationNumber(String data) { Document secData = Jsoup.parse(data); Element body = secData.selectFirst("body"); Element section = body.selectFirst("section.main > section"); Elements sections = section.select("div"); for (Element element : sections) { if (element.text().equals("Results") || element.text().equals("Okay")) { continue; } System.out.println(element.text()); } }
Example #18
Source File: NumTest.java From JsoupXpath with Apache License 2.0 | 5 votes |
@Test public void testOnZero() throws Exception { Elements context = new Elements(); Element el = new Element("V"); el.appendText("test 69."); context.add(el); Num n = new Num(); XValue v = n.call(Scope.create(context)); logger.info("v = {}",v); Assert.assertEquals(69,v.asDouble(),0.00000000000001); }
Example #19
Source File: JsoupProcessor.java From AcgClub with MIT License | 5 votes |
/** * Extract first element according to a query */ private static Element element(Element container, String query) { Elements select = container.select(query); if (select.size() == 0) { return null; } return select.first(); }
Example #20
Source File: CityParser.java From zuihou-admin-cloud with Apache License 2.0 | 5 votes |
private List<Area> parseProvince(String url) { String htmlStr = HttpUtil.get(url, CHARSET); Document document = Jsoup.parse(htmlStr); // 获取 class='provincetr' 的元素 Elements elements = document.getElementsByClass("provincetr"); List<Area> provinces = new LinkedList<Area>(); int sort = 1; for (Element element : elements) { // 获取 elements 下属性是 href 的元素 Elements links = element.getElementsByAttribute("href"); for (Element link : links) { String provinceName = link.text(); String href = link.attr("href"); String provinceCode = href.substring(0, 2); Area provinceArea = Area.builder().code(provinceCode + "0000") .label(provinceName).source(url) .sortValue(sort++) .level(new RemoteData<>("PROVINCE")) .fullName(provinceName) .build(); provinceArea.setChildren(parseCity(provinceName, COMMON_URL + href)); StaticLog.info("省级数据: {} ", provinceArea); provinces.add(provinceArea); } } return provinces; }
Example #21
Source File: CombingXPathEvaluator.java From xsoup with MIT License | 5 votes |
@Override public XElements evaluate(Element element) { List<XElements> xElementses = new ArrayList<XElements>(); for (XPathEvaluator xPathEvaluator : xPathEvaluators) { xElementses.add(xPathEvaluator.evaluate(element)); } return new CombiningDefaultXElements(xElementses); }
Example #22
Source File: TianLaiReadUtil.java From MissZzzReader with Apache License 2.0 | 5 votes |
/** * 从搜索html中得到书列表 * * @param html * @return */ public static ArrayList<Book> getBooksFromSearchHtml(String html) { ArrayList<Book> books = new ArrayList<>(); Document doc = Jsoup.parse(html); // Element node = doc.getElementById("results"); // for (Element div : node.children()) { Elements divs = doc.getElementsByClass("result-list"); Element div = divs.get(0); // if (!StringHelper.isEmpty(div.className()) && div.className().equals("result-list")) { for (Element element : div.children()) { Book book = new Book(); Element img = element.child(0).child(0).child(0); book.setImgUrl(img.attr("src")); Element title = element.getElementsByClass("result-item-title result-game-item-title").get(0); book.setName(title.child(0).attr("title")); book.setChapterUrl(title.child(0).attr("href")); Element desc = element.getElementsByClass("result-game-item-desc").get(0); book.setDesc(desc.text()); Element info = element.getElementsByClass("result-game-item-info").get(0); for (Element element1 : info.children()) { String infoStr = element1.text(); if (infoStr.contains("作者:")) { book.setAuthor(infoStr.replace("作者:", "").replace(" ", "")); } else if (infoStr.contains("类型:")) { book.setType(infoStr.replace("类型:", "").replace(" ", "")); } else if (infoStr.contains("更新时间:")) { book.setUpdateDate(infoStr.replace("更新时间:", "").replace(" ", "")); } else { Element newChapter = element1.child(1); book.setNewestChapterUrl(newChapter.attr("href")); book.setNewestChapterTitle(newChapter.text()); } } book.setSource(BookSource.tianlai.toString()); books.add(book); } return books; }
Example #23
Source File: DeckstatsDeckSniffer.java From MtgDesktopCompanion with GNU General Public License v3.0 | 5 votes |
@Override public List<RetrievableDeck> getDeckList() throws IOException { int nbPage = getInt(MAX_PAGE); List<RetrievableDeck> list = new ArrayList<>(); for (int i = 1; i <= nbPage; i++) { Document d = URLTools.extractHtml(getString(URL) + "/" + getString(FORMAT) + "/?lng=fr&page=" + i); Elements e = d.select("tr.touch_row"); for (Element cont : e) { RetrievableDeck deck = new RetrievableDeck(); Element info = cont.select("a").get(0); String idColor = cont.select("img").get(0).attr("src"); idColor = idColor.substring(idColor.lastIndexOf('/') + 1, idColor.lastIndexOf('.')); String name = info.text(); String url = info.attr("href") + "/fr?get_code=1&code_type=bb_deck&code_extended=0&code_html_nl=off"; String auteur = cont.select("a").get(1).text(); deck.setName(name); try { deck.setUrl(new URI(url)); } catch (URISyntaxException e1) { deck.setUrl(null); } deck.setAuthor(auteur); deck.setColor(cacheColor.get(Integer.parseInt(idColor))); list.add(deck); } } return list; }
Example #24
Source File: InputField.java From apogen with Apache License 2.0 | 5 votes |
public InputField(Element singleElement) { super(); tag = "input"; this.type = "text"; // default type this.variableName = UtilsStaticAnalyzer.getElementName(singleElement); this.locator = singleElement.cssSelector(); this.isMethod = false; }
Example #25
Source File: ApiTest.java From MyBlogDemo with Apache License 2.0 | 5 votes |
@Test public void testJsoup3() throws IOException { Document document = Jsoup.connect("https://android-arsenal.com/search?q=Circle").get(); // Elements select = document.select("div.container.content"); Elements select = document.select("div.pc"); int i = 0; for (Element element : select) { System.out.println(element.toString()); i++; System.out.println("---------------------------------------"); if (i == 3) { return; } } }
Example #26
Source File: BootstrapHandler.java From flow with Apache License 2.0 | 5 votes |
private Element createDependencyElement(BootstrapContext context, JsonObject dependencyJson) { String type = dependencyJson.getString(Dependency.KEY_TYPE); if (Dependency.Type.contains(type)) { Dependency.Type dependencyType = Dependency.Type.valueOf(type); return createDependencyElement(context.getUriResolver(), LoadMode.INLINE, dependencyJson, dependencyType); } return Jsoup.parse( dependencyJson.getString(Dependency.KEY_CONTENTS), "", Parser.xmlParser()); }
Example #27
Source File: ImgboxRipper.java From ripme with MIT License | 5 votes |
@Override public List<String> getURLsFromPage(Document doc) { List<String> imageURLs = new ArrayList<>(); for (Element thumb : doc.select("div.boxed-content > a > img")) { String image = thumb.attr("src").replaceAll("thumbs", "images"); image = image.replace("_b", "_o"); image = image.replaceAll("\\d-s", "i"); imageURLs.add(image); } return imageURLs; }
Example #28
Source File: Elements.java From astor with GNU General Public License v2.0 | 5 votes |
/** * Remove an attribute from every matched element. * @param attributeKey The attribute to remove. * @return this (for chaining) */ public Elements removeAttr(String attributeKey) { for (Element element : this) { element.removeAttr(attributeKey); } return this; }
Example #29
Source File: EncodingDetect.java From HaoReader with GNU General Public License v3.0 | 5 votes |
public static String getHtmlEncode(@NonNull byte[] bytes) { try { Document doc = Jsoup.parse(new String(bytes, StandardCharsets.UTF_8)); Elements metaTags = doc.getElementsByTag("meta"); String charsetStr; for (Element metaTag : metaTags) { charsetStr = metaTag.attr("charset"); if (!isEmpty(charsetStr)) { return charsetStr; } String content = metaTag.attr("content"); String http_equiv = metaTag.attr("http-equiv"); if (http_equiv.toLowerCase().equals("content-type")) { if (content.toLowerCase().contains("charset")) { charsetStr = content.substring(content.toLowerCase().indexOf("charset") + "charset=".length()); } else { charsetStr = content.substring(content.toLowerCase().indexOf(";") + 1); } if (!isEmpty(charsetStr)) { return charsetStr; } } } } catch (Exception e) { e.printStackTrace(); } return getJavaEncode(bytes); }
Example #30
Source File: AppsGamesCatalogApi.java From 4pdaClient-plus with Apache License 2.0 | 5 votes |
public static ArrayList<Topic> loadCategoryThemes(IHttpClient client, String catalogId) throws IOException { String pageBody = client.performGet(GAMES_CATALOG_URL).getResponseBody(); ArrayList<Topic> res = new ArrayList<>(); Pattern pattern = Pattern.compile("<a name=\"entry" + catalogId + "\">([\\s\\S]*?)</div>(?:<!--Begin Msg Number|<!-- TABLE FOOTER)", Pattern.CASE_INSENSITIVE); Matcher m = pattern.matcher(pageBody); if (!m.find()) return res; Document doc = Jsoup.parse(m.group(1)); Elements subCategoryElements = doc.select("ol[type=1]>li"); for (Element topicElement : subCategoryElements) { Elements elements = topicElement.select("a"); if (elements.size() == 0) continue; Element element = elements.get(0); Uri uri = Uri.parse(element.attr("href")); Topic topic = new Topic(uri.getQueryParameter("showtopic"), element.text()); m = Pattern.compile("</a>(?:\\s*</b>\\s*-\\s*)(.*)?(?:<br\\s*/>|$)", Pattern.CASE_INSENSITIVE).matcher(topicElement.html()); if (m.find()) topic.setDescription(m.group(1)); res.add(topic); } return res; }