List of usage examples for org.jsoup.nodes Node childNodes
public List<Node> childNodes()
From source file:Main.java
private static void removeComments(Node node) { for (int i = 0; i < node.childNodes().size();) { Node child = node.childNode(i); if (child.nodeName().equals("#comment")) child.remove();//from w w w .j av a 2 s .c o m else { removeComments(child); i++; } } }
From source file:Main.java
public static String GetNodeTextWithNewLines(Node node) { String text = ""; if (node != null) { for (Node childNode : node.childNodes()) { if (childNode.nodeName().toLowerCase().equals("br")) { text += "\n"; } else { if (childNode instanceof TextNode) { text += childNode;//w ww .ja v a 2 s. co m } else { text += GetNodeTextWithNewLines(childNode); } } } } return text; }
From source file:damo.three.ie.util.HtmlUtilities.java
private static void removeComments(Node node) { for (int i = 0; i < node.childNodes().size();) { Node child = node.childNode(i); if (child.nodeName().equals("#comment")) { child.remove();//from ww w.j a va 2 s . c o m } else { removeComments(child); i++; } } }
From source file:com.bibisco.export.HTMLParser.java
private static void parseChildNodes(Node pNode, TextFormatting pTextFormatting, IExporter pExporter) { List<Node> lListNode = pNode.childNodes(); for (Node lNode : lListNode) { parseNode(lNode, pTextFormatting, pExporter); }//from ww w .j a va 2 s . c o m }
From source file:com.mycollab.core.utils.StringUtils.java
private static void replaceHtml(Node element) { List<Node> elements = element.childNodes(); Pattern compile = Pattern.compile("(?:https?|ftps?)://[\\w/%.-][/\\??\\w=?\\w?/%.-]?[/\\?&\\w=?\\w?/%.-]*"); for (int i = elements.size() - 1; i >= 0; i--) { Node node = elements.get(i); if (node instanceof TextNode) { String value = ((TextNode) node).text(); Matcher matcher = compile.matcher(value); if (matcher.find()) { value = value.replaceAll( "(?:https?|ftps?)://[\\w/%.-][/\\??\\w=?\\w?/%.-]?[/\\?&\\w=?\\w?/%.-]*", "<a href=\"$0\" target=\"_blank\">$0</a>"); Document newDoc = Jsoup.parse(value); List<Node> childs = newDoc.body().childNodes(); for (int j = 0; j < childs.size(); j++) { Node childNode = childs.get(j).clone(); node.before(childNode); }/* www.ja va 2s . com*/ node.remove(); } } } }
From source file:com.zacwolf.commons.email.Email.java
public static void removeComments(org.jsoup.nodes.Node node) { for (int i = 0; i < node.childNodes().size(); i++) { org.jsoup.nodes.Node child = node.childNode(i); if (child.nodeName().equals("#comment")) child.remove();/*w w w. ja va 2 s . c o m*/ else removeComments(child); } }
From source file:de.luhmer.owncloudnewsreader.reader.GoogleReaderApi.GoogleReaderMethods.java
@SuppressWarnings("unused") public static ArrayList<FolderSubscribtionItem> getSubList(String _USERNAME, String _PASSWORD) throws UnsupportedEncodingException, IOException { ArrayList<FolderSubscribtionItem> _SUBTITLE_ARRAYLIST = new ArrayList<FolderSubscribtionItem>(); Document doc = Jsoup.connect(GoogleReaderConstants._SUBSCRIPTION_LIST_URL) .header("Authorization", GoogleReaderConstants._AUTHPARAMS + AuthenticationManager.getGoogleAuthKey(_USERNAME, _PASSWORD)) .userAgent(GoogleReaderConstants.APP_NAME).timeout(5000).get(); Elements objects = doc.select("object"); Element element = objects.get(0); Node childTemp = element.childNodes().get(0); List<Node> childs = childTemp.childNodes(); for (Node node : childs) { Elements links = ((Element) node).select("string"); String idFeed = null;/*from w w w.j a va 2 s. co m*/ String feedName; String parentSubscriptionName; for (Element link : links) { String tagAttrib = link.attr("name"); String tagText = link.text(); if (tagAttrib.equals("id") && idFeed == null) idFeed = tagText; else if (tagAttrib.equals("title")) feedName = tagText; else if (tagAttrib.equals("label")) parentSubscriptionName = tagText; } //String idFeed = node.attr("id"); //String name = node.attr("title"); //_SUBTITLE_ARRAYLIST.add(new FolderSubscribtionItem(feedName, -1, idFeed, parentSubscriptionName));//TODO implements this again... ? Update FolderSubscribtionItem } //String[] _SUBTITLE_ARRAY = new String[_SUBTITLE_ARRAYLIST.size()]; //_SUBTITLE_ARRAYLIST.toArray(_SUBTITLE_ARRAY); return _SUBTITLE_ARRAYLIST; }
From source file:org.coronastreet.gpxconverter.GarminForm.java
private static String findFlowKey(Node node) { String key = null;/*from w ww . ja v a 2 s . co m*/ for (int i = 0; i < node.childNodes().size();) { Node child = node.childNode(i); if (child.nodeName().equals("#comment")) { //System.out.println(child.toString()); String flowKeyPattern = "\\<\\!-- flowExecutionKey\\: \\[(e1s1)\\] --\\>"; key = child.toString().replaceAll(flowKeyPattern, "$1").trim(); break; } else { findFlowKey(child); i++; } } return key; }
From source file:com.sfs.DataFilter.java
/** * Removes the comments./*from w w w.j a v a 2s .c o m*/ * * @param node the node */ private static void removeComments(Node node) { for (int i = 0; i < node.childNodes().size();) { Node child = node.childNode(i); if (child.nodeName().equals("#comment")) child.remove(); else { removeComments(child); i++; } } }
From source file:com.screenslicer.core.scrape.Dissect.java
public static String nodeHash(Node node, List<Node> nodes, boolean lenientUrl, boolean lenientTitle) { StringBuilder position = new StringBuilder(); Node cur = node; while (cur != null) { position.append("<<0>>"); position.append(cur.hashCode()); position.append("<<1>>"); position.append(cur.nodeName()); position.append("<<2>>"); position.append(cur.childNodes().size()); position.append("<<3>>"); position.append(cur.siblingIndex()); position.append("<<4>>"); cur = cur.parent();//w ww .ja va 2 s.c o m } for (Node child : node.childNodes()) { position.append("<<c0>>"); position.append(child.hashCode()); position.append("<<c1>>"); position.append(child.nodeName()); position.append("<<c2>>"); position.append(child.childNodes().size()); position.append("<<c3>>"); position.append(child.siblingIndex()); position.append("<<c4>>"); } if (nodes != null) { for (Node n : nodes) { position.append("<<s0>>"); position.append(n.hashCode()); position.append("<<s1>>"); position.append(n.nodeName()); position.append("<<s2>>"); position.append(n.childNodes().size()); position.append("<<s3>>"); position.append(n.siblingIndex()); position.append("<<s4>>"); } } position.append("<<>>"); position.append(Util.outerHtml(node).hashCode()); return "dissectedResults-<<" + lenientUrl + ">>-<<" + lenientTitle + ">>-" + position.toString(); }