Parser parser = new Parser(url); NodeList movies = parser.extractAllNodesThatMatch( new AndFilter(new TagNameFilter("div"), new HasAttributeFilter("class", "movie")));
/** * Convenience method to extract all nodes of a given class type. * Equivalent to * <code>extractAllNodesThatMatch (new NodeClassFilter (nodeType))</code>. * @param nodeType The class of the nodes to collect. * @throws ParserException If a parse error occurs. * @return A list of nodes which have the class specified. * @deprecated Use extractAllNodesThatMatch (new NodeClassFilter (cls)). * @see #extractAllNodesThatAre */ public Node [] extractAllNodesThatAre (Class nodeType) throws ParserException { NodeList ret; ret = extractAllNodesThatMatch (new NodeClassFilter (nodeType)); return (ret.toNodeArray ()); }
Parser parser = Parser.createParser(comment.getText(), "UTF-8"); NodeList htmlAnchorNodes = null; try { htmlAnchorNodes = parser .extractAllNodesThatMatch(new TagNameFilter("a")); } catch (ParserException e) { e.printStackTrace(); } int size = htmlAnchorNodes.size();
public static List<String> getLinks(String url) throws ParserException { Parser htmlParser = new Parser(url); List<String> links = new LinkedList<String>(); NodeList tagNodeList = htmlParser.extractAllNodesThatMatch(new NodeClassFilter(LinkTag.class)); for (int m = 0; m < tagNodeList.size(); m++) { LinkTag loopLinks = (LinkTag) tagNodeList.elementAt(m); String linkName = loopLinks.getLink(); links.add(linkName); } return links; }
int size; { Parser parser = Parser.createParser(comment.getText(), "UTF-8"); NodeList htmlAnchorNodes = null; try { htmlAnchorNodes = parser .extractAllNodesThatMatch(new TagNameFilter("a")); } catch (ParserException e) { e.printStackTrace(); } size = htmlAnchorNodes.size(); }
try list = mParser.extractAllNodesThatMatch (filter); list = mParser.extractAllNodesThatMatch (filter);
try list = mParser.extractAllNodesThatMatch (filter); list = mParser.extractAllNodesThatMatch (filter);
NodeList list = parser.extractAllNodesThatMatch(new TagNameFilter("P"));
NodeList list = parser.extractAllNodesThatMatch(new TagNameFilter("P"));
/** * Extracts the title from the given HTML. * * @return never null, just an empty string if not parsable. */ public static String extractTitle(String html) throws ParserException { String title = ""; Parser parser = new Parser(html); NodeList matches = parser.extractAllNodesThatMatch(TITLE_FILTER); SimpleNodeIterator it = matches.elements(); while (it.hasMoreNodes()) { TitleTag node = (TitleTag) it.nextNode(); title = node.getTitle().trim(); } return title; }
NodeList matches = parser.extractAllNodesThatMatch(LINK_FILTER); SimpleNodeIterator it = matches.elements(); while (it.hasMoreNodes()) {
list = parser.extractAllNodesThatMatch (filter); for (int i = 0; i < list.size (); i++) System.out.println (list.elementAt (i).toHtml ());
Node[] tables = parser.extractAllNodesThatMatch( new TagNameFilter( "table" ) ).toNodeArray();
list = parser.extractAllNodesThatMatch(filter);
list = parser.extractAllNodesThatMatch(filter); } catch (ParserException e) { reporter.incrCounter(LinkCounter.PARSER_FAILED, 1);
NodeList links = new NodeList (); parser = createParserParsingAnInputString(output); links = parser.extractAllNodesThatMatch(filter);
NodeList links = new NodeList (); parser = createParserParsingAnInputString(output); links = parser.extractAllNodesThatMatch(filter);
NodeList links = new NodeList (); parser = createParserParsingAnInputString(output); links = parser.extractAllNodesThatMatch(filterLink);
NodeList links = new NodeList (); parser = createParserParsingAnInputString(output); links = parser.extractAllNodesThatMatch(filterLink);