htmlpaser打造個性化的爬蟲程序 第一天

htmlpaser打造個性化的爬蟲程序 第一天

/**
	 * A method to get all the Links that follow the given pattern in the page . 
	 * @param url
	 * @param pattern
	 * @return Links list
	 * @author hym
	 * 
	 */
	public List extractUrls(String url,String pattern)
	{
		List list = new ArrayList();
		System.out.println("extractURL method here!");
		try{
		Parser parser = new Parser();
		parser.setURL(url);
		NodeFilter filter = new LinkStringFilter(pattern,true);
		NodeList nlist=parser.extractAllNodesThatMatch(filter);
		for(int i = 0 ; i <nlist.size(); i++)
		{
			Node n = nlist.elementAt(i);
		      if (n instanceof LinkTag) {
		    	  LinkTag  link = (LinkTag)n;
		    	  //System.out.println(link.getLink());  
		    	  list.add(link.getLink());
		       }	
		}
		}catch(ParserException e)
		{
			e.printStackTrace();
		}
		return list;
	}