使用HtmlParser 提取百度贴吧中的邮箱地址

下载地址

经测试，实际用时1秒左右

private static final Pattern p = Pattern.compile("\\w+([-+.]\\w+)*@\\w+([-.]\\w+)*\\.\\w+([-.]\\w+)*");
public static ArrayList<String> extractEmail(int id,int start,int end){
		ArrayList<String> list = new ArrayList<String>();
		try {
			for (int i = start; i <= end; i++) {

				Parser parser = new Parser("http://tieba.baidu.com/p/"+id+"?pn="+i);
			
				NodeFilter filter = new RegexFilter(
						"\\w+([-+.]\\w+)*@\\w+([-.]\\w+)*\\.\\w+([-.]\\w+)*");
				
				NodeList nodes = parser.extractAllNodesThatMatch(filter);
				
				if (nodes.size() > 0) {
					for (NodeIterator ni = nodes.elements(); ni.hasMoreNodes();) {
						Matcher m = p.matcher(ni.nextNode().toHtml());
						if (m.find()) {
							list.add(m.group());
						}
					}
				}
			}
			
		} catch (ParserException e) {
			
		}
		return list;
	}