购导航xml解析学习总结

团购导航网站如：http://www.tuanp.com,，http://www.tuan800.com，首先需要对抓取的团购网站进行分析，因为很多团购网站没有对外的API即xml格式文件，然后对xml格式分析，且在后台录入xml格式标签，最后使用定时器每隔一段时间抓取。

1.团购网站信息Test.xml

<?xml version="1.0" encoding="utf-8"?>
<result>
	<error>0</error>
	<data>
		<site>
			<site_name>团购网站</site_name>
			<site_title>团购标题</site_title>
			<site_url>http://xxx.xxx.com</site_url>
		</site>
		<teams>
			<team>
				<id>21</id>
				<link>http://xxx.xxx.com/team.php?id=21</link>
				<large_image_url>http://xxx.xxx.com/upfile/team/2010/1013/12869663322493.jpg</large_image_url>
				<small_image_url>http://xxx.xxx.com/upfile/team/2010/1013/12869663322493_index.jpg</small_image_url>
				<title> Title1……</title>
				<product> Product1…… </product>
				<team_price>37.50</team_price>
				<market_price>60.90</market_price>
				<rebate>6.16</rebate>
				<start_date>2010-10-14T00:00:00+08:00</start_date>
				<end_date>2010-10-20T00:00:00+08:00</end_date>
				<state>success</state>
				<tipped>true</tipped>
				<tipped_date>2010-10-15T10:55:14+08:00</tipped_date>
				<tipping_point>10</tipping_point>
				<current_point>192</current_point>
				<conditions>
					<limited_quantity>false</limited_quantity>
					<maximum_purchase>0</maximum_purchase>
					<expiration_date>2011-01-14T00:00:00+08:00</expiration_date>
				</conditions>
				<city></city>
				<group></group>
			</team>
			<team>
				<id>23</id>
				<link>http://xxx.xxx.com/team.php?id=23</link>
				<large_image_url>http://xxx.xxx.com/upfile/team/2010/1015/12870801418707.jpg</large_image_url>
				<small_image_url>http://xxx.xxx.com/upfile/team/2010/1015/12870801418707_index.jpg</small_image_url>
				<title> Title2…… </title>
				<product> Product2……</product>
				<team_price>58.00</team_price>
				<market_price>298.00</market_price>
				<rebate>1.95</rebate>
				<start_date>2010-10-16T00:00:00+08:00</start_date>
				<end_date>2010-10-19T00:00:00+08:00</end_date>
				<state>success</state>
				<tipped>true</tipped>
				<tipped_date>2010-10-16T10:45:10+08:00</tipped_date>
				<tipping_point>10</tipping_point>
				<current_point>138</current_point>
				<conditions>
					<limited_quantity>false</limited_quantity>
					<maximum_purchase>0</maximum_purchase>
					<expiration_date>2011-01-16T00:00:00+08:00</expiration_date>
				</conditions>
				<city></city>
				<group></group>
			</team>
		</teams>
	</data>
</result>

2.后台java解析程序：  //

按照路径定位解析技术：dom4j解析

public static void main(String[] args) {
		try {
			SAXReader reader = new SAXReader();
			Document doc = reader.read(new File("Test.xml"));
			Element root = doc.getRootElement();

			List list = root.selectNodes("//data/teams/team");

			Element element;
			for (int i = 0; i < list.size(); i++) {
				element = (Element) list.get(i);

				String id = getNodeText(element, "id");
				System.out.println("id:"+id);
				
				String title = getNodeText(element, "title");
				System.out.println("title:"+title);

				String image = getNodeText(element, "large_image_url");
				System.out.println("image:"+image);

				String dealUrl = getNodeText(element, "link");
				System.out.println("dealUrl:"+dealUrl);
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	
	public static String getNodeText(Element element, String nodename) throws Exception{
		Node node = element.selectSingleNode(nodename);
		if(node == null) {
			throw new RuntimeException("标签错误");
		}
		return node.getText();
	}