JSoup 用于Html分析

       1.Jsoup概念

    jsoup 是一款Java 的HTML解析器，可直接解析某个URL地址、HTML文本内容。它提供了一套非常省力的API，可通过DOM，CSS以及类似于jQuery的操作方法来取出和操作数据。

2.应用场景

  适用于数据抓取解析工作，尤其是类似于Jquery选择器可以快速定位要获取的数据片段。

3.例子

   如下，实现一个解析一周天气的数据，数据由网页抓取得到，需要提取相关的气温、风速、风向等信息。

 

Maven地址：

 <dependency>
      <groupId>org.jsoup</groupId>
      <artifactId>jsoup</artifactId>
      <version>1.9.2</version>
</dependency>

    	       String url = "http://www.weather.com.cn/weather/101210101.shtml";
		Document doc = Jsoup.connect(url)
				.data("query", "Java")
				.userAgent("Mozilla")
				.cookie("auth", "token").
				timeout(3000)
				.get();
		
		Elements elems = doc.select("#7d>ul>li");
		
		List<Map<String, Object>> dataList = new ArrayList<Map<String, Object>>();
		
		for( Element el : elems){
			/**
			 *  "procewind": "东风",
                "wind": "3-4级",
                "when": "白天",
                "temp": "8℃/12°C",
                "weather": "小雨",
                "procedure": ""
			 */

			
			String date = el.select("h1").html();
			String procewind = el.select(".win span").attr("title");
			String wind = el.select(".win>i").html();
			String temp = el.select(".tem span").html();
			temp += "/" + el.select(".tem>i").html();
			
			String weather = el.select(".wea").html();
			String procedure = "";
			
			Map<String, Object> map = new HashMap<String, Object>();
			map.put("date", date);
			
			List<Object> parts = new ArrayList<Object>();
			{
				Map<String, Object> mapDay = new HashMap<String, Object>();
				mapDay.put("procewind", procewind);
				mapDay.put("wind", wind);
				mapDay.put("when", "白天");
				mapDay.put("temp", temp);
				mapDay.put("weather", weather);
				mapDay.put("procedure", procedure);
				
				Map<String, Object> mapNight = new HashMap<String, Object>();
				mapNight.put("procewind", procewind);
				mapNight.put("wind", wind);
				mapNight.put("when", "夜晚");
				mapNight.put("temp", temp);
				mapNight.put("weather", weather);
				mapNight.put("procedure", procedure);
				
				parts.add(mapDay);
				parts.add(mapNight);
			}
			map.put("parts", parts);

			dataList.add(map);
		}

or 正则表达式

String reg = "<div id=\"7d\".*?<ul class=\"t clearfix\">.*?";
// String each ="<li.*?sky.*?>.*?<h1>(?<pdate>.*?)</h1>.*?wea\">(?<pweather>.*?)</p>.*?tem\">\\s+(?<ptem>.*?(?<ptem1>\\d+).*?(?<ptem2>\\d+)+.*?)</p>.*?win\">.*?title=\"(?<pwindspeed>.*?)\".*?<i>(?<pwinddir>.*?)</i>.*?</li>.*?";
String each = "<li.*?sky.*?>.*?<h1>(.*?)</h1>.*?wea\">(.*?)</p>.*?tem\">\\s+(.*?)</p>.*?win\">.*?title=\"(.*?)\".*?<i>(.*?)</i>.*?</li>.*?";

4.参考链接

http://www.open-open.com/jsoup/