正则两次,group(1)获取时,group(2)获取分,中间以:相连
华哥帮忙写了一个LIST,获取GROUP的值,List再依次读出
package com.zzk.cn; import java.awt.List; import java.io.BufferedReader; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.net.MalformedURLException; import java.net.URL; import java.net.URLConnection; import java.util.ArrayList; import java.util.regex.Matcher; import java.util.regex.Pattern; public class TestSun { public static void main(String[] args) { URL url = null; URLConnection conn = null; InputStream in = null; InputStreamReader isr = null; BufferedReader br = null; try { url = new URL("http://www.weather.com.cn/weather/101010100.shtml"); conn = url.openConnection(); in = conn.getInputStream(); isr = new InputStreamReader(in,"utf8"); br = new BufferedReader(isr); String line = ""; String info=""; while (null != (line = br.readLine())) { //System.out.println(line); info+=line; } //System.out.println(info); Pattern p=Pattern.compile("div\\sclass=.weatherTopright.*?</div>");//正则获取网页大致信息 Matcher m=p.matcher(info); String s1=""; while(m.find()) { s1=m.group(); //System.out.println(s1); } String s2=""; Pattern p1=Pattern.compile("bold;.>(\\d+):(\\d+)</strong>");//正则获取网页日出日落信息 //Pattern p1=Pattern.compile("<(/?\\s?br\\b)>"); Matcher m1=p1.matcher(s1); //System.out.println(s1); ArrayList<String> a = new ArrayList<String>(); while(m1.find()) { //m1.group(1); String s=m1.group(1); String s0=m1.group(2); String result = s+":"+s0; a.add(result); } System.out.println(a.get(0)); System.out.println(a.get(1)); // System.out.println(a.get(2)); // System.out.println(a.get(3)); } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { try { if (null != br) { br.close(); } } catch (IOException e) { e.printStackTrace(); } br = null; try { if (null != isr) { isr.close(); } } catch (IOException e) { e.printStackTrace(); } isr = null; try { if (null != in) { in.close(); } } catch (IOException e) { e.printStackTrace(); } in = null; } } }
输出:
07:31
16:51