多行就是在前边加"(?s)"
非贪婪模式就是在*、?、+ 后边再加?
例子:
URL url = new URL("http://money.finance.sina.com.cn/corp/go.php/vMS_MarketHistory/stockid/600000.phtml");
URLConnection conn = url.openConnection();
InputStream is = conn.getInputStream();
ByteArrayOutputStream out = new ByteArrayOutputStream();
byte[] arr = new byte[1024];
int len = -1;
while((len = is.read(arr)) > 0) {
out.write(arr);
}
String content = out.toString("GBK");
System.out.println(content);
String regstr = "(?s)<a target='_blank'\\s+href='http://vip.stock.finance.sina.com.cn/quotes_service/view/vMS_tradehistory.php\\?symbol=\\w{2}\\d{6}&date=\\d{4}-\\d{2}-\\d{2}'>"
+ "\\s+(\\d{4}-\\d{2}-\\d{2})\\s+.*?</td>\\s+"
+ "<td[^\\d]*([^<]*).*?</td>\\s+"
+ "<td[^\\d]*([^<]*).*?</td>\\s+"
+ "<td[^\\d]*([^<]*).*?</td>\\s+"
+ "<td[^\\d]*([^<]*).*?</td>\\s+"
+ "<td[^\\d]*([^<]*).*?</td>\\s+"
+ "<td[^\\d]*([^<]*).*?</td>\\s+";
Pattern p = Pattern.compile(regstr);
Matcher m = p.matcher(content);
while(m.find()){
System.out.println(m.group());
System.out.println(m.group(1));
System.out.println(m.group(2));
System.out.println(m.group(3));
System.out.println(m.group(4));
System.out.println(m.group(5));
System.out.println(m.group(6));
System.out.println(m.group(7));
}
//System.out.println(content);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}