java 正则表达式学习 (二)

2014-11-24 10:26:31 · 作者: · 浏览: 1
cher m2 = p2.matcher(inputStr);

while (m2.find()) {

if (!"".equals(m2.group())) {

String date = m2.group();

date = date.replaceAll("年", "-");

date = date.replaceAll("月", "-");

date = date.replaceAll("日", " ");

date = date.replaceAll("/", "-");

strDate = date;

}

}

}

return strDate;

}

8.网址提取

publicstaticvoid extractsURL2(String url2) throws IOException {

HttpURLConnection url=null;

String htmladdr="http://news.163.com/special/0001220O/news_json.js";

try {

URL url1 = new URL(htmladdr);

url = (HttpURLConnection)url1.openConnection ();

url.connect();

} catch (Exception e) {

e.printStackTrace();

return ;

}

String temp = null;

String temp2 = "";

if(url!=null){

InputStream stream;

stream = url.getInputStream();

BufferedReader reader = new BufferedReader(new InputStreamReader(stream));

try {

while ((temp = reader.readLine()) != null){

temp2 += temp;

}

} catch (RuntimeException e) {

//e.printStackTrace();

}

reader.close();

}

String ruleUrl = "http://[a-z]+.163.com/yy/mmdd/[\\d]+/[\\w]+.html";

String urlFilter = urlFilterStrategy(ruleUrl);

Pattern p = Pattern

.compile(urlFilter);

Matcher m = p.matcher(temp2);

while (m.find()) {

if (!"".equals(m.group())) {

System.out.println(m.group());

}

}

}

publicstatic String urlFilterStrategy(String urlFilter) {

Calendar calendar = Calendar.getInstance();

String year = Integer.toString(calendar.get(calendar.YEAR))

.substring(2);

String year2 = Integer.toString(calendar.get(calendar.YEAR));

String month = "0" + Integer.toString(calendar.get(calendar.MONTH) + 1);

month = month.substring(month.length() - 2);

String day = "0"

+ Integer.toString(calendar.get(calendar.DAY_OF_MONTH));

day = day.substring(day.length() - 2);

urlFilter = urlFilter.replaceAll("yyyy-mm-dd", year2+"-"+month+"-"+day);

urlFilter = urlFilter.replaceAll("yyyy", year2);

urlFilter = urlFilter.replaceAll("yy", year);

urlFilter = urlFilter.replaceAll("mm", month);

urlFilter = urlFilter.replaceAll("dd", day);

return urlFilter;

}