Question

java如何利用正则表达式去掉文本中的HTML标签

Answer 1

如下：
public static String do_post(String url, List<NameValuePair> name_value_pair) throws IOException {
        String body = "{}";
        DefaultHttpClient httpclient = new DefaultHttpClient();
        try {
            HttpPost httpost = new HttpPost(url);
            httpost.setEntity(new UrlEncodedFormEntity(name_value_pair, StandardCharsets.UTF_8));
            HttpResponse response = httpclient.execute(httpost);
            HttpEntity entity = response.getEntity();
            body = EntityUtils.toString(entity);
        } finally {
            httpclient.getConnectionManager().shutdown();
        }
        return body;
    }
    public static String do_get(String url) throws ClientProtocolException, IOException {
        String body = "{}";
        DefaultHttpClient httpclient = new DefaultHttpClient();
        try {
            HttpGet httpget = new HttpGet(url);
            HttpResponse response = httpclient.execute(httpget);
            HttpEntity entity = response.getEntity();
            body = EntityUtils.toString(entity);
        } finally {
            httpclient.getConnectionManager().shutdown();
        }
        return body;
    }