HttpClient的HttpGet请求乱码问题解决

最新推荐文章于 2022-10-26 21:16:11 发布

原创最新推荐文章于 2022-10-26 21:16:11 发布 · 2.5w 阅读

5 ·

本内容遵循CC 4.0 BY-SA版权协议

Java技术专栏收录该内容

31 篇文章

订阅专栏

本文详细介绍了如何使用Java代码自动解析网页的编码方式，并将其转换为相应的字符集，确保了跨平台的正确显示。

自动解析页面编码，并转换为相应编码的字符


public static String httpGet(String url) throws ClientProtocolException, IOException, URISyntaxException {
            HttpClient httpclient = new DefaultHttpClient();
            String result = "";
             try {
                   // 连接超时
                  httpclient.getParams().setParameter(
                              CoreConnectionPNames. CONNECTION_TIMEOUT, 5000);
                   // 读取超时
                  httpclient.getParams().setParameter(
                              CoreConnectionPNames. SO_TIMEOUT, 5000);

                   HttpGet hg = new HttpGet (url);
                   //模拟浏览器
                  hg.addHeader( "User-Agent", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.64 Safari/537.31"); 
                  String charset = "UTF-8"; 
                  hg.setURI( new java.net.URI(url)); 
                        HttpResponse response = httpclient.execute(hg); 
                        HttpEntity entity = response.getEntity(); 
                        if (entity != null) { 
                            charset = getContentCharSet(entity);
                               // 使用EntityUtils的toString方法，传递编码，默认编码是ISO-8859-1 
                            result = EntityUtils.toString(entity, charset); 
                      } 
      
            } finally {
                  httpclient.getConnectionManager().shutdown();
            }
             return result;
      }

     /**
     * 默认编码utf -8
     * Obtains character set of the entity, if known.
     * 
     * @param entity must not be null
     * @return the character set, or null if not found
     * @throws ParseException if header elements cannot be parsed
     * @throws IllegalArgumentException if entity is null
     */  
    public static String getContentCharSet(final HttpEntity entity) 
        throws ParseException { 
 
        if (entity == null) { 
            throw new IllegalArgumentException("HTTP entity may not be null"); 
        } 
        String charset = null; 
        if (entity.getContentType() != null) {  
            HeaderElement values[] = entity.getContentType().getElements(); 
            if (values.length > 0) { 
                NameValuePair param = values[0].getParameterByName("charset" ); 
                if (param != null) { 
                    charset = param.getValue(); 
                } 
            } 
        } 
       
        if(StringUtils.isEmpty(charset)){
            charset = "UTF-8";
        }
        return charset; 
    }