Android httpclient receiving xml garbled problem solving

2019 Unicorn Enterprises heavily recruiting engineers Python standard >>>

 

Because the character encoding issues, causing me to toss two hours. Here is the code, we look to understand.

String url = "http://www.google.com/ig/api?weather=,,,31174165,121433841";   
		DefaultHttpClient client = new DefaultHttpClient();
		HttpUriRequest req = new HttpGet(url);
		HttpResponse resp = client.execute(req);
		HttpEntity ent = resp.getEntity();
		int status = resp.getStatusLine().getStatusCode();
		if(L.Debug) {
			L.d("" + status);
		}
		// 若状态码为 200 ，则表示OK
		if (status == HttpStatus.SC_OK) {
			//String result = EntityUtils.toString(ent);
			
			if(L.Debug) {
				//L.d(result);
			}
			InputStream stream = ent.getContent();
			BufferedReader br =  new BufferedReader(new InputStreamReader(stream, "utf-8"));
			DocumentBuilder b = DocumentBuilderFactory.newInstance()
								.newDocumentBuilder();
			String xmlString = "";
			for(String temp = br.readLine(); temp != null;xmlString += temp ,temp = br.readLine());
			// 去除字符串中的换行符，制表符，回车符。
			xmlString = xmlString.replaceAll("/n|/t|/r", "");
			InputStream stream2 = new ByteArrayInputStream(xmlString.getBytes());
			Document d = b.parse(new InputSource(stream2));
			NodeList n = d.getElementsByTagName("forecast_conditions");
			String tips = "";
			tips += n.item(0).getChildNodes().item(0).getAttributes()
						.item(0).getNodeValue();
			if(L.Debug) {
				L.d("" + tips );
				L.d("" + n.item(0).getChildNodes().getLength());
				//L.Toast(tips, this);
			}
			br.close();
			stream.close();
			stream2.close();
		}

 

The key is this line of code

BufferedReader br =  new BufferedReader(new InputStreamReader(stream, "utf-8"));

 

The received stream into the buffer, the encoding process into a utf-8 (if or distortion, or that Instead gb2312 GBK)

 

Method Two

 

String url = "http://www.google.com/ig/api?weather=,,,31174165,121433841";   
		DefaultHttpClient client = new DefaultHttpClient();
		HttpUriRequest req = new HttpGet(url);
		HttpResponse resp = client.execute(req);
		HttpEntity ent = resp.getEntity();
		int status = resp.getStatusLine().getStatusCode();
		// If the status is equal to 200 ，that is OK
		if (status == HttpStatus.SC_OK) {
			String result = EntityUtils.toString(ent);
			if(L.Debug) {
				L.testCharset(result);
			}
			// Encode utf-8 to iso-8859-1
			result = new String(result.getBytes("ISO-8859-1"), "UTF-8");
			DocumentBuilder b = DocumentBuilderFactory.newInstance()
								.newDocumentBuilder();
			String xmlString = result;
			// Remove the newline,tabs and return characters from string
			xmlString = xmlString.replaceAll("/n|/t|/r", "");
			InputStream stream = new ByteArrayInputStream(xmlString.getBytes());
			Document d = b.parse(new InputSource(stream));
			getWeatherBean(d);
			stream.close();
		}

 

 

// 以下是测试字符编码的
public static void testCharset(String datastr){
                try {
                        String temp = new String(datastr.getBytes(), "GBK");
                        Log.v("TestCharset","****** getBytes() -> GBK ******/n"+temp);
                        temp = new String(datastr.getBytes("GBK"), "UTF-8");
                        Log.v("TestCharset","****** GBK -> UTF-8 *******/n"+temp);
                        temp = new String(datastr.getBytes("GBK"), "ISO-8859-1");
                        Log.v("TestCharset","****** GBK -> ISO-8859-1 *******/n"+temp);
                        temp = new String(datastr.getBytes("ISO-8859-1"), "UTF-8");
                        Log.v("TestCharset","****** ISO-8859-1 -> UTF-8 *******/n"+temp);
                        temp = new String(datastr.getBytes("ISO-8859-1"), "GBK");
                        Log.v("TestCharset","****** ISO-8859-1 -> GBK *******/n"+temp);
                        temp = new String(datastr.getBytes("UTF-8"), "GBK");
                        Log.v("TestCharset","****** UTF-8 -> GBK *******/n"+temp);
                        temp = new String(datastr.getBytes("UTF-8"), "ISO-8859-1");
                        Log.v("TestCharset","****** UTF-8 -> ISO-8859-1 *******/n"+temp);
                } catch (UnsupportedEncodingException e) {
                        e.printStackTrace();
                }
        }

 

 

TestCharset first with this method, test coding which no distortion occurs, and then modify result = new String (result.getBytes ( "ISO-8859-1"), "UTF-8"); inside the corresponding coding.

Reproduced in: https: //my.oschina.net/lendylongli/blog/226779