Android进阶(十三)网络爬虫&json应用

刚开始接触网络爬虫，怎一个“菜”字了得！经过几次的折磨，对其原理以及其中用到的json技术有了大致的了解，故作一总结，供有同样迷惑的朋友参考学习。

自己爬取的网站内容为12306的余票查询模块。利用火狐浏览器为Web开发者置的Web控制台，可得到爬取网页的请求网址，如下图所示：

其中的请求网址即为我们需要爬取的网址。另外，可得知其请求协议采用的是Https协议，采用GET方式访问。爬取源代码如下所示：

        public static String queryDate = "2015-04-19";
	public static String from_station = "JNK";
	public static String to_station = "BJP";

	public static void main(String[] args) throws Exception {

		HostnameVerifier hv = new HostnameVerifier() {
			public boolean verify(String urlHostName, SSLSession session) {
				System.out.println("Warning: URL Host: " + urlHostName
						+ " vs. " + session.getPeerHost());
				return true;
			}
		};

        String url = "https://kyfw.12306.cn/otn/lcxxcx/query?purpose_codes=ADULT&queryDate="
				+ queryDate
				+ "&from_station="
				+ from_station
				+ "&to_station="
				+ to_station;

		ProtocolUrlValidator.trustAllHttpsCertificates();
		HttpsURLConnection.setDefaultHostnameVerifier(hv);

		String result = WebServiceUtil.invokeByHTTPGET(url, null);

		Gson gson = new Gson();
		Trains trains = gson.fromJson(result, Trains.class);

		List<Item> items = trains.getData().getItems();

		if (trains.getHttpstatus() != 200) {
			trains.getMessages();
		} else {
			if (items != null && items.size() != 0)
				for (Item item : items) {
					System.out.println(item);
				}
		}
	}
}

<span style="font-size:14px;">由于使用的协议为Https，故访问之前需要先进行证书的校验。其中蓝色代码块为我们需要访问的网址，涉及到的invokeByHTTPGET(url,null)代码如下所示：</span>

<span style="font-size:18px;">public class WebServiceUtil {

	/**
	 * 通过SOAP1.1协议调用Web服务
	 *
	 * @param wsdl		WSDL路径
	 * @param method	方法名
	 * @param namespace	命名空间
	 * @param headerParameters 头参数
	 * @param bodyParameters   体参数
	 * @param isBodyParametersNS 体参数是否有命名空间
	 * @return	String
	 * @throws Exception
	 */
	public static String invokeBySoap11(String wsdl, String method,
			String namespace, Map<String, String> headerParameters,
			Map<String, String> bodyParameters, boolean isBodyParametersNS)
			throws Exception {
		StringBuffer soapOfResult = null;
		// 去除 ?wsdl,获取方法列表
		int length = wsdl.length();
		wsdl = wsdl.substring(0, length - 5);
		URL url = new URL(wsdl);
		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
		conn.setRequestMethod("POST");
		conn.setDoInput(true);
		conn.setDoOutput(true);
		conn.setRequestProperty("Content-Type", "text/xml;charset=utf-8");
		OutputStream out = conn.getOutputStream();
		// 获取soap1.1版本消息
		StringBuilder sb = new StringBuilder();
		sb.append("<soap:Envelope xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"
                xmlns:xsd=\"http://www.w3.org/2001/XMLSchema\" xmlns:soap=\"http://schemas.xmlsoap.org/soap/envelope/\" ");
		sb.append("xmlns:ns0=\"" + namespace + "\"");
		sb.append(">");
		if (headerParameters != null) {
			sb.append("<soap:Header>");
			for (Entry<String, String> headerParameter : headerParameters
					.entrySet()) {
				sb.append("<ns0:");
				sb.append(headerParameter.getKey());
				sb.append(">");
				sb.append(headerParameter.getValue());
				sb.append("</ns0:");
				sb.append(headerParameter.getKey());
				sb.append(">");
			}
			sb.append("</soap:Header>");
		}
		sb.append("<soap:Body><ns0:");
		sb.append(method);
		sb.append(">");
		// 输入参数
		if (bodyParameters != null) {
			for (Entry<String, String> inputParameter : bodyParameters
					.entrySet()) {
				if (isBodyParametersNS) {
					sb.append("<ns0:");
					sb.append(inputParameter.getKey());
					sb.append(">");
					sb.append(inputParameter.getValue());
					sb.append("</ns0:");
					sb.append(inputParameter.getKey());
					sb.append(">");
				} else {
					sb.append("<");
					sb.append(inputParameter.getKey());
					sb.append(">");
					sb.append(inputParameter.getValue());
					sb.append("</");
					sb.append(inputParameter.getKey());
					sb.append(">");
				}
			}
		}
		sb.append("</ns0:");
		sb.append(method);
		sb.append("></soap:Body></soap:Envelope>");
		//System.out.println(sb.toString());
		out.write(sb.toString().getBytes());
		int code = conn.getResponseCode();
		if (code == 200) {
			InputStream is = conn.getInputStream();
			byte[] b = new byte[1024];
			int len = 0;
			soapOfResult = new StringBuffer();
			while ((len = is.read(b)) != -1) {
				String s = new String(b, 0, len, "UTF-8");
				soapOfResult.append(s);
			}
		}
		conn.disconnect();
		return soapOfResult == null ? null : soapOfResult.toString();
	}

	/**
	 * 通过SOAP1.2协议调用Web服务
	 *
	 * @param wsdl
	 * @param method
	 * @param namespace
	 * @param headerParameters
	 * @param bodyParameters
	 * @param isBodyParametersNS
	 * @return
	 * @throws Exception
	 */
	public static String invokeBySoap12(String wsdl, String method,
			String namespace, Map<String, String> headerParameters,
			Map<String, String> bodyParameters, boolean isBodyParametersNS)
			throws Exception {
		StringBuffer soapOfResult = null;
		// 去除 ?wsdl
		int length = wsdl.length();
		wsdl = wsdl.substring(0, length - 5);
		URL url = new URL(wsdl);
		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
		conn.setRequestMethod("POST");
		conn.setDoInput(true);
		conn.setDoOutput(true);
		conn.setRequestProperty("Content-Type", "text/xml;charset=utf-8");
		OutputStream out = conn.getOutputStream();
		// 获取soap1.1版本消息
		StringBuilder sb = new StringBuilder();
		sb.append("<soap12:Envelope xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"
                xmlns:xsd=\"http://www.w3.org/2001/XMLSchema\" soap12:Envelope xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" ");
		sb.append("xmlns:ns0=\"" + namespace + "\"");
		sb.append(">");
		if (headerParameters != null) {
			sb.append("<soap12:Header>");
			for (Entry<String, String> headerParameter : headerParameters
					.entrySet()) {
				sb.append("<ns0:");
				sb.append(headerParameter.getKey());
				sb.append(">");
				sb.append(headerParameter.getValue());
				sb.append("</ns0:");
				sb.append(headerParameter.getKey());
				sb.append(">");
			}
			sb.append("</soap12:Header>");
		}
		sb.append("<soap12:Body><ns0:");
		sb.append(method);
		sb.append(">");
		// 输入参数
		if (bodyParameters != null) {
			for (Entry<String, String> inputParameter : bodyParameters
					.entrySet()) {
				if (isBodyParametersNS) {
					sb.append("<ns0:");
					sb.append(inputParameter.getKey());
					sb.append(">");
					sb.append(inputParameter.getValue());
					sb.append("</ns0:");
					sb.append(inputParameter.getKey());
					sb.append(">");
				} else {
					sb.append("<");
					sb.append(inputParameter.getKey());
					sb.append(">");
					sb.append(inputParameter.getValue());
					sb.append("</");
					sb.append(inputParameter.getKey());
					sb.append(">");
				}
			}
		}
		sb.append("</ns0:");
		sb.append(method);
		sb.append("></soap12:Body></soap12:Envelope>");
		System.out.println(sb.toString());
		out.write(sb.toString().getBytes());
		int code = conn.getResponseCode();
		if (code == 200) {
			InputStream is = conn.getInputStream();
			byte[] b = new byte[1024];
			int len = 0;
			soapOfResult = new StringBuffer();
			while ((len = is.read(b)) != -1) {
				String s = new String(b, 0, len, "UTF-8");
				soapOfResult.append(s);
			}
		}
		conn.disconnect();
		return soapOfResult == null ? null : soapOfResult.toString();
	}

	/**
	 * 通过HTTP POST传参方式调用服务
	 *
	 * @param urlPath
	 * @param method
	 * @param namespace
	 * @param inputParameters
	 * @return
	 * @throws Exception
	 */
	public static String invokeByHTTPPOST(String urlPath, Map<String, String> inputParameters)
			throws Exception {
		StringBuffer resultStr = null;
		URL url = new URL(urlPath);
		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
		conn.setRequestMethod("POST");
		conn.setDoInput(true);
		conn.setDoOutput(true);
		conn.setRequestProperty("Content-Type",
				"application/x-www-form-urlencoded");
		StringBuilder sb = new StringBuilder();
		// 输入参数
		if (inputParameters != null) {
			for (Entry<String, String> inputParameter : inputParameters
					.entrySet()) {
				sb.append(inputParameter.getKey());
				sb.append("=");
				sb.append(inputParameter.getValue());
				sb.append("&");
			}
			sb.deleteCharAt(sb.length() - 1);
		}
		System.out.println(sb.toString());
		OutputStream out = conn.getOutputStream();
		out.write(sb.toString().getBytes());
		int code = conn.getResponseCode();
		if (code == 200) {
			InputStream is = conn.getInputStream();
			byte[] b = new byte[1024];
			int len = 0;
			resultStr = new StringBuffer();
			while ((len = is.read(b)) != -1) {
				String s = new String(b, 0, len, "UTF-8");
				resultStr.append(s);
			}
		}
		conn.disconnect();
		return resultStr == null ? null : resultStr.toString();
	}

	/**
	 * 通过HTTP GET传参方式调用服务
	 *
	 * @param urlPath   url路径
	 * @param method	方法名
	 * @param namespace 命名空间
	 * @param inputParameters 输入参数
	 * @return String
	 * @throws Exception
	 */
	public static String invokeByHTTPGET(String urlPath,  Map<String, String> inputParameters)
			throws Exception {
		StringBuilder sb = new StringBuilder();
		sb.append(urlPath);
		// GET参数
		if (inputParameters != null) {
			sb.append("?");
			//entrySet()方法	返回此映射中包含的映射关系的 set 视图集合
			//Map.Entry表示单个映射关系即一个key+value
			for (Entry<String, String> inputParameter : inputParameters
					.entrySet()) {
				sb.append(inputParameter.getKey());
				sb.append("=");
				sb.append(inputParameter.getValue());
				sb.append("&");
			}
			//作用:去除最后一个拼接的'&'字符
			sb.deleteCharAt(sb.length() - 1);
		}
		System.out.println(sb.toString());
		URL url = new URL(sb.toString());
		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
		conn.setRequestMethod("GET");
		conn.setDoOutput(true);
		int code = conn.getResponseCode();
		StringBuffer resultString = null;
		if (code == 200) {
			InputStream is = conn.getInputStream();
			byte[] b = new byte[4096];
			int len = 0;
			resultString = new StringBuffer();
			while ((len = is.read(b)) != -1) {
				String s = new String(b, 0, len, "UTF-8");
				//System.out.println(len+">>>>"+s);
				resultString.append(s);
			}
		}
		conn.disconnect();
		return resultString == null ? null : resultString.toString();
	}</span>

以上代码块涉及到的发送请求方式有通过SOAP1.1协议调用Web服务、通过SOAP1.2协议调用Web服务、

通过HTTP POST传参方式调用服务和通过HTTP GET传参方式调用服务。其具体的请求方式在源代码中以注释方式以详细给出，故此处不再赘述。

在爬取过程中，我们还需要用到json在线校验工具，网址为：点击打开链接。主要利用此工具完成的操作为：验证json格式的正确性，根据json串生成相应的POJO类。如下图所示：

json格式校验

生成POJO类

<span style="font-size:18px;">至此，网络爬虫的过程基本结束。此次实验的返回结果如下图所示：</span>

注：自己对GSon解析json还存在一定的误区。对于json串中的Key,其实是与相应类中的变量名一一对应的，否则，在解析式将会是null!例如，

以上的json串中存在key为data，则在创建POJO时，不可随意更变变量名，若将private List<Item> datas;改写为private List<Item> items;则会使变List<Item> items = trains.getData().getItems();返回null。若自己需要更改变量名的话，可以采用注解的方式解决，例如@SerializedName("datas")private List<Item> items;