通过post向指定URL地址访问爬取数据

 一：直接上代码，控制层

//这是下面要用的HOST，里面的数据是F12在页面看到的，例如：127.0.0.1:8088
private final static String HOST = PropertiesUtil.getDocking("url:端口号");
@RequestMapping("findPackageDetails")
    public void findPackageDetails() {

        // 根据固定地址获取cookie
String param ="USERNAME=用户名&PASSWORD=密码";
//其中USERNAME和PASSWORD是在网址上找到的定义名字（F12可以看到）
 String result = HttpRequestWdqy.getNewToken("URL（这里填写固定的URL）", param);
        String cookie = result.substring(0, 82);（result是返回的cookie，根据情况截取部分）
        cookie = cookie + "JSESSIONID=0000pMWMIp_OmSU2-on7_IbMOR7:1c2e6s2rt;";
           //cookie后面添加的是我访问地址固定添加的部分，看地址上面的要求

//方法一    //下面这个是访问本系统的另一个地址，和上面的是一个系统，所以用到cookie。
        String params = "FWBID=P20190109174053505";//需要传的数据
        String url = "这里填写固定的URL";
        // 获取签约团队列表,通过这种方法返回的是string类型。因为感觉不好处理，用了方法二
        String results = HttpRequestWdqy.httpPost(url, params, cookie);
        String infoList = JSONObject.parseObject(results).getString("rows");
           //rows是返回的results串里面的key值。


 //方法二   //下面这个是访问本系统的另一个地址，和上面的是一个系统，所以用到cookie。
        String Url = "这里填写固定的URL";
        CloseableHttpClient httpClient = HttpClients.createDefault();
        ArrayList<NameValue> arrayList = new ArrayList<>();
        arrayList.add(new NameValue("FWBID", "P20190109174053505"));//需要传的数
//通过下面这个方法返回的是JsonResult 格式的，里面的HOST在最上面定义
JsonResult httpPost4 = HttpRequestWd.httpPost(httpClient,HOST,Url,null,arrayList,cookie);
       //通过下面的方法处理返回的页面数据
        Document parse = Jsoup.parse(httpPost4.getMessage());
//因为需要爬取的数据在标签script中，所以使用下面的方法，获取所有的script标签
        Elements elementsByAttributeValue11 = parse.getElementsByTag("script");
        String str = "";
//下面设置一个循环，查找符合的数据
        for (Element ele : elementsByAttributeValue11) {
           //把数据转成text格式
            String text = ele.data();
            //通过里面的数据判断：/**服务项数组*/（这个是其中一个script标签中特有的）
            if (text.contains("/**服务项数组*/")) {
                //然后截取其中[]包裹的数据。完成
                str = text.substring(text.indexOf("["), text.indexOf("]") + 1);
            }
        }
    }

二：下面是上一个使用到的方法：

1.HttpRequestWdqy.getNewToken 获取cookie；

/**
	 * 获取cookie
	 *
	 * @author lgs
	 */
	public static String getNewToken(String url, String param) {
		String cookie = "";
		try {
			@SuppressWarnings("resource")
			HttpClient httpclient = new DefaultHttpClient();
			//创建登录请求的URL
			// 登录url
			HttpPost httpost = new HttpPost("登录地址");
			//创建登录时候所需要传递的数据
	List<NameValuePair> nvp = new ArrayList<NameValuePair>();
	//此处的key值对应你在浏览器上获取的
	nvp.add(new BasicNameValuePair("USERNAME", "YTJJJSKFQDJJSQWSFWZXGLY"));
	nvp.add(new BasicNameValuePair("PASSWORD", "e10adc3949ba59abbe56e057f20f883e"));
			String sCharSet = "utf-8";
			httpost.setEntity(new UrlEncodedFormEntity(nvp, sCharSet));

			HttpResponse response;
			String value = null;
			response = httpclient.execute(httpost);
			// post请求成功后的返回值
			String str = EntityUtils.toString(response.getEntity());
			System.out.println(str);

			//获取response中的cookie值
			Header[] headers = response.getHeaders("Set-Cookie");
			//取出所有的cookie值
			for (int i = 0; i < headers.length; i++) {
				value = headers[i].getValue();
				cookie += value;
			}
		} catch (UnsupportedEncodingException e) {
			e.printStackTrace();
		} catch (ClientProtocolException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return cookie;
	}

    2.HttpRequestWdqy.httpPost 方法一：获取页面数据；

/**
	 * 获取列表
	 *
	 * @author lgs
	 */
	public static String httpPost(String url, String param, String cookie) {
		PrintWriter out = null;
		BufferedReader in = null;
		String result = "";
		try {
			URL realUrl = new URL(url);
			//打开和URL之间的连接
			URLConnection conn = realUrl.openConnection();
			//设置通用的请求属性
			conn.setRequestProperty("Accept", "application/json, text/javascript, */*; q=0.01");
			conn.setRequestProperty("Connection", "keep-alive");
			conn.setRequestProperty("Cookie", cookie);
			conn.setRequestProperty("User-Agent",
					"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36");
			//发送POST请求必须设置如下两行
			conn.setDoOutput(true);
			conn.setDoInput(true);

			//获取URLConnection对象对应的输出流
			out = new PrintWriter(conn.getOutputStream());
			//发送请求参数
			out.print(param);
			//flush输出流的缓冲
			out.flush();
			//定义BufferedReader输入流来读取URL的响应
			in = new BufferedReader(new InputStreamReader(conn.getInputStream()));
			String line;
			StringBuffer resultDate = new StringBuffer();
			while ((line = in.readLine()) != null) {
				result += line;
				resultDate.append(line.trim());
				System.out.println(resultDate);
			}
		} catch (Exception e) {
			System.out.println("发送POST请求出现异常！" + e);
			e.printStackTrace();
		}
		//使用finally块来关闭输出流、输入流
		finally {
			try {
				if (out != null) {
					out.close();
				}
				if (in != null) {
					in.close();
				}
			} catch (IOException ex) {
				ex.printStackTrace();
			}
		}
		return result;
	}

    3.HttpRequestWd.httpPost 方法二：获取页面数据

 public static JsonResult httpPost(CloseableHttpClient httpclient, String host, String path, HashMap<String, String> params, List<NameValue> entityList, String cookie) {

        JsonResult jsonResult = new JsonResult();

        CloseableHttpResponse response = null;
        try {
  URIBuilder uriBuilder = new URIBuilder().setScheme("http").setHost(host).setPath(path);
            if (params != null) {
                Set<Entry<String, String>> entrySet = params.entrySet();
                for (Iterator<Entry<String, String>> iterator = entrySet.iterator(); iterator.hasNext(); ) {
                    Entry<String, String> entry = (Entry<String, String>) iterator.next();
                    String key = entry.getKey();
                    String value = entry.getValue();
                    uriBuilder.addParameter(key, value);
                }
            }
            URI url = null;
            try {
                url = uriBuilder.build();
            } catch (URISyntaxException e1) {
                // TODO Auto-generated catch block
                e1.printStackTrace();
            }
            HttpPost httpPost = new HttpPost(url);
            httpPost.setHeader("Cookie", cookie);
            httpPost.setHeader("ContentType", "application/x-www-form-urlencoded");
            UrlEncodedFormEntity entity = new UrlEncodedFormEntity(entityList, Consts.UTF_8);
            LogWd.log(entity.toString());
            LogWd.log("参数信息：" + URLEncodedUtils.format(entityList, "UTF-8"));
            LogWd.log("token:" + cookie);
            httpPost.setEntity(entity);
            response = httpclient.execute(httpPost);
            StatusLine statusLine = response.getStatusLine();
            String string = null;
            string = EntityUtils.toString(response.getEntity());
            LogWd.log(new Date().toString());
            LogWd.log("参数信息111：" + response);
            LogWd.log("开始" + url);
            LogWd.log(string);
            LogWd.log("结束" + url);
            if (statusLine != null && 200 != statusLine.getStatusCode()) {
                jsonResult.setCode(statusLine.getStatusCode());
                jsonResult.setMessage("反馈信息出错");
                return jsonResult;
            }
            jsonResult.setCode(200);
            jsonResult.setMessage(string);
            return jsonResult;
        } catch (SecurityException | IllegalArgumentException | IOException e) {
            jsonResult.setCode(500);
            e.printStackTrace();
            jsonResult.setMessage(e.getMessage());
            return jsonResult;
        } finally {
            try {
                if (response != null) {
                    response.close();
                }
            } catch (IOException e) {

                e.printStackTrace();
            }
        }

    }

方法一获取的是个String类型的页面数据，暂时不知道咋分析String类型的页面数据，可以作为返回列表的数据接口使用。