3数据分析每日进度报告01

题目要求：

基本完成地域维度标准化，将地址更新为省市县三级，并将行政区划代码添加。

效果图：

关键功能代码片段：

 1 public static String addressResolution(String address){
 2         String regex="(?<province>[^省]+自治区|.*?省|.*?行政区|.*?市)(?<city>[^市]+自治州|.*?地区|.*?行政单位|.+盟|市辖区|.*?市|.*?县|.+区|.+市)(?<county>[^县]+县|.+区|.+市|.+旗|.+海域|.+岛)";
 3         Matcher m=Pattern.compile(regex).matcher(address);
 4         String province=null,city=null,county=null;
 5         String str="";
 6         while(m.find()){
 7             province=m.group("province");
 8             city=m.group("city");
 9             county=m.group("county");
10             str = province + city + county;
11             System.out.println(str);
12         }
13         return str;
14     }

标准地址转换

 1 public static String getlocation1(String loc){
 2         String location2="";
 3           String url="http://api.map.baidu.com/geocoding/v3/?address="+loc+"10号&output=xml&ak=ld0uqubVfSTAUlXH5qIMN2F3Snsp16LU&callback=showLocation";
 4           System.out.println(url);
 5           Document doc = null;
 6            java.net.HttpURLConnection conn = null;
 7            InputStream ins = null;
 8            SAXReader reader = null;
 9            try{
10             //HttpTimeoutHandler hth = new HttpTimeoutHandler(600000);
11             URL conURL = new URL(null,url);
12             conn = (HttpURLConnection)conURL.openConnection();
13             conn.setDoInput(true);
14             conn.setDoOutput(true);
15             conn.setUseCaches(false);
16             ins = conn.getInputStream();
17             reader =new SAXReader();
18             doc= reader.read(ins);
19             //System.out.println(url);
20             Element root=doc.getRootElement();
21             String docXmlText=doc.asXML();
22             //System.out.println(docXmlText);
23             Element e=root.element("result");
24             Element location=e.element("location");
25             Element lng=location.element("lng");
26             Element lat=location.element("lat");
27             String lng1=lng.asXML();
28             String lat1=lat.asXML();
29             System.out.println("lng"+lng1);
30             System.out.println("lat"+lat1);
31            // System.out.println("location"+location.asXML());
32             //System.out.println("xiayukun"+e.asXML());
33             lng1=lng1.substring(lng1.indexOf("<lng>")+5,lng1.indexOf("</lng>"));
34             
35             System.out.println(lng1);
36             lat1=lat1.substring(lat1.indexOf("<lat>")+5,lat1.indexOf("</lat>"));
37             System.out.println(lat1);
38             location2=getLocation(lat1,lng1);
39             List<Element> list = root.elements("location");
40             System.out.println(url);
41             for (Element object : list) {
42                 System.out.println(url);
43                 System.out.println(object.getName());
44                 for (Element element : (List<Element>) object.elements()) {
45                     System.out.print(((Element) element).getName() + ":");
46                     System.out.print(element.getText() + " ");
47                 }
48                 System.out.println();
49 
50             }
51 
52             ins.close();
53             conn.disconnect();
54            }catch (MalformedURLException e) {
55             e.printStackTrace();
56            } catch (IOException e) {
57             e.printStackTrace();   
58            } catch (DocumentException e) {
59             e.printStackTrace();
60            }catch(Exception e){
61             e.printStackTrace();
62            }finally {
63             try {
64              if (ins != null) {
65               ins.close();
66               ins = null;
67              }
68             } catch (IOException e1) {
69              e1.printStackTrace();
70             }
71             try {
72              if (conn != null) {
73               conn.disconnect();
74               conn = null;
75              }
76             } catch (Exception e2) {
77              e2.printStackTrace();
78             }
79            }
80            return location2;
81         }

根据地址调用百度api获取详细地址（参考网络）

 部分运行结果截图：