爬取数据

chinese/.classpath

@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<classpath>
+	<classpathentry kind="src" output="target/classes" path="src/main/java">
+		<attributes>
+			<attribute name="optional" value="true"/>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="src" output="target/test-classes" path="src/test/java">
+		<attributes>
+			<attribute name="test" value="true"/>
+			<attribute name="optional" value="true"/>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/J2SE-1.5">
+		<attributes>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.m2e.MAVEN2_CLASSPATH_CONTAINER">
+		<attributes>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.jdt.USER_LIBRARY/userlib"/>
+	<classpathentry kind="output" path="target/classes"/>
+</classpath>

chinese/.project

@@ -0,0 +1,23 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>chinese</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.eclipse.jdt.core.javabuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+		<buildCommand>
+			<name>org.eclipse.m2e.core.maven2Builder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.eclipse.jdt.core.javanature</nature>
+		<nature>org.eclipse.m2e.core.maven2Nature</nature>
+	</natures>
+</projectDescription>

chinese/.settings/org.eclipse.core.resources.prefs

@@ -0,0 +1,4 @@
+eclipse.preferences.version=1
+encoding//src/main/java=UTF-8
+encoding//src/test/java=UTF-8
+encoding/<project>=UTF-8

chinese/.settings/org.eclipse.jdt.core.prefs

@@ -0,0 +1,6 @@
+eclipse.preferences.version=1
+org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.5
+org.eclipse.jdt.core.compiler.compliance=1.5
+org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning
+org.eclipse.jdt.core.compiler.release=disabled
+org.eclipse.jdt.core.compiler.source=1.5

chinese/.settings/org.eclipse.m2e.core.prefs

@@ -0,0 +1,4 @@
+activeProfiles=
+eclipse.preferences.version=1
+resolveWorkspaceProjects=true
+version=1

chinese/pom.xml

@@ -0,0 +1,30 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+
+  <groupId>chinesemedicine</groupId>
+  <artifactId>chinese</artifactId>
+  <version>0.0.1-SNAPSHOT</version>
+  <packaging>jar</packaging>
+
+  <name>chinese</name>
+  <url>http://maven.apache.org</url>
+
+  <properties>
+    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+  </properties>
+
+  <dependencies>
+    <dependency>
+      <groupId>junit</groupId>
+      <artifactId>junit</artifactId>
+      <version>3.8.1</version>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+    <groupId>org.jsoup</groupId>
+    <artifactId>jsoup</artifactId>
+    <version>1.8.3</version>
+</dependency>
+  </dependencies>
+</project>

chinese/src/main/java/Reptile/DBUtil.java

@@ -0,0 +1,150 @@
+package Reptile;
+
+import java.sql.Connection;
+import java.sql.DriverManager;
+import java.sql.ResultSet;
+import java.sql.SQLException;
+import java.sql.Statement;
+
+public class DBUtil {
+	public static String driverString = "com.mysql.cj.jdbc.Driver";
+	public static String sqlurl = "jdbc:mysql://114.55.37.70:3306/graph";
+
+	public static Connection conn = null;//连接对象
+	public static Statement stat = null;//执行对象
+	public static boolean isnewyid = true;
+	//建立连接
+	public static void Connection() {
+		try {
+			Class.forName(driverString);
+		} catch (ClassNotFoundException e1) {
+			// TODO Auto-generated catch block
+			e1.printStackTrace();
+		}
+		try {
+			conn = DriverManager.getConnection(sqlurl, "root", "XBxb0525@");
+		} catch (SQLException e1) {
+			// TODO Auto-generated catch block
+			e1.printStackTrace();
+		}
+		try {
+			stat = conn.createStatement();
+		} catch (SQLException e1) {
+			// TODO Auto-generated catch block
+			e1.printStackTrace();
+		}
+	}
+	
+	//返回desease的did，如果已经存在了，就返回did，不存在就返回下一个
+	public static int finddid(String dname) {
+		String sqlString = "select id from desease where dname="+dname;
+		ResultSet resultSet = null;
+		try {
+			resultSet = stat.executeQuery(sqlString);
+			resultSet.next();
+				return resultSet.getInt(1);
+		} catch (SQLException e) {
+
+//			空，这个病没有存在，将其插入到里面
+			
+				int did = countTable("desease")+1;
+				sqlString = "insert into desease values("+did+",'"+dname+"');";//插入这个疾病
+				System.out.println(sqlString);
+				try {
+					stat.executeUpdate(sqlString);
+				} catch (SQLException e1) {
+					// TODO Auto-generated catch block
+					e1.printStackTrace();
+				}//执行语句
+				return did;
+			// TODO Auto-generated catch block
+		}
+	}
+	
+	//返回药的yid,如果已经存在了，就返回yid，不存在就返回下一个
+	public static int findyid(String mname) {
+		String sqlString = "select id from yangsheng where mname="+mname;
+		ResultSet resultSet = null;
+		try {
+			resultSet = stat.executeQuery(sqlString);
+				isnewyid = false;
+				resultSet.next();
+				return resultSet.getInt(1);
+			
+		} catch (SQLException e) {
+			
+//			为空，暂时为它新创建一个id
+		
+			isnewyid = true;
+			return countTable("yangsheng")+1;
+		}
+	}
+	
+	public static int insertintoY(String index,String values) {
+		String sqlString = "insert into yangsheng("+index+") values("+values+");";
+		System.out.println(sqlString);
+		try {
+			return stat.executeUpdate(sqlString);
+			
+		} catch (SQLException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+		return -1;
+	}
+	
+	//插入关系表，dtoy
+	public static void dtoy(int did,int yid) {
+		//did是疾病的id，yid是养生方法id
+		String sqlString = "insert into dtoy values("+did+","+yid+");";
+		try {
+			stat.executeUpdate(sqlString);
+		} catch (SQLException e) {
+			// TODO Auto-generated catch block
+			System.out.println("dtoy插入数据失败");
+			e.printStackTrace();
+		}
+	}
+	//插入关系，ytod
+	public static void ytod(int yid,int did) {
+		String sqlString = "insert into ytod values("+yid+","+did+");";
+		try {
+			stat.executeUpdate(sqlString);
+		} catch (SQLException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+	}
+	
+	//获取某个表的个数
+	public static int countTable(String tablename) {
+		String sqlString = "select count(*) from "+tablename+";";
+		ResultSet resultSet = null;
+		try {
+			resultSet = stat.executeQuery(sqlString);
+		} catch (SQLException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+		try {
+			if(resultSet.next()) return resultSet.getInt(1);
+		} catch (SQLException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+		return -1;
+	}
+	
+	//关闭数据库连接
+	public static void close() {
+		try {
+			conn.close();
+		} catch (SQLException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+	}
+	
+	
+	
+}	

chinese/src/main/java/Reptile/ReadUrlUtil.java

@@ -0,0 +1,37 @@
+package Reptile;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.nio.charset.Charset;
+
+import javax.naming.ldap.Rdn;
+
+import net.sf.json.JSONObject;
+
+public class ReadUrlUtil {
+	public static JSONObject readJsonFromUrl(String urlString) throws MalformedURLException, IOException {
+		InputStream iStream = new URL(urlString).openStream();
+		try {
+			BufferedReader reader = new BufferedReader(new InputStreamReader(iStream, Charset.forName("UTF-8")));
+			StringBuilder sBuilder = new StringBuilder();
+			int cp;
+			while((cp = reader.read())!=-1) {
+				sBuilder.append((char)cp);
+				
+			}
+			String jsonText = sBuilder.toString();
+			JSONObject jsonObject = JSONObject.fromObject(jsonText);
+			return jsonObject;
+		} catch (Exception e) {
+			// TODO: handle exception
+		}finally {
+			iStream.close();
+		}
+		return null;
+		
+	}
+}

chinese/src/main/java/Reptile/perfix.java

@@ -0,0 +1,23 @@
+package Reptile;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+
+public class perfix {
+	/*
+	 * 
+名字:name
+作用:function
+操作方法:operation
+疾病disease
+证候:syndromes
+部位:position
+症状symptom
+备注Remarks
+禁忌:taboo
+
+	 * */
+	public static ArrayList<String> indexchinese = new ArrayList<String>(Arrays.asList("名字","作用","操作方法","疾病","证候","部位","症状","备注","禁忌"));
+	public static ArrayList<String> indexenglish = new ArrayList<String>(Arrays.asList("mname","mfunction","moperation","mdisease","msyndromes","mposition","msymptom","mremarks","mtaboo"));
+	
+}

chinese/src/main/java/Reptile/text.java

@@ -0,0 +1,97 @@
+package Reptile;
+
+import java.io.BufferedWriter;
+import java.io.File;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.sql.Connection;
+import java.sql.DriverManager;
+import java.sql.ResultSet;
+import java.sql.SQLException;
+import java.sql.Statement;
+
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+
+import com.google.gson.JsonArray;
+import com.mysql.cj.jdbc.result.ResultSetMetaData;
+
+import net.sf.json.JSONArray;
+import net.sf.json.JSONObject;
+
+public class text {
+	public static void main(String[] args) {
+		/*
+		 * 在这里调用dochck方法，传参症状
+		 * */
+		 
+	}
+	public static void dochck(String keyworString) {
+		DBUtil.Connection();
+		String urlString = "http://www.tcmkb.cn/kg/health2_service.php?keywords="+keyworString;
+		JSONObject jsonObject = null;
+		try {
+			jsonObject = ReadUrlUtil.readJsonFromUrl(urlString);
+		} catch (MalformedURLException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		} catch (IOException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+		
+		int deseaseid = DBUtil.finddid(keyworString);		
+		
+//		已经能够得出json数据
+//		能够分理处nodes属性的内容d,id,label,type
+		JSONArray datasArray = jsonObject.getJSONObject("data").getJSONArray("nodes");
+		for(int i=1;i<datasArray.size();i++) {
+			//外部循环可以获取每一种养生方法
+//			每个数组有type，id，label，description
+			JSONObject jo = (JSONObject) datasArray.get(i);
+			String nameString = jo.getString("id");//养生方法名
+//			String typeString = jo.getString("type");//关系：养生方法
+//			String labelString = jo.getString("label");//标签
+			String describtionString = jo.getString("description");
+			
+//			先将病症和养生方法关系建立起来
+			int yid = DBUtil.findyid(nameString);	//这个返回要么是新的id，要么是已经存在的yid，如果已经存在的没必要重复插入这个养生方法,但是不管是不是新的，did和yid的关系还是要建立
+			
+			DBUtil.ytod(yid, deseaseid);
+			DBUtil.dtoy(deseaseid, yid);
+			
+			
+			if(DBUtil.isnewyid) {
+				//不存在就要先插入这个养生方法，然后写入id，并将其他信息搞进去。
+				
+//					接下来解析description：就是有关某个养生方法的信息，这些养生方法信息要插入到yangsheng表里
+				StringBuilder sqllindex = new StringBuilder("id,mname");
+				StringBuilder sqlvalue = new StringBuilder(yid+",'"+nameString+"'");
+				Document document = Jsoup.parse(describtionString);
+				Elements elements = document.select("p:has(font)");//该药的所有的p标签
+				for(Element element:elements) {
+					String element2 = element.select("font:has(strong)").first().text();//获取字段名
+					String eleString = element.text();
+					String valueString = eleString.substring(element2.length(), eleString.length());
+					if(valueString.startsWith(": ")) valueString = valueString.substring(2);
+					//valueString是字段对应的值
+					if(perfix.indexchinese.contains(element2)) {
+						//如果包含了，那么就包含进去
+						sqllindex = sqllindex.append(","+perfix.indexenglish.get(perfix.indexchinese.indexOf(element2)));
+						sqlvalue = sqlvalue.append(",'"+valueString+"'");
+					}//不包含就不要管了			
+				}
+				//插入
+				DBUtil.insertintoY(sqllindex.toString(), sqlvalue.toString());
+			}
+			
+			
+		}
+		System.out.println("end");
+		DBUtil.close();
+	
+	}
+}

chinese/src/main/java/chinesemedicine/chinese/App.java

@@ -0,0 +1,13 @@
+package chinesemedicine.chinese;
+
+/**
+ * Hello world!
+ *
+ */
+public class App 
+{
+    public static void main( String[] args )
+    {
+        System.out.println( "Hello World!" );
+    }
+}

chinese/src/test/java/chinesemedicine/chinese/AppTest.java

@@ -0,0 +1,38 @@
+package chinesemedicine.chinese;
+
+import junit.framework.Test;
+import junit.framework.TestCase;
+import junit.framework.TestSuite;
+
+/**
+ * Unit test for simple App.
+ */
+public class AppTest 
+    extends TestCase
+{
+    /**
+     * Create the test case
+     *
+     * @param testName name of the test case
+     */
+    public AppTest( String testName )
+    {
+        super( testName );
+    }
+
+    /**
+     * @return the suite of tests being tested
+     */
+    public static Test suite()
+    {
+        return new TestSuite( AppTest.class );
+    }
+
+    /**
+     * Rigourous Test :-)
+     */
+    public void testApp()
+    {
+        assertTrue( true );
+    }
+}