Python 爬取 热词并进行分类数据分析-[JSP演示+页面跳转]

日期：2020.02.03

博客期：142

星期一

　　　　【本博客的代码如若要使用，请在下方评论区留言，之后再用（就是跟我说一声）】

　　所有相关跳转：

　　a.【简单准备】

　　b.【云图制作+数据导入】

　　c.【拓扑数据】

　　d.【数据修复】

　　e.【解释修复+热词引用】

　　 f.【JSP演示+页面跳转】（本期博客）

　　g.【热词分类+目录生成】

　　h.【热词关系图+报告生成】

　　i . 【App制作】

　　j . 【安全性改造】

---

　　　　今天开始准备把昨天的任务补一下，再补充一下以前的博客。

　　　　1、全部热词演示页面改写

 　　　　我追加了其他页的展示和页面跳转部分js内容

 　　　　附加新增代码：

　　　　　　com.servlet 包：

package com.servlet;

import java.io.IOException;
import java.sql.SQLException;
import java.util.List;

import javax.servlet.ServletException;
import javax.servlet.ServletOutputStream;
import javax.servlet.annotation.WebServlet;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

import org.json.JSONArray;
import org.json.JSONObject;

import com.dblink.basic.utils.SqlUtils;
import com.dblink.basic.utils.sqlKind.MySql_s;
import com.dblink.basic.utils.user.UserInfo;
import com.dblink.bean.BeanGroup;
import com.dblink.sql.DBLink;

@SuppressWarnings("unused")
public class ServletForLinkData extends HttpServlet{
    /**
     * 
     */
    private static final long serialVersionUID = 1L;
    //----------------------------------------------------------------------//
    public void doPost(HttpServletRequest request,HttpServletResponse response) throws ServletException, IOException
    {
        request.setCharacterEncoding("utf-8");
        response.setCharacterEncoding("utf-8");
        response.setContentType("application/json");
        response.setHeader("Cache-Control", "no-cache");
        response.setHeader("Pragma", "no-cache");
        
        String word = request.getParameter("word");
        
        JSONArray jsonArray = new JSONArray();
        
        JSONObject jsonObj = new JSONObject();
        
        
        DBLink dbLink = new DBLink(new SqlUtils(new MySql_s("rc"),new UserInfo("root","123456")));
        BeanGroup bg = null;
        try {
            bg = dbLink.getSelect("Select * From words where word = '"+word+"'").beans;
            
            int leng = bg.size();
            
            jsonObj.put("Length",leng);
            
            jsonArray.put(jsonObj);
            
            for(int i=0;i<leng;++i)
            {
                JSONObject jsonObject = new JSONObject();
                jsonObject.put("word",bg.get(i).get(0));
                jsonObject.put("num",bg.get(i).get(1));
                jsonObject.put("title",bg.get(i).get(2));
                jsonObject.put("link",bg.get(i).get(3));
                jsonArray.put(jsonObject);
            }
        } catch (SQLException e) {
            // Do Nothing ...
        }
        dbLink.free();
        
        ServletOutputStream os = response.getOutputStream();
        os.write(jsonArray.toString().getBytes());
        os.flush();
        os.close();
    }
    //---------------------------------------------------------------------------------//
}

package com.servlet;

import java.io.IOException;
import java.sql.SQLException;
import java.util.List;

import javax.servlet.ServletException;
import javax.servlet.ServletOutputStream;
import javax.servlet.annotation.WebServlet;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

import org.json.JSONArray;
import org.json.JSONObject;

import com.dblink.basic.utils.SqlUtils;
import com.dblink.basic.utils.sqlKind.MySql_s;
import com.dblink.basic.utils.user.UserInfo;
import com.dblink.bean.BeanGroup;
import com.dblink.sql.DBLink;

@SuppressWarnings("unused")
public class ServletForAllKeyWords extends HttpServlet{
    /**
     * 
     */
    private static final long serialVersionUID = 1L;
    //----------------------------------------------------------------------//
    public void doPost(HttpServletRequest request,HttpServletResponse response) throws ServletException, IOException
    {
        request.setCharacterEncoding("utf-8");
        response.setCharacterEncoding("utf-8");
        response.setContentType("application/json");
        response.setHeader("Cache-Control", "no-cache");
        response.setHeader("Pragma", "no-cache");
        
        String sql_rest = request.getParameter("sql");
        
        JSONArray jsonArray = new JSONArray();
        
        JSONObject jsonObj = new JSONObject();
        
        
        DBLink dbLink = new DBLink(new SqlUtils(new MySql_s("rc"),new UserInfo("root","123456")));
        BeanGroup bg = null;
        try {
            bg = dbLink.getSelect("Select * From keywords "+sql_rest).beans;
            
            int leng = bg.size();
            
            int maxSize = dbLink.getSelect("Select * From keywords ").beans.size();
            
            int page = maxSize%leng==0?(maxSize/30):(maxSize/30)+1;
            
            jsonObj.put("Length",leng);
            jsonObj.put("MaxSize",maxSize);
            jsonObj.put("Page",page);
            
            jsonArray.put(jsonObj);
            
            for(int i=0;i<leng;++i)
            {
                JSONObject jsonObject = new JSONObject();
                jsonObject.put("word",bg.get(i).get(0));
                jsonObject.put("num",bg.get(i).get(1));
                jsonObject.put("exp",bg.get(i).get(2));
                jsonArray.put(jsonObject);
            }
        } catch (SQLException e) {
            // Do Nothing ...
        }
        dbLink.free();
        
        ServletOutputStream os = response.getOutputStream();
        os.write(jsonArray.toString().getBytes());
        os.flush();
        os.close();
    }
    //---------------------------------------------------------------------------------//
}

　　　　　　web.xml 文件更改：

<?xml version="1.0" encoding="UTF-8"?>
<web-app xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://xmlns.jcp.org/xml/ns/javaee" xsi:schemaLocation="http://xmlns.jcp.org/xml/ns/javaee http://xmlns.jcp.org/xml/ns/javaee/web-app_4_0.xsd" id="WebApp_ID" version="4.0">
  <display-name>HotWord</display-name>
  <servlet>
    <description>This is the description of my J2EE component</description>
    <display-name>This is the display name of my J2EE component</display-name>
    <servlet-name>ServletForWords</servlet-name>
    <servlet-class>com.servlet.ServletForWords</servlet-class>
  </servlet>
  <servlet-mapping>
    <servlet-name>ServletForWords</servlet-name>
    <url-pattern>/com/servlet/ServletForWords</url-pattern>
  </servlet-mapping>
  <servlet>
    <description>This is the description of my J2EE component</description>
    <display-name>This is the display name of my J2EE component</display-name>
    <servlet-name>ServletForAllKeyWords</servlet-name>
    <servlet-class>com.servlet.ServletForAllKeyWords</servlet-class>
  </servlet>
  <servlet-mapping>
    <servlet-name>ServletForAllKeyWords</servlet-name>
    <url-pattern>/com/servlet/ServletForAllKeyWords</url-pattern>
  </servlet-mapping>
  <servlet>
    <description>This is the description of my J2EE component</description>
    <display-name>This is the display name of my J2EE component</display-name>
    <servlet-name>ServletForLinkData</servlet-name>
    <servlet-class>com.servlet.ServletForLinkData</servlet-class>
  </servlet>
  <servlet-mapping>
    <servlet-name>ServletForLinkData</servlet-name>
    <url-pattern>/com/servlet/ServletForLinkData</url-pattern>
  </servlet-mapping>
  <welcome-file-list>
    <welcome-file>index.html</welcome-file>
    <welcome-file>index.htm</welcome-file>
    <welcome-file>index.jsp</welcome-file>
    <welcome-file>default.html</welcome-file>
    <welcome-file>default.htm</welcome-file>
    <welcome-file>default.jsp</welcome-file>
  </welcome-file-list>
</web-app>

　　　　　　jsFiles/word.js 文件

var wordPage = 1;
function makePageToWord()
{
    var Area = '';
    Area += '<div class="row">';
    Area += '<div class="col-md-12">';
    Area += '<h2>全部热词</h2>';
    Area += '</div>';
    Area += '</div>';
    Area += '<hr />';
    Area += '<br>';
    Area += '<div style="background:rgb(0,153,255);margin-left:20px;margin-right:20px;height:25px;">';
    Area += '    <div style="margin-left:10px;margin-right:10px;margin-top:5px;margin-bottom:5px;">';
    Area += '        <b style="float:left;">热词表</b>';
    Area += '        <div style="float:right;">';
    Area += '        <select id="sty" onchange="simpleReset()">';
    Area += '            <option value="0" selected>按照词频顺序</option>';
    Area += '            <option value="1">按照字母表顺序</option>';
    Area += '        </select>';
    Area += '&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;';
    Area += '        <select id="order" onchange="simpleReset()">';
    Area += '            <option value="0" selected>降序</option>';
    Area += '            <option value="1">增序</option>';
    Area += '        </select>';
    Area += '&nbsp;&nbsp;';
    Area += '        </div>';
    Area += '    </div>';
    Area += '</div>';
    Area += '<br>';
    Area += '<br>';
    Area += '<div id="MessageArea">';
    Area += '</div>';
    document.getElementById("page-inner").innerHTML = Area;
    simpleReset();
}
function simpleReset()
{
    wordPage = 1;
    resetAndFresh();
}
function XReset(p)
{
    wordPage = p;
    wordPage = parseInt(""+wordPage);
    resetAndFresh();
}
function resetAndFresh()
{
    var sty = document.getElementById("sty").value;
    var order = document.getElementById("order").value;
    var xmlHttp = null;
    try{
        xmlHttp = new XMLHttpRequest();
       } catch (e1) {
            try {
                xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");
        } catch (e2) {
            alert("Your browser does not support XMLHTTP!");
            return;
        }
    }
    xmlHttp.onreadystatechange = function() {
        if (xmlHttp.readyState == 4) {
            if (xmlHttp.status == 200) 
            {
                var Area = "";
                                
                s = xmlHttp.responseText;
                var InformationSet = eval('('+s+')');
                var leng = InformationSet[0].Length;
                var max = InformationSet[0].MaxSize;
                var pageNum = InformationSet[0].Page;
                
                Area += "<table class='WhatATable' style='margin-left:200px;float:left;'>";
                Area += "<tr>";
                Area += "<th style='100px;'>热词</th>";
                Area += "<th style='100px;'>词频</th>";
                Area += "<th style='100px;'>详细信息链接</th>";
                Area += "</tr>";
                if(leng<10)
                {
                    for (var i=1;i<=leng;++i)
                    {
                        Area += "<tr>";
                        Area += "    <td>";
                        Area += InformationSet[i].word;
                        Area += "    </td>";
                        Area += "    <td>";
                        Area += InformationSet[i].num;
                        Area += "    </td>";
                        Area += "    <td>";
                        Area += "        <a href='#' onclick='toSomeWhere(""+InformationSet[i].word+"")'>详细信息</a>";
                        Area += "    </td>";
                        Area += "</tr>";
                    }
                }
                else
                {
                    for (var i=1;i<=10;++i)
                    {
                        Area += "<tr>";
                        Area += "    <td>";
                        Area += InformationSet[i].word;
                        Area += "    </td>";
                        Area += "    <td>";
                        Area += InformationSet[i].num;
                        Area += "    </td>";
                        Area += "    <td>";
                        Area += "        <a href='#' onclick='toSomeWhere(""+InformationSet[i].word+"")'>详细信息</a>";
                        Area += "    </td>";
                        Area += "</tr>";
                    }
                }
                Area += "</table>";
                
                
                if(leng>10)
                {
                    Area += "<table class='WhatATable' style='margin-left:10px;float:left;'>";
                    Area += "<tr>";
                    Area += "<th style='100px;'>热词</th>";
                    Area += "<th style='100px;'>词频</th>";
                    Area += "<th style='100px;'>详细信息链接</th>";
                    Area += "</tr>";
                    if(leng<=20)
                    {
                        for (var i=11;i<=leng;++i)
                        {
                            Area += "<tr>";
                            Area += "    <td>";
                            Area += InformationSet[i].word;
                            Area += "    </td>";
                            Area += "    <td>";
                            Area += InformationSet[i].num;
                            Area += "    </td>";
                            Area += "    <td>";
                            Area += "        <a href='#' onclick='toSomeWhere(""+InformationSet[i].word+"")'>详细信息</a>";
                            Area += "    </td>";
                            Area += "</tr>";
                        }
                    }
                    else
                    {
                        for (var i=11;i<=20;++i)
                        {
                            Area += "<tr>";
                            Area += "    <td>";
                            Area += InformationSet[i].word;
                            Area += "    </td>";
                            Area += "    <td>";
                            Area += InformationSet[i].num;
                            Area += "    </td>";
                            Area += "    <td>";
                            Area += "        <a href='#' onclick='toSomeWhere(""+InformationSet[i].word+"")'>详细信息</a>";
                            Area += "    </td>";
                            Area += "</tr>";
                        }
                    }
                    Area += "</table>";
                }
                
                if(leng>20)
                {
                    Area += "<table class='WhatATable' style='margin-left:10px;float:left;'>";
                    Area += "<tr>";
                    Area += "<th style='100px;'>热词</th>";
                    Area += "<th style='100px;'>词频</th>";
                    Area += "<th style='100px;'>详细信息链接</th>";
                    Area += "</tr>";
                    for (var i=21;i<=leng;++i)
                    {
                        Area += "<tr>";
                        Area += "    <td>";
                        Area += InformationSet[i].word;
                        Area += "    </td>";
                        Area += "    <td>";
                        Area += InformationSet[i].num;
                        Area += "    </td>";
                        Area += "    <td>";
                        Area += "        <a href='#' onclick='toSomeWhere(""+InformationSet[i].word+"")'>详细信息</a>";
                        Area += "    </td>";
                        Area += "</tr>";
                    }
                    Area += "</table>";
                }
                Area += "<div style='clear:both;'></div>";
                Area += "<br>";
                Area += "<br>";
                Area += "<br>";
                Area += "<br>";
                Area += "<p style='margin-left:30px;margin-right:30px;'>";
                Area += "&nbsp;<button onclick='simpleReset()'>起始页</button>&nbsp;";
                
                var start = ((wordPage-4)>=1)?wordPage-4:1;
                var end = ((wordPage+4)<=pageNum)?(wordPage+4):pageNum;
                
                //alert(parseInt(wordPage+4+""));
                
                if(start!=1)
                {
                    Area += "&nbsp;...&nbsp;";
                }
                
                for(var i=start;i<=end;++i)
                {
                    Area += "&nbsp;<button onclick='XReset("+i+")'>"+i+"</button>&nbsp;";
                }
                
                if(end!=pageNum)
                {
                    Area += "&nbsp;...&nbsp;";
                }
                
                Area += "&nbsp;<button onclick='XReset("+pageNum+")'>结束页</button>&nbsp;";
                Area += "&nbsp;&nbsp;<b>选择页数跳转</b>&nbsp;&nbsp;";
                Area += "<select id='selPage' onchange='makeSurePage()'>";
                for(var i=1;i<=pageNum;++i)
                {
                    Area += "<option value='"+i+"'>"+i+"</option>";
                }
                Area += "</select>";
                Area += "</p>";
                document.getElementById("MessageArea").innerHTML = Area;
                surePage();
            }
           }
    };
    var url ="../com/servlet/ServletForAllKeyWords";
    var server = "sql=";
    // 按照词频顺序
    if(sty==0)
    {
        server += " order by num ";
    }
    // 按照字母表顺序
    else if(sty==1)
    {
        server += " order by word ";
    }
    
    // 如果是降序
    if(order==0)
    {
        server += " DESC ";
    }
    
    server += (" Limit "+((wordPage-1)*30)+",30 ");

    xmlHttp.open("POST", url, true);
    xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");
    xmlHttp.send(server);
}
function toSomeWhere(word)
{
    var Area = '';
    Area += '<div class="row">';
    Area += '    <div class="col-md-12">';
    Area += '        <h2>'+word+'</h2>';
    Area += '    </div>';
    Area += '</div>';
    Area += '<hr />';
    Area += '<br>';
    Area += '<div id="MessageArea">';
    Area += '</div>';
    document.getElementById("page-inner").innerHTML = Area;
    
    var xmlHttp = null;
    try{
        xmlHttp = new XMLHttpRequest();
       } catch (e1) {
            try {
                xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");
        } catch (e2) {
            alert("Your browser does not support XMLHTTP!");
            return;
        }
    }
    xmlHttp.onreadystatechange = function() {
        if (xmlHttp.readyState == 4) {
            if (xmlHttp.status == 200) 
            {
                var Area = "";
                
                s = xmlHttp.responseText;
                var InformationSet = eval('('+s+')');
                var word = InformationSet[1].word;
                var num  = InformationSet[1].num;
                var exp  = InformationSet[1].exp;
                
                Area += "<p><b id='word' style='font-size:120%;'>"+word+"</b></p>";
                Area += "<p>引用次数:"+num+"</p>"
                Area += "<p style='font:"楷体";font-size:90%;'>&nbsp;&nbsp;";
                if(exp=="")
                {
                    Area += "目前百度百科上并没有相关解释信息...";
                }
                else
                {
                    Area += exp;
                }
                Area += "</p>";
                Area += "<br>";
                Area += "<div id='finalDIV'></div>"
                document.getElementById("MessageArea").innerHTML = Area;
                
                getLinksForKey(word);
            }
           }
    };
    var url ="../com/servlet/ServletForAllKeyWords";
    var server = "sql= where word='"+word+"'";

    xmlHttp.open("POST", url, true);
    xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");
    xmlHttp.send(server);
}
function getLinksForKey(word)
{
    var xmlHttp = null;
    try{
        xmlHttp = new XMLHttpRequest();
       } catch (e1) {
            try {
                xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");
        } catch (e2) {
            alert("Your browser does not support XMLHTTP!");
            return;
        }
    }
    xmlHttp.onreadystatechange = function() {
        if (xmlHttp.readyState == 4) {
            if (xmlHttp.status == 200) 
            {
                var Area = "";
                Area += "<br>";
                Area += "<br>";
                Area += "<b style='font-size:120%;'>引用网页：</b>";
                Area += "<br>";
                Area += "<br>";
                s = xmlHttp.responseText;
                var InformationSet = eval('('+s+')');
                var leng = InformationSet[0].Length;
                
                for(var i=1;i<=leng;++i)
                {
                    var word  = InformationSet[i].word;
                    var num   = InformationSet[i].num;
                    var title = InformationSet[i].title;
                    var link  = InformationSet[i].link;
                    Area += "<p>";
                    Area += "<a href='"+link+"' title='引用次数："+num+"'>"+title+"</a>"
                    Area += "</p>";
                }
                
                document.getElementById("finalDIV").innerHTML = Area;
            }
           }
    };
    var url ="../com/servlet/ServletForLinkData";
    var server = "word="+word;

    xmlHttp.open("POST", url, true);
    xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");
    xmlHttp.send(server);
}
function surePage()
{
    document.getElementById("selPage").selectedIndex = wordPage-1;
}
function makeSurePage()
{
    wordPage = document.getElementById("selPage").value;
    wordPage = parseInt(""+wordPage);
    resetAndFresh();
}

　　　　这个页面跳转是自己写的，自己慢慢调 Bug 调了很久，最后所有页面的跳转都能实现了，我才开始写博客。

　　　　2、热词展示页面改写

 　　　　之后我将热词展示页面稍稍改写了一下，要比昨天的好看，呃~其实就是加了一点CSS修饰，无关紧要的。

 　　　　对应修改的 word.js 文件里的 function :

function getLinksForKey(word)
{
	var xmlHttp = null;
	try{
		xmlHttp = new XMLHttpRequest();
	   } catch (e1) {
	   	 try {
	   		 xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");
		} catch (e2) {
			alert("Your browser does not support XMLHTTP!");
			return;
		}
	}
	xmlHttp.onreadystatechange = function() {
		if (xmlHttp.readyState == 4) {
		    if (xmlHttp.status == 200) 
		    {
		    	var Area = "";
		    	Area += "<br>";
		    	Area += "<br>";
		    	Area += "<b style='font-size:120%;'>引用网页：</b>";
		    	Area += "<br>";
		    	Area += "<br>";
		    	Area += "<ul>";
		    	s = xmlHttp.responseText;
	    		var InformationSet = eval('('+s+')');
	    		var leng = InformationSet[0].Length;
	    		
	    		for(var i=1;i<=leng;++i)
	    		{
	    			var word  = InformationSet[i].word;
		    		var num   = InformationSet[i].num;
		    		var title = InformationSet[i].title;
		    		var link  = InformationSet[i].link;
		    		Area += "<li>";
		    		Area += "<a href='"+link+"' title='引用次数："+num+"'>"+title+"</a>"
		    		Area += "</li>";
	    		}
	    		Area += "</ul>";
	    		
	    		document.getElementById("finalDIV").innerHTML = Area;
	    	}
	   	}
	};
    var url ="../com/servlet/ServletForLinkData";
    var server = "word="+word;

	xmlHttp.open("POST", url, true);
	xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");
	xmlHttp.send(server);
}

function toSomeWhere(word)
{
	var Area = '';
	Area += '<div class="row">';
	Area += '	<div class="col-md-12">';
	Area += '		<h2>'+word+'</h2>';
	Area += '	</div>';
	Area += '</div>';
	Area += '<hr />';
	Area += '<br>';
	Area += '<div id="MessageArea">';
	Area += '</div>';
	document.getElementById("page-inner").innerHTML = Area;
	
	var xmlHttp = null;
	try{
		xmlHttp = new XMLHttpRequest();
	   } catch (e1) {
	   	 try {
	   		 xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");
		} catch (e2) {
			alert("Your browser does not support XMLHTTP!");
			return;
		}
	}
	xmlHttp.onreadystatechange = function() {
		if (xmlHttp.readyState == 4) {
		    if (xmlHttp.status == 200) 
		    {
		    	var Area = "";
		    	
		    	s = xmlHttp.responseText;
	    		var InformationSet = eval('('+s+')');
	    		var word = InformationSet[1].word;
	    		var num  = InformationSet[1].num;
	    		var exp  = InformationSet[1].exp;
	    		
	    		Area += "<p><b id='word' style='font-size:120%;'>"+word+"</b></p>";
	    		Area += "<p style='color:rgb(200,200,200);'>   引用次数:"+num+"</p>"
	    		Area += "<p style='font:"楷体";font-size:90%;'>      ";
	    		if(exp=="")
	    		{
	    			Area += "目前百度百科上并没有相关解释信息...";
	    		}
	    		else
	    		{
	    			Area += exp;
	    		}
	    		Area += "</p>";
	    		Area += "<br>";
	    		Area += "<div id='finalDIV'></div>"
	    		document.getElementById("MessageArea").innerHTML = Area;
	    		
	    		getLinksForKey(word);
	    	}
	   	}
	};
    var url ="../com/servlet/ServletForAllKeyWords";
    var server = "sql= where word='"+word+"'";

	xmlHttp.open("POST", url, true);
	xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");
	xmlHttp.send(server);
}

　　　　页面还可以，说的过去...反正最终应该不会提交这个Java Web网页。