python爬取jsp网页_Python 爬取热词并进行分类数据分析-[JSP演示+页面跳转]

最新推荐文章于 2021-11-15 19:24:35 发布

weixin_39735166

最新推荐文章于 2021-11-15 19:24:35 发布

阅读量1k

点赞数

文章标签： python爬取jsp网页

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】

c.【拓扑数据】

d.【数据修复】

f.【JSP演示+页面跳转】(本期博客)

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：

1 packagecom.servlet;2

3 importjava.io.IOException;4 importjava.sql.SQLException;5 importjava.util.List;6

7 importjavax.servlet.ServletException;8 importjavax.servlet.ServletOutputStream;9 importjavax.servlet.annotation.WebServlet;10 importjavax.servlet.http.HttpServlet;11 importjavax.servlet.http.HttpServletRequest;12 importjavax.servlet.http.HttpServletResponse;13

14 importorg.json.JSONArray;15 importorg.json.JSONObject;16

17 importcom.dblink.basic.utils.SqlUtils;18 importcom.dblink.basic.utils.sqlKind.MySql_s;19 importcom.dblink.basic.utils.user.UserInfo;20 importcom.dblink.bean.BeanGroup;21 importcom.dblink.sql.DBLink;22

23 @SuppressWarnings("unused")24 public class ServletForLinkData extendsHttpServlet{25 /**

26 *27 */

28 private static final long serialVersionUID = 1L;29 //----------------------------------------------------------------------//30 public void doPost(HttpServletRequest request,HttpServletResponse response) throwsServletException, IOException31 {32 request.setCharacterEncoding("utf-8");33 response.setCharacterEncoding("utf-8");34 response.setContentType("application/json");35 response.setHeader("Cache-Control", "no-cache");36 response.setHeader("Pragma", "no-cache");37

38 String word = request.getParameter("word");39

40 JSONArray jsonArray = newJSONArray();41

42 JSONObject jsonObj = newJSONObject();43

45 DBLink dbLink = new DBLink(new SqlUtils(new MySql_s("rc"),new UserInfo("root","123456")));46 BeanGroup bg = null;47 try{48 bg = dbLink.getSelect("Select * From words where word = '"+word+"'").beans;49

50 int leng =bg.size();51

52 jsonObj.put("Length",leng);53

54 jsonArray.put(jsonObj);55

56 for(int i=0;i

67 }68 dbLink.free();69

70 ServletOutputStream os =response.getOutputStream();71 os.write(jsonArray.toString().getBytes());72 os.flush();73 os.close();74 }75 //---------------------------------------------------------------------------------//76 }

ServletForLinkData.java

1 packagecom.servlet;2

3 importjava.io.IOException;4 importjava.sql.SQLException;5 importjava.util.List;6

14 importorg.json.JSONArray;15 importorg.json.JSONObject;16

23 @SuppressWarnings("unused")24 public class ServletForAllKeyWords extendsHttpServlet{25 /**

26 *27 */

38 String sql_rest = request.getParameter("sql");39

40 JSONArray jsonArray = newJSONArray();41

42 JSONObject jsonObj = newJSONObject();43

45 DBLink dbLink = new DBLink(new SqlUtils(new MySql_s("rc"),new UserInfo("root","123456")));46 BeanGroup bg = null;47 try{48 bg = dbLink.getSelect("Select * From keywords "+sql_rest).beans;49

50 int leng =bg.size();51

52 int maxSize = dbLink.getSelect("Select * From keywords ").beans.size();53

54 int page = maxSize%leng==0?(maxSize/30):(maxSize/30)+1;55

56 jsonObj.put("Length",leng);57 jsonObj.put("MaxSize",maxSize);58 jsonObj.put("Page",page);59

60 jsonArray.put(jsonObj);61

62 for(int i=0;i

72 }73 dbLink.free();74

75 ServletOutputStream os =response.getOutputStream();76 os.write(jsonArray.toString().getBytes());77 os.flush();78 os.close();79 }80 //---------------------------------------------------------------------------------//81 }

ServletForAllKeyWords.java

web.xml 文件更改：

1 <?xml version="1.0" encoding="UTF-8"?>

3 HotWord

5 This is the description of my J2EE component

6 This is the display name of my J2EE component

7 ServletForWords

8 com.servlet.ServletForWords

11 ServletForWords

12 /com/servlet/ServletForWords

15 This is the description of my J2EE component

16 This is the display name of my J2EE component

17 ServletForAllKeyWords

18 com.servlet.ServletForAllKeyWords

21 ServletForAllKeyWords

22 /com/servlet/ServletForAllKeyWords

25 This is the description of my J2EE component

26 This is the display name of my J2EE component

27 ServletForLinkData

28 com.servlet.ServletForLinkData

31 ServletForLinkData

32 /com/servlet/ServletForLinkData

35 index.html

36 index.htm

37 index.jsp

38 default.html

39 default.htm

40 default.jsp

web.xml

jsFiles/word.js 文件

1 var wordPage = 1;2 functionmakePageToWord()3 {4 var Area = '';5 Area += '

';6 Area += '

';7 Area += '

全部热词

';8 Area += '

';9 Area += '

';10 Area += '

';11 Area += '
';12 Area += '

';13 Area += '

';14 Area += ' 热词表';15 Area += '

';16 Area += ' ';17 Area += ' 按照词频顺序';18 Area += ' 按照字母表顺序';19 Area += ' ';20 Area += ' ';21 Area += ' ';22 Area += ' 降序';23 Area += ' 增序';24 Area += ' ';25 Area += ' ';26 Area += '

';27 Area += '

';28 Area += '

';29 Area += '
';30 Area += '
';31 Area += '

';32 Area += '

';33 document.getElementById("page-inner").innerHTML =Area;34 simpleReset();35 }36 functionsimpleReset()37 {38 wordPage = 1;39 resetAndFresh();40 }41 functionXReset(p)42 {43 wordPage =p;44 wordPage = parseInt(""+wordPage);45 resetAndFresh();46 }47 functionresetAndFresh()48 {49 var sty = document.getElementById("sty").value;50 var order = document.getElementById("order").value;51 var xmlHttp = null;52 try{53 xmlHttp = newXMLHttpRequest();54 } catch(e1) {55 try{56 xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");57 } catch(e2) {58 alert("Your browser does not support XMLHTTP!");59 return;60 }61 }62 xmlHttp.onreadystatechange = function() {63 if (xmlHttp.readyState == 4) {64 if (xmlHttp.status == 200)65 {66 var Area = "";67

68 s =xmlHttp.responseText;69 var InformationSet = eval('('+s+')');70 var leng = InformationSet[0].Length;71 var max = InformationSet[0].MaxSize;72 var pageNum = InformationSet[0].Page;73

74 Area += "

热词	词频	详细信息链接
";86 Area +=InformationSet[i].word;87 Area += "	";89 Area +=InformationSet[i].num;90 Area += "	";92 Area += " 详细信息";93 Area += "

98 {99 for (var i=1;i<=10;++i)100 {101 Area += "

";102 Area += " ";103 Area +=InformationSet[i].word;104 Area += " ";105 Area += " ";106 Area +=InformationSet[i].num;107 Area += " ";108 Area += " ";109 Area += " 详细信息";110 Area += " ";111 Area += "";112 }113 }114 Area += "";115

116

117 if(leng>10)118 {119 Area += "

热词	词频	详细信息链接
";131 Area +=InformationSet[i].word;132 Area += "	";134 Area +=InformationSet[i].num;135 Area += "	";137 Area += " 详细信息";138 Area += "

143 {144 for (var i=11;i<=20;++i)145 {146 Area += "

";147 Area += " ";148 Area +=InformationSet[i].word;149 Area += " ";150 Area += " ";151 Area +=InformationSet[i].num;152 Area += " ";153 Area += " ";154 Area += " 详细信息";155 Area += " ";156 Area += "";157 }158 }159 Area += "";160 }161

162 if(leng>20)163 {164 Area += "

热词	词频	详细信息链接
";174 Area +=InformationSet[i].word;175 Area += "	";177 Area +=InformationSet[i].num;178 Area += "	";180 Area += " 详细信息";181 Area += "

";185 }186 Area += "
";188 Area += "
";189 Area += "
";190 Area += "
";191 Area += "

";192 Area += " 起始页 ";193

194 var start = ((wordPage-4)>=1)?wordPage-4:1;195 var end = ((wordPage+4)<=pageNum)?(wordPage+4):pageNum;196

197 //alert(parseInt(wordPage+4+""));

198

199 if(start!=1)200 {201 Area += " ... ";202 }203

204 for(var i=start;i<=end;++i)205 {206 Area += " "+i+" ";207 }208

209 if(end!=pageNum)210 {211 Area += " ... ";212 }213

214 Area += " 结束页 ";215 Area += " 选择页数跳转 ";216 Area += "";217 for(var i=1;i<=pageNum;++i)218 {219 Area += ""+i+"";220 }221 Area += "";222 Area += "

";223 document.getElementById("MessageArea").innerHTML =Area;224 surePage();225 }226 }227 };228 var url ="../com/servlet/ServletForAllKeyWords";229 var server = "sql=";230 //按照词频顺序

231 if(sty==0)232 {233 server += " order by num ";234 }235 //按照字母表顺序

236 else if(sty==1)237 {238 server += " order by word ";239 }240

241 //如果是降序

242 if(order==0)243 {244 server += " DESC ";245 }246

247 server += (" Limit "+((wordPage-1)*30)+",30 ");248

249 xmlHttp.open("POST", url, true);250 xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");251 xmlHttp.send(server);252 }253 functiontoSomeWhere(word)254 {255 var Area = '';256 Area += '

';257 Area += '

';258 Area += '

'+word+'

';259 Area += '

';260 Area += '

';261 Area += '

';262 Area += '
';263 Area += '

';264 Area += '

';265 document.getElementById("page-inner").innerHTML =Area;266

267 var xmlHttp = null;268 try{269 xmlHttp = newXMLHttpRequest();270 } catch(e1) {271 try{272 xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");273 } catch(e2) {274 alert("Your browser does not support XMLHTTP!");275 return;276 }277 }278 xmlHttp.onreadystatechange = function() {279 if (xmlHttp.readyState == 4) {280 if (xmlHttp.status == 200)281 {282 var Area = "";283

284 s =xmlHttp.responseText;285 var InformationSet = eval('('+s+')');286 var word = InformationSet[1].word;287 var num = InformationSet[1].num;288 var exp = InformationSet[1].exp;289

290 Area += "

"+word+"

";291 Area += "

引用次数:"+num+"

292 Area += "

";293 if(exp=="")294 {295 Area += "目前百度百科上并没有相关解释信息...";296 }297 else

298 {299 Area +=exp;300 }301 Area += "

";302 Area += "
";303 Area += "

304 document.getElementById("MessageArea").innerHTML =Area;305

306 getLinksForKey(word);307 }308 }309 };310 var url ="../com/servlet/ServletForAllKeyWords";311 var server = "sql= where word='"+word+"'";312

313 xmlHttp.open("POST", url, true);314 xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");315 xmlHttp.send(server);316 }317 functiongetLinksForKey(word)318 {319 var xmlHttp = null;320 try{321 xmlHttp = newXMLHttpRequest();322 } catch(e1) {323 try{324 xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");325 } catch(e2) {326 alert("Your browser does not support XMLHTTP!");327 return;328 }329 }330 xmlHttp.onreadystatechange = function() {331 if (xmlHttp.readyState == 4) {332 if (xmlHttp.status == 200)333 {334 var Area = "";335 Area += "
";336 Area += "
";337 Area += "引用网页：";338 Area += "
";339 Area += "
";340 s =xmlHttp.responseText;341 var InformationSet = eval('('+s+')');342 var leng = InformationSet[0].Length;343

344 for(var i=1;i<=leng;++i)345 {346 var word =InformationSet[i].word;347 var num =InformationSet[i].num;348 var title =InformationSet[i].title;349 var link =InformationSet[i].link;350 Area += "

";351 Area += ""+title+""

352 Area += "

";353 }354

355 document.getElementById("finalDIV").innerHTML =Area;356 }357 }358 };359 var url ="../com/servlet/ServletForLinkData";360 var server = "word="+word;361

362 xmlHttp.open("POST", url, true);363 xmlHttp.setRequestHeader("Content-Type","application/x-www-form-urlencoded");364 xmlHttp.send(server);365 }366 functionsurePage()367 {368 document.getElementById("selPage").selectedIndex = wordPage-1;369 }370 functionmakeSurePage()371 {372 wordPage = document.getElementById("selPage").value;373 wordPage = parseInt(""+wordPage);374 resetAndFresh();375 }

word.js

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 += "
";

Area += "引用网页：";

Area += "
";

Area += "

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 += "

Area += ""+title+""

Area += "

}

Area += "

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 += '

'+word+'

Area += '

Area += '
';

Area += '

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 += "

"+word+"

Area += "

引用次数:"+num+"

Area += "

if(exp=="")

{

Area += "目前百度百科上并没有相关解释信息...";

}

else

{

Area += exp;

}

Area += "

Area += "
";

Area += "

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。

weixin_39735166

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
python爬取jsp网页_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】c.【拓扑数据】d.【数据修复】f.【JSP演示+页面跳转】(本期博客)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：...
复制链接

扫一扫

python爬取jsp网页_Python 爬取 热词并进行分类数据分析-[JSP演示+页面跳转]

全部热词

'+word+'

'+word+'

“相关推荐”对你有帮助么？

python爬取jsp网页_Python 爬取热词并进行分类数据分析-[JSP演示+页面跳转]