注册 登录
> Java

Java版PageRank及网站收录情况查询代码

系统 1577 0

在Google这个由10的100次方得名的站点中，各种评估网站的算法层出不穷，而PageRank即是其中之一。

Google的PageRank根据网站的外部链接和内部链接的数量和质量俩衡量网站的价值。PageRank背后的概念是，每个到页面的链接都是对该页面的一次投票，被链接的越多，就意味着被其他网站投票越多。这个就是所谓的“链接流行度”——衡量多少人愿意将他们的网站和你的网站挂钩。PageRank这个概念引自学术中一篇论文的被引述的频度——即被别人引述的次数越多，一般判断这篇论文的权威性就越高。

通常情况下讲，原创内容越多的站点，PageRank越容易提升，反之则相对比较困难，PageRank最大上限值为10。在Google的评估中，能上10的网站真可谓凤毛麟角，即使算上Google，能成就PageRank 10这“伟业”者，望眼环球也不足40家。一般来说，个人站点评估值4即办的不错，商业网站到6以上便算步入正轨了。

网上虽然有不少现成的查询器及源码，但是光用别人的毕竟不符合程序员风格，所以今天自己用Java重造轮子又写了个PageRank查询实现，捎带着把一些常用搜索引擎的网站链接及反向链接查询也加上了。

源码如下：

GooglePageRank.java
  1. package org.loon.test;
  3. import java.io.IOException;
  4. import java.util.Random;
  5. import java.util.regex.Matcher;
  6. import java.util.regex.Pattern;
  8. /**
  9. *Copyright2008
  10. *
  11. *LicensedundertheApacheLicense,Version2.0(the"License");youmaynot
  12. *usethisfileexceptincompliancewiththeLicense.Youmayobtainacopyof
  13. *theLicenseat
  14. *
  15. *http://www.apache.org/licenses/LICENSE-2.0
  16. *
  17. *Unlessrequiredbyapplicablelaworagreedtoinwriting,software
  18. *distributedundertheLicenseisdistributedonan"ASIS"BASIS,WITHOUT
  19. *WARRANTIESORCONDITIONSOFANYKIND,eitherexpressorimplied.Seethe
  20. *Licenseforthespecificlanguagegoverningpermissionsandlimitationsunder
  21. *theLicense.
  22. *
  23. *@projectloonframework
  24. *@authorchenpeng
  25. *@email：ceponline@yahoo.com.cn
  26. *@version0.1
  27. */
  28. public class GooglePageRank{
  30. //googlepagerank服务器ip地址列表（最近google小气了很多，反复查询一个封ip）
  31. final static String[]GoogleServiceIP= new String[]{ "64.233.161.100" ,
  32. "64.233.161.101" , "64.233.183.91" , "64.233.189.44" , "66.102.1.103" ,
  33. "66.102.9.115" , "66.249.89.83" , "66.249.91.99" , "66.249.93.190" };
  35. //google用识别标记
  36. final static private int GOOGLE_MAGIC= 0xE6359A60 ;
  38. //ch数值混合器
  39. private class CHMix{
  41. int a;
  43. int b;
  45. int c;
  47. public CHMix(){
  48. this ( 0 , 0 , 0 );
  49. }
  51. public CHMix( int a, int b, int c){
  52. this .a=a;
  53. this .b=b;
  54. this .c=c;
  55. }
  56. }
  58. /**
  59. *按google要求混合成ch数据
  60. *
  61. *@parammix
  62. */
  63. private static void mix( final CHMixmix){
  64. mix.a-=mix.b;
  65. mix.a-=mix.c;
  66. mix.a^=mix.c>> 13 ;
  67. mix.b-=mix.c;
  68. mix.b-=mix.a;
  69. mix.b^=mix.a<< 8 ;
  70. mix.c-=mix.a;
  71. mix.c-=mix.b;
  72. mix.c^=mix.b>> 13 ;
  73. mix.a-=mix.b;
  74. mix.a-=mix.c;
  75. mix.a^=mix.c>> 12 ;
  76. mix.b-=mix.c;
  77. mix.b-=mix.a;
  78. mix.b^=mix.a<< 16 ;
  79. mix.c-=mix.a;
  80. mix.c-=mix.b;
  81. mix.c^=mix.b>> 5 ;
  82. mix.a-=mix.b;
  83. mix.a-=mix.c;
  84. mix.a^=mix.c>> 3 ;
  85. mix.b-=mix.c;
  86. mix.b-=mix.a;
  87. mix.b^=mix.a<< 10 ;
  88. mix.c-=mix.a;
  89. mix.c-=mix.b;
  90. mix.c^=mix.b>> 15 ;
  91. }
  93. /**
  94. *获得ch数值混合器
  95. *
  96. *@return
  97. */
  98. public static CHMixgetInnerCHMix(){
  99. return new GooglePageRank(). new CHMix();
  100. }
  102. /**
  103. *通过url获得googlech(google数据库针对页面的全球唯一标识)
  104. *
  105. *@paramurl
  106. *@return
  107. */
  108. public static StringGoogleCH( final Stringurl){
  109. //格式化为google要求的info:url模式
  110. StringnUrl=String.format( "info:%s" , new Object[]{url});
  111. //获得新url字符串格式
  112. char []urls=nUrl.toCharArray();
  113. //获得新url长度
  114. int length=urls.length;
  116. //获得一个ch数值混合器
  117. CHMixchMix=GooglePageRank.getInnerCHMix();
  118. //为c注入google识别标识
  119. chMix.c=GOOGLE_MAGIC;
  121. //为a、b项注入google要求的初始标识
  122. chMix.a=chMix.b= 0x9E3779B9 ;
  124. int k= 0 ;
  126. int len=length;
  128. while (len>= 12 ){
  130. chMix.a+=( int )(urls[k+ 0 ]+(urls[k+ 1 ]<< 8 )
  131. +(urls[k+ 2 ]<< 16 )+(urls[k+ 3 ]<< 24 ));
  132. chMix.b+=( int )(urls[k+ 4 ]+(urls[k+ 5 ]<< 8 )
  133. +(urls[k+ 6 ]<< 16 )+(urls[k+ 7 ]<< 24 ));
  134. chMix.c+=( int )(urls[k+ 8 ]+(urls[k+ 9 ]<< 8 )
  135. +(urls[k+ 10 ]<< 16 )+(urls[k+ 11 ]<< 24 ));
  136. //获得混合运算后的数据
  137. GooglePageRank.mix(chMix);
  138. k+= 12 ;
  139. len-= 12 ;
  140. }
  141. chMix.c+=length;
  143. //产生googlech的11位标识
  144. switch (len){
  145. case 11 :
  146. chMix.c+=( int )(urls[k+ 10 ]<< 24 );
  147. case 10 :
  148. chMix.c+=( int )(urls[k+ 9 ]<< 16 );
  149. case 9 :
  150. chMix.c+=( int )(urls[k+ 8 ]<< 8 );
  151. case 8 :
  152. chMix.b+=( int )(urls[k+ 7 ]<< 24 );
  153. case 7 :
  154. chMix.b+=( int )(urls[k+ 6 ]<< 16 );
  155. case 6 :
  156. chMix.b+=( int )(urls[k+ 5 ]<< 8 );
  157. case 5 :
  158. chMix.b+=( int )(urls[k+ 4 ]);
  159. case 4 :
  160. chMix.a+=( int )(urls[k+ 3 ]<< 24 );
  161. case 3 :
  162. chMix.a+=( int )(urls[k+ 2 ]<< 16 );
  163. case 2 :
  164. chMix.a+=( int )(urls[k+ 1 ]<< 8 );
  165. case 1 :
  166. chMix.a+=( int )(urls[k+ 0 ]);
  167. break ;
  168. default :
  169. break ;
  170. }
  171. //获得混合运算后的数据
  172. GooglePageRank.mix(chMix);
  173. //获得未修订的CH
  174. Stringtch=String.valueOf(chMix.c);
  175. //矫正差值后反馈正确CH
  176. return String
  177. .format( "6%s" , new Object[]{tch.length()< 10 ?( "-" +tch)
  178. .intern():tch});
  179. }
  181. /**
  182. *正则匹配pagerank结果
  183. *
  184. *@paramvalue
  185. *@return
  186. */
  187. private static StringMatchRank( final Stringvalue){
  188. Patternpattern=Pattern.compile( "Rank_1:[0-9]:([0-9]+)" );
  189. Matchermatcher=pattern.matcher(value);
  190. if (matcher.find()){
  191. return matcher.group( 1 );
  192. }
  193. return "0" ;
  194. }
  196. /**
  197. *获得指定页面的googlepagerank值
  198. *
  199. *@paramurl
  200. *@return
  201. */
  202. public static StringGooglePR( final Stringurl){
  203. Stringrip=GoogleServiceIP[ new Random()
  204. .nextInt(GoogleServiceIP.length)];
  205. return GooglePR(url,rip);
  206. }
  208. /**
  209. *以指定的google服务器获得指定页面的googlepagerank值
  210. *
  211. *@paramurl
  212. *@paramip
  213. *@return
  214. */
  215. public static StringGooglePR( final Stringurl, final Stringip){
  216. //产生查询用唯一标识
  217. Stringchecksum=GoogleCH(url);
  218. //产生查询用url
  219. StringqueryUrl=String
  220. .format(
  221. "http://%s/search?client=navclient-auto&ch=%s&features=Rank&q=info:%s" ,
  222. new Object[]{ip,checksum,url});
  224. Stringresponse;
  225. try {
  226. response=SimpleWebClient.getRequestHttp(queryUrl);
  227. } catch (IOExceptione){
  228. response= "" ;
  229. }
  230. if (response.length()== 0 ){
  231. return "0" ;
  232. } else {
  233. return GooglePageRank.MatchRank(response);
  234. }
  235. }
  237. }

SimpleWebClient.java

  1. package org.loon.test;
  3. import java.io.BufferedInputStream;
  4. import java.io.ByteArrayOutputStream;
  5. import java.io.IOException;
  6. import java.io.InputStream;
  7. import java.io.InputStreamReader;
  8. import java.io.OutputStreamWriter;
  9. import java.net.HttpURLConnection;
  10. import java.net.URL;
  11. import java.util.HashMap;
  12. import java.util.Iterator;
  13. import java.util.Map;
  14. import java.util.Set;
  15. import java.util.Map.Entry;
  17. import sun.misc.BASE64Encoder;
  19. /**
  20. *Copyright2008
  21. *
  22. *LicensedundertheApacheLicense,Version2.0(the"License");youmaynot
  23. *usethisfileexceptincompliancewiththeLicense.Youmayobtainacopyof
  24. *theLicenseat
  25. *
  26. *http://www.apache.org/licenses/LICENSE-2.0
  27. *
  28. *Unlessrequiredbyapplicablelaworagreedtoinwriting,software
  29. *distributedundertheLicenseisdistributedonan"ASIS"BASIS,WITHOUT
  30. *WARRANTIESORCONDITIONSOFANYKIND,eitherexpressorimplied.Seethe
  31. *Licenseforthespecificlanguagegoverningpermissionsandlimitationsunder
  32. *theLicense.
  33. *
  34. *@projectloonframework
  35. *@authorchenpeng
  36. *@email：ceponline@yahoo.com.cn
  37. *@version0.1
  38. */
  39. public class SimpleWebClient{
  41. /**
  42. *向指定url发送请求并获得响应数据
  43. *
  44. *@paramurlString
  45. *@return
  46. *@throwsIOException
  47. */
  48. public static StringgetRequestHttp(StringurlString) throws IOException{
  49. return getRequestHttp(urlString, "utf-8" );
  50. }
  52. /**
  53. *向指定url发送请求并获得响应数据
  54. *
  55. *@paramurlString
  56. *@paramencoding
  57. *@return
  58. *@throwsIOException
  59. */
  60. public static StringgetRequestHttp(StringurlString,Stringencoding)
  61. throws IOException{
  62. return getRequestHttp(urlString,encoding, null , 5000 );
  63. }
  65. /**
  66. *向指定url发送请求并获得响应数据
  67. *
  68. *@paramurlString
  69. *@paramencoding
  70. *@paramparameter
  71. *@return
  72. *@throwsIOException
  73. */
  74. public static StringgetRequestHttp( final StringurlString,
  75. final Stringencoding, final Mapparameter, final int timeout)
  76. throws IOException{
  78. StringnURL=(urlString.startsWith( "http://" )||urlString
  79. .startsWith( "https://" ))?urlString:( "http:" +urlString)
  80. .intern();
  82. Stringuser= null ;
  83. Stringpassword= null ;
  84. Stringmethod= "GET" ;
  85. Stringpost= null ;
  86. Stringdigest= null ;
  88. StringresponseContent= "ERROR" ;
  90. boolean foundRedirect= false ;
  92. Mapheaders= new HashMap();
  94. if (parameter!= null ){
  95. SetentrySet=parameter.entrySet();
  97. for (Iteratorit=entrySet.iterator();it.hasNext();){
  98. Entryheader=(Entry)it.next();
  99. Stringkey=(String)header.getKey();
  100. Stringvalue=(String)header.getValue();
  101. if ( "user" .equals(key)){
  102. user=value;
  103. } else if ( "pass" .equals(key)){
  104. password=value;
  105. } else if ( "method" .equals(key)){
  106. method=value;
  107. } else if ( "post" .equals(key)){
  108. post=value;
  109. } else {
  110. headers.put(key,value);
  111. }
  112. }
  113. }
  114. URLurl= new URL(nURL);
  116. if (user!= null &&password!= null ){
  117. BASE64Encoderbase64= new BASE64Encoder();
  118. digest= "Basic"
  119. +base64.encode((user+ ":" +password).getBytes());
  120. }
  122. do {
  124. HttpURLConnectionurlConnection=(HttpURLConnection)url
  125. .openConnection();
  126. //添加访问授权
  127. if (digest!= null ){
  128. urlConnection.setRequestProperty( "Authorization" ,digest);
  129. }
  130. urlConnection.setDoOutput( true );
  131. urlConnection.setDoInput( true );
  132. urlConnection.setUseCaches( false );
  133. urlConnection.setInstanceFollowRedirects( false );
  134. urlConnection.setRequestMethod(method);
  135. if (timeout> 0 ){
  136. urlConnection.setConnectTimeout(timeout);
  137. }
  138. //模拟http头文件
  139. urlConnection.setRequestProperty( "User-Agent" , "Mozilla/4.0(compatible;MSIE7.0;)" );
  140. urlConnection.setRequestProperty( "Accept" , "image/gif,image/x-xbitmap,image/jpeg,image/pjpeg,application/x-shockwave-flash,application/msword,application/vnd.ms-excel,application/vnd.ms-powerpoint,*/*" );
  141. //追加http头文件
  142. SetheadersSet=headers.entrySet();
  143. for (Iteratorit=headersSet.iterator();it.hasNext();){
  144. Entryentry=(Entry)it.next();
  145. urlConnection.setRequestProperty((String)entry.getKey(),
  146. (String)entry.getValue());
  147. }
  149. if (post!= null ){
  150. OutputStreamWriteroutRemote= new OutputStreamWriter(
  151. urlConnection.getOutputStream());
  152. outRemote.write(post);
  153. outRemote.flush();
  154. }
  156. //获得响应状态
  157. int responseCode=urlConnection.getResponseCode();
  159. //获得返回的数据长度
  160. int responseLength=urlConnection.getContentLength();
  162. if (responseCode== 302 ){
  163. //重定向
  164. Stringlocation=urlConnection.getHeaderField( "Location" );
  165. url= new URL(location);
  166. foundRedirect= true ;
  167. } else {
  168. BufferedInputStreamin;
  169. if (responseCode== 200 ||responseCode== 201 ){
  170. in= new BufferedInputStream(urlConnection.getInputStream());
  171. } else {
  172. in= new BufferedInputStream(urlConnection.getErrorStream());
  173. }
  174. int size=responseLength==- 1 ? 4096 :responseLength;
  175. if (encoding!= null ){
  176. responseContent=SimpleWebClient.read(in,size,encoding);
  177. } else {
  178. ByteArrayOutputStreamout= new ByteArrayOutputStream();
  179. byte []bytes= new byte [size];
  180. int read;
  181. while ((read=in.read(bytes))>= 0 ){
  182. out.write(bytes, 0 ,read);
  183. }
  184. responseContent= new String(out.toByteArray());
  185. in.close();
  186. out.close();
  187. }
  188. foundRedirect= false ;
  189. }
  190. //如果重定向则继续
  191. } while (foundRedirect);
  193. return responseContent;
  194. }
  196. /**
  197. *转化InputStream为String
  198. *
  199. * @param in
  200. * @param size
  201. * @return
  202. * @throws IOException
  203. */
  204. private static Stringread( final InputStreamin, final int size,
  205. final Stringencoding) throws IOException{
  206. StringBuildersbr= new StringBuilder();
  207. int nSize=size;
  208. if (nSize== 0 ){
  209. nSize= 1 ;
  210. }
  211. char []buffer= new char [nSize];
  212. int offset= 0 ;
  213. InputStreamReaderisr= new InputStreamReader(in,encoding);
  214. while ((offset=isr.read(buffer))!=- 1 ){
  215. sbr.append(buffer, 0 ,offset);
  216. }
  217. in.close();
  218. isr.close();
  219. return sbr.toString();
  220. }
  221. }

WebAppraise.java
  1. package org.loon.test;
  3. import java.io.IOException;
  5. /**
  6. *Copyright2008
  7. *
  8. *LicensedundertheApacheLicense,Version2.0(the"License");youmaynot
  9. *usethisfileexceptincompliancewiththeLicense.Youmayobtainacopyof
  10. *theLicenseat
  11. *
  12. *http://www.apache.org/licenses/LICENSE-2.0
  13. *
  14. *Unlessrequiredbyapplicablelaworagreedtoinwriting,software
  15. *distributedundertheLicenseisdistributedonan"ASIS"BASIS,WITHOUT
  16. *WARRANTIESORCONDITIONSOFANYKIND,eitherexpressorimplied.Seethe
  17. *Licenseforthespecificlanguagegoverningpermissionsandlimitationsunder
  18. *theLicense.
  19. *
  20. *@projectloonframework
  21. *@authorchenpeng
  22. *@email：ceponline@yahoo.com.cn
  23. *@version0.1
  24. */
  25. public class WebAppraise{
  27. private StringgoogleSum;
  29. private StringbaiduSum;
  31. private StringmsnSum;
  33. private StringaltaVistaSum;
  35. private StringallTheWebSum;
  37. private StringyahooSum;
  39. private StringtestURL;
  41. public WebAppraise( final Stringurl){
  43. if (url!= null &&! "" .equals(url)){
  44. this .testURL=url.trim();
  45. if ( this .testURL.startsWith( "http://" )){
  46. this .testURL= this .testURL.substring( 7 );
  47. }
  48. if ( this .testURL.startsWith( "https://" )){
  49. this .testURL= this .testURL.substring( 8 );
  50. }
  51. } else {
  52. throw new RuntimeException( "urlisNULL!" );
  53. }
  55. }
  57. /**
  58. *分析指定链接结果，并返回整型数值
  59. *
  60. *@paramsearchURL
  61. *@paramanchor
  62. *@paramtrail
  63. *@return
  64. */
  65. private static int getLinks( final StringsearchURL, final Stringanchor,
  66. final Stringtrail){
  67. int count= 0 ;
  68. StringserverResponse;
  70. try {
  71. //我国特色……
  72. if (searchURL.startsWith( "http://www.baidu.com" )){
  73. //永不离休的gb2312同志(-_-||)
  74. serverResponse=SimpleWebClient.getRequestHttp(searchURL,
  75. "gb2312" );
  76. } else {
  77. serverResponse=SimpleWebClient.getRequestHttp(searchURL);
  78. }
  79. } catch (IOExceptione){
  80. serverResponse=e.getMessage();
  81. }
  83. int pos=serverResponse.indexOf(anchor);
  84. if (pos> 1 ){
  85. serverResponse=serverResponse.substring(pos+anchor.length());
  86. pos=serverResponse.indexOf(trail);
  87. Stringvalue=serverResponse.substring( 0 ,pos).trim();
  88. value=value.replace( "," , "" );
  89. value=value.replace( "." , "" );
  90. count=Integer.parseInt(value);
  91. }
  92. return count;
  93. }
  95. public StringgetAllTheWebSite(){
  96. return getAllTheWebSite( false );
  97. }
  99. public StringgetAllTheWebSite( boolean isDomain){
  100. try {
  101. StringallTheWeb;
  102. if (isDomain){
  103. allTheWeb= "http://www.alltheweb.com/search?cat=web&cs=utf8&rys=0&itag=crv&_sb_lang=any&q=linkdomain%3A"
  104. + this .testURL;
  105. } else {
  106. allTheWeb= "http://www.alltheweb.com/search?cat=web&cs=utf-8&q=link%3Ahttp%3A%2F%2F"
  107. + this .testURL+ "&_sb_lang=any" ;
  108. }
  109. allTheWebSum= ""
  110. +getLinks(allTheWeb, "<spanclass=/"ofSoMany/">" ,
  111. "</span>" );
  112. } catch (Exceptionex){
  113. allTheWebSum=ex.getMessage();
  114. }
  115. return allTheWebSum;
  116. }
  118. public StringgetAltaVistaSite(){
  119. return getAltaVistaSite( false );
  120. }
  122. public StringgetAltaVistaSite( boolean isDomain){
  123. try {
  124. StringaltaVista;
  125. if (isDomain){
  126. altaVista= "http://www.altavista.com/web/results?itag=ody&q=link%3A"
  127. + this .testURL+ "&kgs=0&kls=0" ;
  128. } else {
  129. altaVista= "http://www.altavista.com/web/results?itag=ody&kgs=0&kls=0&q=site%3A"
  130. + this .testURL;
  131. }
  132. altaVistaSum= "" +getLinks(altaVista, "AltaVistafound" , "" );
  133. } catch (Exceptionex){
  134. altaVistaSum=ex.getMessage();
  135. }
  136. return altaVistaSum;
  137. }
  139. public StringgetGooglePR(){
  140. return GooglePageRank.GooglePR( this .testURL);
  141. }
  143. public StringgetGoogleSite(){
  144. return getGoogleSite( false );
  145. }
  147. public StringgetGoogleSite( final boolean isDomian){
  148. try {
  149. Stringgoogle;
  150. //反向链接
  151. if (isDomian){
  152. google= "http://www.google.com/search?hl=en&q=link%3A"
  153. + this .testURL;
  154. } else {
  155. google= "http://www.google.com/search?hl=en&q=site%3A"
  156. + this .testURL+ "&btnG=Google+Search&aq=f&oq=" ;
  157. }
  158. googleSum= "" +getLinks(google, "about<b>" , "</b>" );
  159. } catch (Exceptionex){
  160. googleSum=ex.getMessage();
  161. }
  162. return googleSum;
  163. }
  165. public StringgetBaiduSite(){
  166. return getBaiduSite( false );
  167. }
  169. public StringgetBaiduSite( final boolean isDomian){
  170. try {
  171. Stringbaidu;
  172. if (isDomian){
  173. baidu= "http://www.baidu.com/s?wd=domain%3A" + this .testURL
  174. + "&cl=3" ;
  175. } else {
  176. baidu= "http://www.baidu.com/s?wd=site%3A" + this .testURL;
  177. }
  178. baiduSum= "" +getLinks(baidu, "找到相关网页" , "篇" );
  179. } catch (Exceptionex){
  180. Stringbaidu;
  181. if (isDomian){
  182. baidu= "http://www.baidu.com/s?wd=domain%3A" + this .testURL
  183. + "&cl=3" ;
  184. } else {
  185. baidu= "http://www.baidu.com/s?wd=site%3A" + this .testURL;
  186. }
  187. baiduSum= "" +getLinks(baidu, "找到相关网页约" , "篇" );
  188. }
  189. return baiduSum;
  190. }
  192. public StringgetYahooSite(){
  193. return getYahooSite( false );
  194. }
  196. public StringgetYahooSite( final boolean isDomian){
  197. try {
  198. Stringyahoo;
  199. if (isDomian){
  200. yahoo= "http://sitemap.cn.yahoo.com/search?p=" + this .testURL
  201. + "&bwm=i" ;
  202. yahooSum= "" +getLinks(yahoo, "<strong>" , "</strong>" );
  203. } else {
  204. yahoo= "http://www.yahoo.cn/s?p=site%3A" + this .testURL
  205. + "&pid=hp&v=web" ;
  206. yahooSum= "" +getLinks(yahoo, "找到相关网页约" , "条" );
  207. }
  209. } catch (Exceptionex){
  210. yahooSum=ex.getMessage();
  211. }
  212. return yahooSum;
  213. }
  215. public StringgetMsnSite(){
  216. return getMsnSite( false );
  217. }
  219. public StringgetMsnSite( boolean isDomain){
  220. try {
  221. Stringmsn;
  222. if (isDomain){
  223. msn= "http://cnweb.search.live.com/results.aspx?q=link%3A"
  224. + this .testURL+ "&mkt=zh-cn&scope=&FORM=LIVSO" ;
  225. } else {
  226. msn= "http://cnweb.search.live.com/results.aspx?q=site%3A"
  227. + this .testURL+ "&go=&form=QBRE" ;
  228. }
  229. msnSum= "" +getLinks(msn, "共" , "条搜索结果" );
  230. } catch (Exceptionex){
  231. msnSum=ex.getMessage();
  232. }
  233. return msnSum;
  234. }
  236. public StringgetTestURL(){
  237. return testURL;
  238. }
  240. }

Test.java
  1. packageorg.loon.test;
  3. /**
  4. *Copyright2008
  5. *
  6. *LicensedundertheApacheLicense,Version2.0(the"License");youmaynot
  7. *usethisfileexceptincompliancewiththeLicense.Youmayobtainacopyof
  8. *theLicenseat
  9. *
  10. *http://www.apache.org/licenses/LICENSE-2.0
  11. *
  12. *Unlessrequiredbyapplicablelaworagreedtoinwriting,software
  13. *distributedundertheLicenseisdistributedonan"ASIS"BASIS,WITHOUT
  14. *WARRANTIESORCONDITIONSOFANYKIND,eitherexpressorimplied.Seethe
  15. *Licenseforthespecificlanguagegoverningpermissionsandlimitationsunder
  16. *theLicense.
  17. *
  18. *@projectloonframework
  19. *@authorchenpeng
  20. *@email：ceponline@yahoo.com.cn
  21. *@version0.1
  22. */
  23. public class Test{
  25. public static void main(String[]args){
  27. WebAppraiseappraise= new WebAppraise( "http://blog.csdn.net/cping1982" );
  29. System. out .println( "GooglePagerRank值：" +appraise.getGooglePR());
  30. System. out .println( "google收录：" +appraise.getGoogleSite());
  31. System. out .println( "google反向收录：" +appraise.getGoogleSite( true ));
  32. System. out .println( "yahoo收录：" +appraise.getYahooSite());
  33. System. out .println( "yahoo反向收录：" +appraise.getYahooSite( true ));
  34. System. out .println( "baidu收录：" +appraise.getBaiduSite());
  35. System. out .println( "baidu反向收录：" +appraise.getBaiduSite( true ));
  36. System. out .println( "msn收录：" +appraise.getMsnSite());
  37. System. out .println( "msn反向收录：" +appraise.getMsnSite( true ));
  38. System. out .println( "AllTheWeb收录：" +appraise.getAllTheWebSite());
  39. System. out .println( "AllTheWeb反向收录：" +appraise.getAllTheWebSite( true ));
  40. System. out .println( "AltaVista收录：" +appraise.getAltaVistaSite());
  41. System. out .println( "AltaVista反向收录：" +appraise.getAltaVistaSite( true ));
  43. }
  44. }

检测 http://blog.csdn.net/cping1982 运行结果如下图：

Java版PageRank及网站收录情况查询代码


源码下载地址： http://download.csdn.net/source/929348

Java版PageRank及网站收录情况查询代码


更多文章、技术交流、商务合作、联系博主

微信扫码或搜索：z360901061

微信扫一扫加我为好友

QQ号联系： 360901061

您的支持是博主写作最大的动力，如果您喜欢我的文章，感觉我的文章对您有帮助，请用微信扫描下面二维码支持博主2元、5元、10元、20元等您想捐的金额吧，狠狠点击下面给点支持吧，站长非常感激您！手机微信长按不能支付解决办法：请将微信支付二维码保存到相册，切换到微信，然后点击微信右上角扫一扫功能，选择支付二维码完成支付。

【本文对您有帮助就好】元

您的支持是博主写作最大的动力，如果您喜欢我的文章，感觉我的文章对您有帮助，请用微信扫描上面二维码支持博主2元、5元、10元、自定义金额等您想捐的金额吧，站长会非常 感谢您的哦！！！

发表我的评论
最新评论 总共0条评论