欢迎来到天天文库
浏览记录
ID:34723835
大小:51.39 KB
页数:4页
时间:2019-03-10
《java爬虫获取网页url源码》由会员上传分享,免费在线阅读,更多相关内容在工程资料-天天文库。
1、packagefileAndStringOperate;importjava.io.BufferedReader;importjava.io.File;importjava.io.FileOutputStream;importjava.io.FileReader;importjava.io.FileWriter;importjava.io.IOException;importjava.io.OutputStream;publicclassReadFileToString{publicstaticvoidmain
2、(String[]args)throwsIOException{StringfileData=readtxt("D:\IR\1\JAVA网络爬虫.txt");CountRelatedDocument(fileData);//MyWebRec[]myWebRec=newMyWebRec[2000];ClassifyURL(fileData);}privatestaticStringreadtxt(StringfilePath)throwsIOException{BufferedReaderbr=newBuf
3、feredReader(newFileReader(filePath));Stringstr="";Stringr=br.readLine();while(r!=null){str+=r+"";r=br.readLine();}returnstr;}privatestaticchar[][]readtxtToChar(StringfilePath)throwsIOException{char[][]data=null;intcurrentline=0;BufferedReaderbr=newBuffered
4、Reader(newFileReader(filePath));Stringstr="";Stringr=br.readLine();while(r!=null){str+=r+"";data[currentline++]=str.toCharArray();r=br.readLine();}returndata;}privatestaticintCountRelatedDocument(StringfileData){intcntRelated=0;intcurrentLine=1;intbaiduCnt
5、=0;intbingCnt=0;intsogouCnt=0;int_360Cnt=0;intState=0;booleanbaiduY[]=newboolean[51];booleanbingY[]=newboolean[51];booleansogouY[]=newboolean[51];boolean_360Y[]=newboolean[51];char[]fileChar=fileData.toCharArray();for(inti=0;i6、r[i]=='#'&&fileChar[i+1]=='*'){State++;System.out.println("分点:"+currentLine);}if(fileChar[i]=='')currentLine++;if(currentLine%3==0){if(fileChar[i]=='Y'7、8、fileChar[i]=='y'){if(State==1){baiduCnt++;baiduY[currentLine/3]=true;}elseif(State==2){bingCnt++;bingY[9、currentLine/3-50]=true;//System.out.println(currentLine/3-50);}elseif(State==3){sogouCnt++;sogouY[currentLine/3-100]=true;}elseif(State==4){_360Cnt++;_360Y[currentLine/3-150]=true;}cntRelated++;}}}try{CaculatePR(baiduY,bingY,_360Y,sogouY,cntRelated);}catch(E10、xceptione){e.getMessage();}System.out.println("cntRelated="+cntRelated);System.out.println("baiduCnt="+baiduCnt);System.out.println("bingCnt="+bingCnt);System.out.println("sohuCnt="+sogouCnt);Sy
6、r[i]=='#'&&fileChar[i+1]=='*'){State++;System.out.println("分点:"+currentLine);}if(fileChar[i]=='')currentLine++;if(currentLine%3==0){if(fileChar[i]=='Y'
7、
8、fileChar[i]=='y'){if(State==1){baiduCnt++;baiduY[currentLine/3]=true;}elseif(State==2){bingCnt++;bingY[
9、currentLine/3-50]=true;//System.out.println(currentLine/3-50);}elseif(State==3){sogouCnt++;sogouY[currentLine/3-100]=true;}elseif(State==4){_360Cnt++;_360Y[currentLine/3-150]=true;}cntRelated++;}}}try{CaculatePR(baiduY,bingY,_360Y,sogouY,cntRelated);}catch(E
10、xceptione){e.getMessage();}System.out.println("cntRelated="+cntRelated);System.out.println("baiduCnt="+baiduCnt);System.out.println("bingCnt="+bingCnt);System.out.println("sohuCnt="+sogouCnt);Sy
此文档下载收益归作者所有