java.util.Scanner未到文件结尾,hasNext跟hasNextLine()返回false,使用默认分割符。import java.io.*;
public class Scans
{
public static void main(String[] args)throws FileNotFoundException{
PrintWriter pw=new PrintWriter(new File("ttttt.txt"));
Scanner sc=new Scanner(new File(Scans.class.getResource("").getPath()+"rt1.txt"));
//sc.useDelimiter("\\r*\\n");
while(sc.hasNext()){
pw.print(sc.nextLine()+"$$$$$$$");
System.out.println(sc.hasNext());
if(sc.hasNext())pw.print("\n");
}
pw.flush();
}
}
//下面是r1.txt
/**
Extraction Rules (HTML/Web)
Target Code
Type
Page Encoding
Query Method
Login Method
Portal Address :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0001&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0002&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0004&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0005&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0006&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0007&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0008&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0009&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0010&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0011&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0011&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0012&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0013&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0014&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0015&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0016&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0017&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0018&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0019&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0022&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0023&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0023&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0024&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0025&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0026&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0027&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0029&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0030&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0031&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0003&dbcode=CLKM&json=&t=%/~
List Regex :/%(?#title)(?i)href="([^"]+)"[^>]*>[^<>]+</a></p>%/~ :/%(?i)setFrame\('([^']+)'\)%/~ :/%[post](?#post)(?#title)(?#accept)(?i)^(?=[\w\W]*?(?:<form[^>]*action="|<PARENT_URL>:\s*)(?<action>[^"<>\s]*)["<])(?=[\w\W]*?name="drpField"[^>]*VALUE="(?<drpField>[^"]*)"|[\W\w])(?=[\w\W]*?name="__EVENTVALIDATION"[^>]*VALUE="(?<__EVENTVALIDATION>[^"]*)"|[\W\w])(?=[\w\W]*?name="__VIEWSTATE"[^>]*VALUE="(?<__VIEWSTATE>[^"]*)"|[\W\w])[\w\W]*href="javascript:KnsPager.go\((?<__CALLBACKPARAM>\d+),'(?<__CALLBACKID>[^']+)'\)" >Next</a>%/~
Data Regex :/%(?#title)(?i)href="([^"]+)"[^>]*>\s*[^<>]+</a>\s*</td%/~
Sublink Regex
Metadata Regex title:/%(?i)href="[^"]+"[^>]*>\s*([^<>]+)</a>\s*</td[^>]*<%/~ author:/%(?i)\【?Author\s*in\s*Chinese\】?(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>(\;)(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>(\;))?(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>)?(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>(\;))?(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>)?%/~ datepublished:/%(?i)Author\s*information[\w\W]+?(\d{4})%/~ Publisher:/%(?i)href="[^"]+"[^>]*>([^<>]+)</a></p>%/~
Result:0 Status:Running Display top:
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GGUDU
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GGZSU
List URL -- size = 2
start...
access : http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0001&dbcode=CLKM&json=&t=
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GANHU
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GAHCC
List URL -- size = 2
access : http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0002&dbcode=CLKM&json=&t=
©2009, Serials Solutions All rights reserved
loadimg
*/
public class Scans
{
public static void main(String[] args)throws FileNotFoundException{
PrintWriter pw=new PrintWriter(new File("ttttt.txt"));
Scanner sc=new Scanner(new File(Scans.class.getResource("").getPath()+"rt1.txt"));
//sc.useDelimiter("\\r*\\n");
while(sc.hasNext()){
pw.print(sc.nextLine()+"$$$$$$$");
System.out.println(sc.hasNext());
if(sc.hasNext())pw.print("\n");
}
pw.flush();
}
}
//下面是r1.txt
/**
Extraction Rules (HTML/Web)
Target Code
Type
Page Encoding
Query Method
Login Method
Portal Address :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0001&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0002&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0004&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0005&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0006&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0007&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0008&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0009&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0010&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0011&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0011&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0012&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0013&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0014&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0015&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0016&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0017&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0018&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0019&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0022&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0023&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0023&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0024&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0025&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0026&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0027&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0029&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0030&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0031&dbcode=CLKM&json=&t=%/~ :/%http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0003&dbcode=CLKM&json=&t=%/~
List Regex :/%(?#title)(?i)href="([^"]+)"[^>]*>[^<>]+</a></p>%/~ :/%(?i)setFrame\('([^']+)'\)%/~ :/%[post](?#post)(?#title)(?#accept)(?i)^(?=[\w\W]*?(?:<form[^>]*action="|<PARENT_URL>:\s*)(?<action>[^"<>\s]*)["<])(?=[\w\W]*?name="drpField"[^>]*VALUE="(?<drpField>[^"]*)"|[\W\w])(?=[\w\W]*?name="__EVENTVALIDATION"[^>]*VALUE="(?<__EVENTVALIDATION>[^"]*)"|[\W\w])(?=[\w\W]*?name="__VIEWSTATE"[^>]*VALUE="(?<__VIEWSTATE>[^"]*)"|[\W\w])[\w\W]*href="javascript:KnsPager.go\((?<__CALLBACKPARAM>\d+),'(?<__CALLBACKID>[^']+)'\)" >Next</a>%/~
Data Regex :/%(?#title)(?i)href="([^"]+)"[^>]*>\s*[^<>]+</a>\s*</td%/~
Sublink Regex
Metadata Regex title:/%(?i)href="[^"]+"[^>]*>\s*([^<>]+)</a>\s*</td[^>]*<%/~ author:/%(?i)\【?Author\s*in\s*Chinese\】?(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>(\;)(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>(\;))?(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>)?(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>(\;))?(?:(?:<(?!/p)[^>]*>|\s)*<a[^>]*>([^<>]*?)</a>)?%/~ datepublished:/%(?i)Author\s*information[\w\W]+?(\d{4})%/~ Publisher:/%(?i)href="[^"]+"[^>]*>([^<>]+)</a></p>%/~
Result:0 Status:Running Display top:
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GGUDU
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GGZSU
List URL -- size = 2
start...
access : http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0001&dbcode=CLKM&json=&t=
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GANHU
List URL -- http://eng.oversea.cnki.net/law/navi/CLKMissue.aspx?dbcode=CLKM&dbPrefix=CLKT&pykm=GAHCC
List URL -- size = 2
access : http://eng.oversea.cnki.net/law/navi/clkb_ifmlist.aspx?navitype=area&navi=0002&dbcode=CLKM&json=&t=
©2009, Serials Solutions All rights reserved
loadimg
*/
pw.print(sc.nextLine()+"$$$$$$$"); }试试
那你用BufferedReader & FileReader 吧
末尾最好加上pw.close();