Shell Programming and Scripting

$ lynx -dump http://www.google.com

[1] txt1 [2]blabla [3]Other txt
[4] some text
1. http://url_of_txt1
2. http://url_of_blabla
3. http://url_of_Other_txt
4. http://url_of_some_text
...

txt1 
http://url_of_txt1

blabla
http://url_of_blabla

Other txt
http://url_of_Other_txt

some text
http://url_of_some_text

... (and so on)

#!perl

$fin = "a";

unless ( open FIN, $fin ){
  print "cannot read file $fin \n";
  exit(9);
  }

$fout = "b";

unless ( open FOUT, ">$fout" ){
  print "cannot write to file $fout \n";
  exit(9);
  }

@a_lines = <FIN>; chomp @a_lines; close FIN;

foreach $line ( @a_lines ){

  next unless ( $line =~ m/[\[\]]/ );

  ( @a_junk ) = split( /[\[]/, $line );
  foreach $junk ( @a_junk ){

    ( $key, @a_more_junk ) = split( /[\]]/, $junk );
    next unless $key;

    $aa_keys{ $key } = join ' ', @a_more_junk;
    }

  }

foreach $line ( @a_lines ){

  next if ( $line =~ m/[\[\]]/ );

  ( $key, @a_junk ) = split /\./, $line;

  printf "$aa_keys{ $key }\n";
  printf "$key.";
  printf join ' ', @a_junk;
  printf "\n\n";

  }

.


.


                                   Google.


.


     _______________________________________________________.


.


.


.


Refers.


.


   1. http://images google com/imghp?hl=en&tab=wi


   2. http://maps google com/maps?hl=en&tab=wl


   3. http://news google com/nwshp?hl=en&tab=wn


   4. http://video google com/?hl=en&tab=wv


   5. http://mail google com/mail/?hl=en&tab=wm


   6. http://www google com/intl/en/options/


   7. http://www google com/url?sa=p&pref=ig&pval=3&q=http://www google com/ig0.000000hl  0en                          ource  0iglk&usg=AFQjCNFA18XPfgb7dKnXfKz7x7g1GDH1tg


   8. https://www google com/accounts/Login?continue=http://www google com/intl/en/&hl=en


   9. http://www google com/advanced_search?hl=en


  10. http://www google com/preferences?hl=en


  11. http://www google com/language_tools?hl=en


  12. http://www google com/intl/en/ads/


  13. http://www google com/services/


  14. http://www google com/intl/en/about html


  15. http://www google com/


  16. http://www google com/intl/en/privacy html

BEGIN {
}
/^[[]/ {
  while (match($0, "^[[][0-9]*[]]") ) {
     idx=substr($0,RSTART+1, RLENGTH-2) "."
     rem=substr($0,RSTART+RLENGTH)
     match(rem, "[^[]*([[]|$)")
     name=substr(rem, RSTART,RLENGTH-1)
     if (length(rem)==(length(name)+1))
         name=substr(rem, RSTART)
     arr[idx]= name
    $0=substr(rem, RSTART+RLENGTH-1)
  }
  next
}
$1 in arr { print arr[$1] ORS $2 }