Shell Programming and Scripting

$ 
$ # show the contents of "input.txt"
$ cat -n input.txt
     1  <b> ODGOVORNOST............. : <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=CB&run=yes&SS1=&quo t;Tauber,%20Daniel%20A.&quot;">Tauber, Daniel A.</a> - zbiratelj</b>                        
     2  <b> NASLOV.................. : #The #complete Linux kit</b>                                                                     
     3  <b> IMPRESUM................ : San Francisco [etc.] : Sybex, 1995</b>                                                           
     4  <b> FIZIČNI OPIS............ : XXIII, 419 str. ; 23 cm + CD-ROM</b>                                                             
     5  <b> ISBN.................... : 0-7821-1669-8</b>                                                                                
     6  <b> PREDMETNE OZNAKE........ : <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;racunalnistvo&quot;">računalništvo</a> // <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;operacijski%20sistemi&quot;">operacijski sistemi</a></b>                                                                                                                         
     7  <b>// <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;linux&quot;">linux</a> // <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;unix&quot;">unix</a> // <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;programska%20oprema&quot;">programska oprema</a> // <a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;Internet&quot;">Internet</a> //</b>
     8  <b><a href="http://cobiss2.izum.si/scripts/cobiss?ukaz=FFRM&mode=5&id=2047435453134563&PF1=AU&PF2=TI&PF3=PY&PF4=KW&CS=a&PF5=SU&run=yes&SS5=&quo t;komercialni%20sistemi&quot;">komercialni sistemi</a></b>
     9  <b> UDK..................... : 681.3.06, 519.68</b>
    10  <b> UDK ZA STATISTIKO....... : 62+66/69</b>
    11  <b> VRSTA GRADIVA........... : monografska publikacija, tekstovno gradivo,</b>
    12  <b>tiskano</b>
    13  <b> COBISS.SI-ID............ : 2952</b>
    14
$
$ # run the script
$ perl -ne '{
>   /^<b> FIZI.*?(\S+)<\/b>/ and $nvd = $1;
>   /^<b> ODGOVORNOST.*?>(.*?), (.*?)<\/a>.*?<\/b>/ and $avt = "$2 $1";
>   /^<b> NASLOV.*?: (.*?)<\/b>/ and $nsl = $1; $nsl =~ s/#//g;
>   /^<b> IMPRESUM.*?: (.*?)<\/b>/ and $kzl = $1; ($krj,$zlz,$lto) = split(/ : |, /, $kzl); $krj =~ s/ \[etc.\]//g;
>   /^<b> COBISS.*?: (\d+)<\/b>/ and $cbs = $1;
>   /^<b> ISBN.*?: (\S+)<\/b>/ and $isb = $1;
> }
> END {
>   printf("{{Navedi %s\n|avtor= %s\n|naslov= %s\n|kraj= %s\n", $nvd, $avt, $nsl, $krj);
>   printf("|zalozba= %s\n|leto= %s\n|cobiss_id= %s\n|isbn= %s\n}}\n", $zlz, $lto, $cbs, $isb);
> }' input.txt
{{Navedi CD-ROM
|avtor= Daniel A. Tauber
|naslov= The complete Linux kit
|kraj= San Francisco
|zalozba= Sybex
|leto= 1995
|cobiss_id= 2952
|isbn= 0-7821-1669-8
}}
$
$

perl -ne '{
  /^<b> FIZI.*?(\S+)<\/b>/ and $nvd = $1;
  /^<b> AVTOR.*?>(.*?), (.*?)<\/a>.*?<\/b>/ and $avt = "$2 $1";
  /^<b> ODGOVORNOST.*?>(.*?), (.*?)<\/a>.*?<\/b>/ and $odg = "$2 $1";
  /^<b> NASLOV.*?: (.*?)<\/b>/ and $nsl = $1; $nsl =~ s/#//g;
  /^<b> IMPRESUM.*?: (.*?)<\/b>/ and $kzl = $1; ($krj,$zlz,$lto) = split(/ : |, /, $kzl); $krj =~ s/ \[etc.\]//g;
  /^<b> COBISS.*?: (\d+)<\/b>/ and $cbs = $1;
  /^<b> ISBN.*?: (\S+)<\/b>/ and $isb = $1;
}
END {
  printf("{{Navedi %s\n|avtor= %s\n|naslov= %s\n|kraj= %s\n", $nvd, ($avt or $odg), $nsl, $krj);
  printf("|zalozba= %s\n|leto= %s\n|cobiss_id= %s\n|isbn= %s\n}}\n", $zlz, $lto, $cbs, $isb);
}' <input_file>