#!/usr/bin/perl# massage Econometrics Journal TOC html page, retrieve abstractsprint "\nectjcvt v1.0\n\n";print "C F Baum  Jul 2000\n\n";use LWP::Simple;use Text::Wrap;$base="http://www.blackwellpublishers.co.uk/ectj/toc.htm";$str=get "$base";#$str=get "$base$voliss$tail" || die "Cannot open $base";$outf=">ectj.rdf";open(OUT,$outf) || die "Cannot open $outf for output";$str =~ s/\n//ig;$str =~ s/\r//ig;#(@y,@v,@i)= ($str =~ m!>(.+?) Volume (.+?), Issue (.+?)<a>!);#(@y)= ($str =~ m!href="#.+?>(.+?)</a!ig); #$y=@y;#$v=@v;#$i=@i;#print "hdr: $y\n";#for($i=0;$i<$y;$i++) { print "$i $y[$i]\n"; }#print "hdr: $y $y[0] $y[1] $y[2] $y[3]  \n";#print "hdr: $y $y[4] $y[5] $y[6] $y[7]  \n";$str =~ s!^.+descript.htm">here</a>.!!;(@iss)=split("Back to Top",$str);$iss=@iss-1;print "iss: $iss\n";$ever=0;for($m=0;$m<$iss;$m++) {$iss[$m] =~ s!</tr>!DeLiM!ig;$iss[$m] =~ s!<.+?>!!ig;$iss[$m] =~ s!&nbsp;!!ig;$iss[$m] =~ s!&#145;!'!ig;$iss[$m] =~ s!&#146;!'!ig;$iss[$m] =~ s!  ! !ig;(@item)=split("DeLiM",$iss[$m]);$item=@item;print "\niss[$m] : $item\n";$base=0;if($m>0) {$base=2};(@vref)=split(",",$item[$base]);$vref=@vref;$yr =$vref[0];$yr =~ s/ //ig;$vref[1] =~ s/Volume//ig;$vol = $vref[1];$vol =~ s/ //ig;$vref[2] =~ s/Issue //ig;$nr = $vref[2];$nr =~ s/Conference.+$/ConferenceIssue/;$nr =~ s/ //ig;print "Year: $yr\n";print "Volume: $vol\n";print "Issue: $nr\n";for($i=$base+2;$i<$item-2;$i=$i+3) {  print OUT "\nTemplate-Type: ReDIF-Article 1.0\n";$item[$i] =~ s/  / /ig;    print OUT "Title: $item[$i]\n";	   ($auv,$pp) = ($item[$i+1] =~ m!^(.+?)\(pp(.+?)\)!);$auv =~ s/  / /ig;    (@au)=split(",",$auv);    $au=@au;    for($j=0;$j<$au;$j++) {print OUT "Author-Name: $au[$j]\n"};print OUT "Journal: The Econometrics Journal\n";(@fau)=split(" ",lc $au[0]);$nf=@fau;$abst= get "http://www.blackwellpublishers.co.uk/ectj/Abstracts/$fau[$nf-1].htm";if($abst) { $abst =~ s/\n//ig;$abst =~ s/\r//ig;($ab,$kw) = ($abst =~ m!Summary(.+?)Keywords:(.+?)</td>!);$ab =~ s!<.+?>!!ig;$ab =~ s!&#145;!'!ig;$ab =~ s!&#146;!'!ig;$ab =~ s!&#150;!-!ig;$ab =~ s!&nbsp;!!ig;$kw =~ s!<.+?>!!ig;print OUT "Abstract:\n";print OUT wrap(" "," ",$ab);print OUT "\nKeywords: $kw\n";}$ever++;$pp =~ s/ //ig;    print OUT "Pages: $pp\n";print OUT "Issue: $nr\nVolume: $vol\n";print OUT "Year: $yr\n";print OUT "Handle: RePEc:ect:emjrnl:v:$vol:y:$yr:i:$nr:p:$pp\n";}}print "\n $Nr templates: $ever\n\n";exit;__END__