#!/usr/local/bin/perl

#
# Extracts the title of each document.  The title is contained within
# the HTML tags <title>...</title>
#
# Usage: extractTitles <inFile> <outFile>
#

#
# Read in one document at a time
#
$/ = "\n\n";


$inFile  = @ARGV[0];
$outFile = @ARGV[1];

#
# Open the files
#
open(INFILE,  "<$inFile")  || die("Couldn't open $inFile for reading\n");
open(OUTFILE, ">$outFile") || die("Couldn't open $outFile for writing\n");


while ( $doc = <INFILE> )
{
  #
  # Remove newlines
  #
  $doc =~ s#\n+# #g;
  
  #
  # Extract title
  #
  $doc =~ s#<title>(.*)</title>#$title = $1#gei;

  #
  # Remove HTML tags from the title
  #
  $title =~ s#<[^>]*>##g;

  #
  # Write the title
  #
  print(OUTFILE "$title\n");
}

close(INFILE);
close(OUTFILE);