firefox_website_02.pl

use strict;
use warnings;

# Initialize variables to store extracted URLs
my @google_maps_urls;

# Process each HTML file (1.html to 25.html)
for my $file_number (1..25) {
    my $input_file = "${file_number}.html";

    # Open the current input file for reading
    open my $input_fh, '<', $input_file or warn "Cannot open input file '$input_file': $!";

    my $previous_line = '';
    my $current_line = '';
    my $extracting = 0;

    # Read each line and look for URLs
    while (my $line = <$input_fh>) {
        chomp $line;

        # Check if the current line contains "+82"
        if ($current_line =~ /\+82/) {
            # Check if the next line contains "Website"
            if ($line =~ /Website/) {
                $extracting = 1;
                push @google_maps_urls, "$input_file, $current_line";
            }
        }

        # Continue extracting 3 more lines if we're in an extraction state
        if ($extracting) {
            push @google_maps_urls, "$input_file, $line";
            if (@google_maps_urls % 4 == 0) {
                $extracting = 0;
            }
        }

        # Store the current line for the next iteration
        $previous_line = $current_line;
        $current_line = $line;
    }

    # Close the current input file
    close $input_fh;
}

# Save the extracted URLs to a file
my $output_file = 'firefox_website_02.txt';
open my $output_fh, '>', $output_file or die "Cannot open output file '$output_file': $!";

foreach my $url (@google_maps_urls) {
    print $output_fh "$url\n";
}

# Close the output file
close $output_fh;

print "Extraction complete. Extracted 4 lines (including +82 and Website) are saved in '$output_file'\n";