#!/usr/bin/perl -w
use strict;
use warnings;
use File::stat;
use lib "c:/strawberry/perl/site/lib";

#This program will extract the header information in 10K and 10Q filings
#as well as file sizes.

#Specify the directory containing the files that you want to read;
#my $files_dir = 'C:\Rick Francis\Data\SEC Filings\Filing Doc';
my $files_dir = 'E:\research\audit fee models\filings\Test';
#Specify the directory containing the results/output;
#my $write_dir = 'C:\Rick Francis\Data\SEC Filings\Header Data\Revised\DataTest.txt';
my $write_dir =  'E:\research\audit fee models\filings\filenames\filenames.txt';

#Open the directory containing the files you plan to read;
opendir(my $dir_handle, $files_dir) or die "Can't open directory $!";

#Initialize file counter variable;
my $file_count = 0;

#Loop for reading each file in the input directory;
while (my $filename = readdir($dir_handle))  {
next unless -f $files_dir.'/'.$filename;
print "Processing $filename\n";

#Initialize the variable names.
my $line_count=0;
my $access_num=-99;
my $cik=-99;
my $form_type="";
my $form="";
my $report_date=-99;
my $file_date=-99;
my $name="";
#my $sic=-99;
#my $sic1=-99;
my $file_name="";
my $htm="";
my $url="";
my $slash='/';

#Open the input file;
open my $FH_IN, '<',$files_dir.'/'.$filename or die "Can't open $filename";
#Within the file loop, read each line of the current file;
while (my $line = <$FH_IN>) {     
next unless -f $files_dir.'/'.$filename;

 if ($line_count > 500000) { last;}
  
#The following steps obtain basic data from various lines in the file;
  if($line=~m/^\s*ACCESSION\s*NUMBER:\s*/m){$access_num=$1; $access_num =~ tr/-//d;}