#!/usr/bin/perl -w
#use strict;
# This program extracts data from an SEC filing, including chunks of text
use Benchmark;
#get the HTML-Format package from the package manager.
use HTML::Formatter;
#get the HTML-TREE from the package manager
use HTML::TreeBuilder;
use HTML::FormatText;
$startTime = new Benchmark;
   
#This program is written to obtain "Significant Accounting Policies" which are typically found in item 4/4 of the 10k

my $startstring='((^\s*?)Significant Accounting Policies\s\n)';
#Specify keywords/phrases you expect to find within the item (make sure the words phrases are not also in the start or end string)
my $keywords='(estimates|Financial  Accounting  Standards  Board|Revenue Recognition|generally accepted accounting principles|accruals|inventories|straight-line|)'; #horizontal line means alternative match if not found
#Specify the end of the text you are looking for.

# Need to create a flexible end string that uses +1 the variable in front of "SAP" 
my $endstring='((^\s*?)Item\s+(10)[\.\-]?[^\d]*?\n)';
my $direct="D:\\ExternalFiles\\Edgar\\tenks\\randomsort";