#!/usr/bin/env perl

# htid2txt.pl - given a HathiTrust identifier, output a plain (OCRed) text

# Eric Lease Morgan <emorgan@nd.edu>
# (c) University of Notre Dame; distributed under a GNU Public License

# February 10, 2019 - first cut


# configure
use constant KEY        => '';
use constant SECRET     => ''; 
use constant OCRREQUEST => 'https://babel.hathitrust.org/cgi/htd/volume/pageocr/';
use constant HTID       => 'uva.x000274833';

# require
use strict;
use OAuth::Lite::Consumer;
use OAuth::Lite::AuthMethod;

# initialize
my $consumer = OAuth::Lite::Consumer->new(
		consumer_key    => KEY,
		consumer_secret => SECRET,
		auth_method     => OAuth::Lite::AuthMethod::URL_QUERY,
	);

# continually get pages
my $continue   = 1;
my $page       = 0;
my $ocrrequest = OCRREQUEST . HTID;
while ( $continue ) {

	# increment and build request url
	$page++;
	my $url = $ocrrequest . '/' . $page;

	# request
	my $response = $consumer->request(
			method  => 'GET',
			url     => $url,
			params  => { v => '2' }
		);

	# output, conditionally
	if ( $response->code == '404' ) { last }
	else { print $response->content, "\n" }
	
}

# done
exit;