#!/usr/bin/perl

use HTTP::OAI;

my $h = new HTTP::OAI::Harvester(baseURL=>'http://arXiv.org/oai2');
my $response = $h->repository($h->Identify);
 if( $response->is_error )
 {
     print "Error requesting Identify:\n",
     $response->code . " " . $response->message, "\n";
     exit;
 }

# Note: repositoryVersion will always be 2.0, $r->version returns
# the actual version the repository is running
print "Repository supports protocol version ", $response->version, "\n";

# Version 1.x repositories don't support metadataPrefix,
# but OAI-PERL will drop the prefix automatically
# if an Identify was requested first (as above)
$response = $h->ListIdentifiers(
   metadataPrefix=>'oai_dc',
   from=>'2001-02-03',
   until=>'2001-04-10'
);

if( $response->is_error ) {
  die("Error harvesting: " . $response->message . "\n");
}

print "responseDate => ", $response->responseDate, "\n",
                       "requestURL => ", $response->requestURL, "\n";

while( my $id = $response->next ) {
   print "identifier => ", $id->identifier;
   # Only available from OAI 2.0 repositories
   print " (", $id->datestamp, ")" if $id->datestamp;
   print " (", $id->status, ")" if $id->status;
   print "\n";
   # Only available from OAI 2.0 repositories
   for( $id->setSpec ) {
      print "\t", $_, "\n";
   }
}

# Using a handler
$response = $h->ListRecords(
   metadataPrefix=>'oai_dc',
   handlers=>{metadata=>'HTTP::OAI::Metadata::OAI_DC'},
);
while( my $rec = $response->next ) {
   print $rec->identifier, "\t",
   $rec->datestamp, "\n",
   $rec->metadata, "\n";
   print join(',', @{$rec->metadata->dc->{'title'}}), "\n";
}
if( $rec->is_error ) {
  die $response->message;
}

# Offline parsing
$I = HTTP::OAI::Identify->new();
$I->parse_string($content);
$I->parse_file($fh);