I am attempting to use the LWP::UserAgent to request a Soap call, and in the response the request returns a TIFF image. When I write the contents out to a file(binary mode), the file also contains header information. How would I go about extracting just the body(TIF image) of the response?
Expand|Select|Wrap|Line Numbers
- #!/usr/bin/perl
- use strict;
- use Data::Dumper;
- use LWP::UserAgent;
- my $type = "TIFF";
- my $ua = new LWP::UserAgent;
- my $service = "http://ops.epo.org//soap-services/document-retrieval";
- my $content = '<soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:ops="http://ops.epo.org">';
- $content = $content . '<soapenv:Header/>';
- $content = $content . '<soapenv:Body>';
- $content = $content . "<ops:document-retrieval id=\"EP 1000000A1 I \" page-number=\"1\" document-format=\"SINGLE_PAGE_$type\" system=\"ops.epo.org\">";
- $content = $content . '</ops:document-retrieval>';
- $content = $content . '</soapenv:Body>';
- $content = $content . '</soapenv:Envelope>';
- my $header = new HTTP::Headers (
- 'Content-Type' => 'text/xml; charset=utf-8',
- 'SOAPAction' => 'document-retrieval',
- );
- my $req = new HTTP::Request('POST',$service,$header,$content);
- my $res = $ua->request($req);
- print "request string:\n". $req->as_string."\n";
- print "content type: ". $res->content_type."\n";
- print "header = ". $res->headers_as_string()."\n";
- #my $response = $res->headers_as_string();
- #my $response .= $res->content;
- #print "---response---\n$response\n";
- #my ($body,$mime);
- #eval
- #{
- # $mime = $res->parts([1]);
- #$body = $mime->body_handle();
- #};
- #if ($@)
- #{ die "error: $@\n"; }
- if ($res->is_success)
- {
- my $dlfile = "file.$type";
- open(OUT, ">$dlfile") or die "whoops $!";
- binmode(OUT);
- print OUT $res->content;
- close OUT;
- }
- else
- { warn "request failed...\n"; }
request string:
POST http://ops.epo.org//soap-services/document-retrieval
User-Agent: libwww-perl/5.834
Content-Type: text/xml; charset=utf-8
SOAPAction: document-retrieval
<soapenv:Envelo pe xmlns:soapenv=" http://schemas.xmlsoap .org/soap/envelope/" xmlns:ops="http ://ops.epo.org"><s oapenv:Header/><soapenv:Body> <ops:document-retrieval id="EP 1000000A1 I " page-number="1" document-format="SINGLE_ PAGE_TIFF" system="ops.epo .org"></ops:document-retrieval></soapenv:Body></soapenv:Envelop e>
content type: multipart/related
header = Connection: close
Date: Wed, 14 Apr 2010 13:31:58 GMT
Accept: text/xml, text/html, image/gif, image/jpeg, *; q=.2, */*; q=.2
Server: Apache
Content-Type: multipart/related; boundary="----=_Part_901910_5 14465450.127125 1918535"; type="text/xml"
Client-Date: Wed, 14 Apr 2010 13:32:00 GMT
Client-Peer: 145.64.132.201: 80
Client-Response-Num: 1
Client-Transfer-Encoding: chunked
SOAPAction: ""
X-Powered-By: Servlet 2.4; JBoss-4.3.0.GA (build: SVNTag=JBPAPP_4 _3_0_GA date=2008010315 48)/Tomcat-5.5
Top few lines of TIFF file:
------=_Part_901910_5 14465450.127125 1918535
Content-Type: text/xml; charset=utf-8
<SOAP-ENV:Envelope xmlns:SOAP-ENV="http://schemas.xmlsoap .org/soap/envelope/"><SOAP-ENV:Header/><SOAP-ENV:Body><ops:w orld-patent-data xmlns="http://www.epo.org/exchange" xmlns:ops="http ://ops.epo.org"><o ps:meta name="elapsed-time" value="42"/><ops:documen t-retrieval document-format="SINGLE_ PAGE_TIFF" id="EP 1000000A1 I " page-number="1" system="ops.epo .org"><ops:desc >FullDocument </ops:desc><ops:c ontent-ref>EP 1000000A1 I .tiff</ops:content-ref></ops:document-retrieval></ops:world-patent-data></SOAP-ENV:Body></SOAP-ENV:Envelope>
------=_Part_901910_5 14465450.127125 1918535
Content-Type: application/tiff
Content-ID: EP 1000000A1 I .tiff
Content-Transfer-Encoding: binary
Thanks for any replies!