Annotation of nsdl/nsdlloncapaorg/harvester.pl, revision 1.7
1.1 www 1: #!/usr/local/bin/perl
2:
3: #
4: # lon-capa.pl
5: # Parse the LON-CAPA metadata
6: #
7: # Andy Dong <adong@smete.org> 10/23/2002
8: #
9: # Contact Gerd Kortemeyer (korte@lite.msu.edu)
10:
11: use strict;
12: use LWP::UserAgent;
13: use Getopt::Std;
1.2 www 14: use Digest::MD5 qw(md5_hex);
1.4 www 15: use IO::File;
16:
17: my $basepath='/home/httpd/cgi-bin/OAI-XMLFile/XMLFile/nsdlexport/data';
1.1 www 18:
19: my $pub_month;
20: my $pub_year;
21: my @loncapa;
22:
23: # HTTP requests
24:
25: my $content;
26: my $content_regex = 'File Not Found';
27:
28: # Configuration
29:
30: my $debug = 0;
1.5 www 31:
1.1 www 32: # The list of servers is from the LON-CAPA CVS repository in /loncapa/loncom/production_hosts.tab
1.5 www 33: my @servers = (
34: 'newscience.westshore.cc.mi.us',
35: 's10.lite.msu.edu',
36: 's12.lite.msu.edu',
37: 'lon-capa.chem.sunysb.edu',
38: 'schubert.tmcc.edu',
39: 'dalton.chem.sfu.ca',
40: 'capa2.phy.ohiou.edu',
41: 'pollux.physics.fsu.edu',
42: 'loncapa.physics.sc.edu',
43: 'loncapa.math.ucf.edu',
44: 'zappa.ags.udel.edu',
45: 'loncapa.gwu.edu',
46: 'neptune.physics.ndsu.nodak.edu',
1.6 www 47: 'capa1.uwsp.edu',
48: 'natasha.it.fit.edu',
49: 'loncapa.Mines.EDU',
50: 'loncapa.chm.nau.edu');
1.1 www 51:
1.5 www 52: foreach (@servers) {
53: my $url='http://'.$_.'/cgi-bin/metadata_harvest.pl';
1.1 www 54: # End Configuration
55:
1.2 www 56: my $ua = new LWP::UserAgent;
57: $ua->timeout(600);
1.1 www 58:
1.2 www 59: my $request = new HTTP::Request GET => $url;
60: $request->authorization_basic('reaper', 'cat4u');
1.1 www 61:
1.2 www 62: my $response = $ua->request( $request );
1.1 www 63:
1.2 www 64: if ( $response->is_success ) {
1.5 www 65: print 'SUCCESS: ' . $response->message.' for '.$url."\n\n";
1.2 www 66: $content = $response->content;
1.1 www 67: # Delete all blank lines
1.2 www 68: $content =~ s/(?<!.)\n//g;
1.1 www 69: # Replace all ^M with spaces
1.2 www 70: $content =~ s/
/\s/g;
1.1 www 71: # Push the content into an array
1.2 www 72: @loncapa = split /\n/, $content;
73: } else {
1.5 www 74: print 'LON-CAPA request failed: ' . $response->message.' for '.$url."\n\n";
75: next;
1.2 www 76: }
1.1 www 77:
1.2 www 78: #@loncapa=undef;
79: #open (LON_FILE, 'metadata_harvest.txt') || die;
1.1 www 80:
1.2 www 81: #while (<LON_FILE>) {
82: # chomp;
83: # push(@loncapa,$_);
84: #}
1.1 www 85:
86: my %records = ();;
1.3 www 87:
1.1 www 88: foreach my $metadata (@loncapa) {
89: chomp $metadata;
1.2 www 90: $metadata=~s/[^\w\d\s\.\;\:\,\|\/]/ /gs;
1.1 www 91: my @tkline = split('\|', $metadata);
92: my $title = $tkline[0];
93: next if ( $title eq '' );
94: my $author = $tkline[1];
95: next if ( $author eq '' );
96: my @authorname = split(' ', $author);
97: my $author_fname = $authorname[0];
98: my $author_lname = $authorname[1];
99: # We have to make an exception for Multimedia Physics which is an organization not a person
100: my $object_type;
101: if ( $author_lname eq 'Physics' ) {
102: $object_type = 'organization';
103: } else {
104: $object_type = 'person';
105: }
106: my $subject = $tkline[2];
107: next if ( ($subject eq 'Sample') || ($subject eq 'Something') );
1.2 www 108: my $resourceurl = 'http://nsdl.lon-capa.org' . $tkline[3];
109: my $baseid=$tkline[3];
1.4 www 110: my ($adom,$auname)=($baseid=~/^\/res\/(\w+)\/(\w+)\//);
1.2 www 111: $baseid=~s/\W/\_/g;
112: $baseid=~s/^\_res\_//g;
1.4 www 113: my $fileid=md5_hex($baseid);
1.2 www 114:
1.1 www 115: next if ( $resourceurl =~ /(.*)\/demo\/(.*)/ );
116: my $keywords = $tkline[4];
117: my $version = $tkline[5];
118: my $notes = $tkline[6];
119: my $abstract = $tkline[7];
1.7 ! www 120: unless ($abstract) { $abstract=$subject; }
! 121: unless ($abstract) { $abstract=$title; }
! 122: unless ($abstract) { $abstract=$keywords; }
1.1 www 123: my $type = $tkline[8];
124: my $learning_resource_type;
125: if ( $type eq 'problem' ) {
126: $learning_resource_type = 114;
127: } elsif ( $type eq 'exam' ) {
128: $learning_resource_type = 114;
129: } elsif ( $type eq 'quiz' ) {
130: $learning_resource_type = 114;
131: } elsif ( $type eq 'assess' ) {
132: $learning_resource_type = 114;
133: } elsif ( $type eq 'survey' ) {
134: $learning_resource_type = 114;
135: } elsif ( $type eq 'form' ) {
136: $learning_resource_type = 114;
137: } elsif ( $type eq 'library' ) {
138: $learning_resource_type = 107;
139: } elsif ( $type eq 'page' ) {
140: $learning_resource_type = 104;
141: } elsif ( $type eq 'sequence' ) {
142: $learning_resource_type = 104;
143: } elsif ( $type eq 'spreadsheet' ) {
144: $learning_resource_type = 114;
145: } else {
146: $learning_resource_type = 0;
147: }
148:
149: my $media_format;
150: if ( ($type eq 'htm') || ($type eq 'gif') || ($type eq 'mov') || ($type eq 'xml') ) {
151: $media_format = 70;
152: } else {
153: $media_format = 0;
154: }
155:
156: my $language = $tkline[9]; # Look only for seniso
157: next if ( $language ne 'seniso');
158: my $primary_language='en-US';
159: my $creation_date = $tkline[10];
1.3 www 160: my ($pub_year,$pub_month,$pub_day) = ( $creation_date =~ /^(\d{4}) (\d{2}) (\d{2})\s(\d{2}):(\d{2}):(\d{2})$/ );
1.1 www 161: my $revision_date = $tkline[11];
1.3 www 162: my ($rev_year,$rev_month,$rev_day) = ( $revision_date =~ /^(\d{4}) (\d{2}) (\d{2})\s(\d{2}):(\d{2}):(\d{2})$/ );
1.1 www 163: my $owner = $tkline[12];
164: my $rights_description;
165: my $copyright = $tkline[13]; # public,domain,default,private (skip if private and domain)
166: # Public means no login required
167:
168: if ( $copyright eq 'public' ) {
169: $rights_description = 'LON-CAPA Public Resource. No login required.';
170: } elsif ($copyright eq 'domain') {
171: $rights_description = 'Restricted to certain LON-CAPA domains.';
172: } else {
173: $rights_description = 'LON-CAPA Default Use Restriction. Login required.';
174: }
175: # Domain means restricted to a particular LON-CAPA domain
176: # Defaults mean access open to any registered LON-CAPA user
177: # Private means open only to author of material
178: next if ( $copyright eq 'private');
1.6 www 179: next if ( $copyright eq 'domain');
1.1 www 180: my $platform = "5"; # HTML Browser (not specified but construed from metadata)
1.4 www 181: #
182: # Create path
183: #
184: unless (-e $basepath.'/'.$adom) { mkdir($basepath.'/'.$adom); }
185: unless (-e $basepath.'/'.$adom.'/'.$auname) {
186: mkdir($basepath.'/'.$adom.'/'.$auname) || die 'Could not create '.$basepath.'/'.$adom.'/'.$auname;
187: }
188: open(XML,'>'.$basepath.'/'.$adom.'/'.$auname.'/'.$baseid.'.xml');
189: print XML (<<ENDMETA);
190: <?xml version="1.0" encoding="UTF-8"?>
191:
1.3 www 192: <oaidc:dc xmlns="http://purl.org/dc/elements/1.1/"
193: xmlns:oaidc="http://www.openarchives.org/OAI/2.0/oai_dc/"
194: xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
195: xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/
196: http://www.openarchives.org/OAI/2.0/oai_dc.xsd"
197: >
198: <title>$title</title>
199: <creator>$author_fname $author_lname</creator>
200: <identifier>$resourceurl</identifier>
201: <subject>$keywords</subject>
202: <subject>$subject</subject>
203: <language>$primary_language</language>
204: <description>$abstract</description>
205: <date>$rev_year-$rev_month-$rev_day</date>
206: </oaidc:dc>
1.2 www 207: ENDMETA
1.4 www 208: close (XML);
1.5 www 209: }
1.1 www 210: }
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/back.gif){kind=icon}
Return to harvester.pl CVS log ![[TXT]](/icons/text.gif){kind=icon}
![[DIR]](/icons/dir.gif){kind=icon}
Up to [LON-CAPA] / nsdl / nsdlloncapaorg