/[hyperestraier_wrappers]/trunk/perl/scripts/est-spider
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Contents of /trunk/perl/scripts/est-spider

Parent Directory Parent Directory | Revision Log Revision Log


Revision 18 - (show annotations)
Sat Sep 10 09:31:53 2005 UTC (17 years, 3 months ago) by dpavlin
File size: 4358 byte(s)
added --node option to use node API
1 #!/usr/bin/perl -w
2 use strict;
3 use File::Find;
4 use Getopt::Long;
5 use File::Which;
6 use HyperEstraier;
7 use Text::Iconv;
8
9 # do we use Node API?
10 my $node_url;
11
12 my $collection; # name which will be inserted
13 my $path_add; # add additional info in path
14 my $verbose;
15 my $exclude;
16
17 #$verbose = 1;
18
19 my $result = GetOptions(
20 "collection=s" => \$collection,
21 "path=s" => \$path_add,
22 "verbose!" => \$verbose,
23 "debug!" => \$verbose,
24 "exclude=s" => \$exclude,
25 "node=s" => \$node_url,
26 );
27
28 my $dir = shift @ARGV || die "usage: $0 [dir]";
29
30 #my $basedir = $0;
31 #$basedir =~ s,/[^/]+$,/,;
32 #require "$basedir/filter.pm";
33
34 my $pdftotext = which('pdftotext');
35
36 my $iconv = new Text::Iconv('iso-8859-2', 'utf-8');
37
38 select(STDERR); $|=1;
39 select(STDOUT); $|=1;
40
41 print STDERR "using $pdftotext to convert pdf into html\n" if ($pdftotext && $verbose);
42
43 my $db;
44 if ($node_url) {
45 $db = HyperEstraier::Node->new($node_url);
46 $db->set_auth('admin', 'admin');
47 } else {
48 # open the database
49 $db = HyperEstraier::Database->new();
50 $db->open('/tmp/casket', $HyperEstraier::Database::DBWRITER | $HyperEstraier::Database::DBCREAT);
51
52 sub signal {
53 my($sig) = @_;
54 print "\nCaught a SIG$sig--syncing database and shutting down\n";
55 $db->sync();
56 exit(0);
57 }
58
59 $SIG{'INT'} = \&signal;
60 $SIG{'QUIT'} = \&signal;
61 }
62
63 find({ wanted => \&file,
64 follow => 1,
65 no_chdir => 1
66 }, $dir);
67
68 unless ($node_url) {
69 print "--- sync\n";
70 $db->sync();
71
72 print "--- optimize...\n";
73 $db->optimize(0);
74 }
75 exit;
76
77 sub dump_contents($$$$) {
78 my ($db,$contents,$mtime,$path) = @_;
79
80 return unless ($contents); # don't die on empty files
81
82 if ($exclude && $path =~ m/$exclude/i) {
83 print STDERR "skip: $path\n" if ($verbose);
84 return;
85 }
86
87 use bytes;
88 my $size = length $contents;
89
90 print STDERR " [$size]" if ($verbose);
91
92 # create a document object
93 my $doc = HyperEstraier::Document->new;
94
95 my $title = $1 if ($contents =~ m#<title>(.+)</title>#is);
96
97 # add attributes to the document object
98 $doc->add_attr('@uri', "file:///$path");
99 $doc->add_attr('@title', $title || $path);
100 $doc->add_attr('@size', $size);
101 $doc->add_attr('@mtime', $mtime);
102
103 # html2text
104 $contents =~ s#<[^>]+/*>##gs;
105 $contents =~ s#\s\s+# #gs;
106
107 $doc->add_text($iconv->convert($contents));
108
109 # print $doc->dump_draft if ($verbose);
110
111 # register the document object to the database
112 if ($node_url) {
113 $db->put_doc($doc);
114 } else {
115 $db->put_doc($doc, $HyperEstraier::Database::PDCLEAN);
116 }
117
118 }
119
120 sub file {
121
122 my $path = $_;
123 my $contents;
124
125 return if (-l $path);
126
127 if ($pdftotext && -f $path && $path =~ m/\.pdf$/i) {
128
129 print STDERR "$path {converting}" if ($verbose);
130
131 open(F,"$pdftotext -htmlmeta \"$path\" - |") || die "can't open $pdftotext with '$path'";
132 my $html;
133 while(<F>) {
134 # XXX why pdftotext barks if I try to use this is beyond me.
135 #$contents .= $_;
136
137 $html .= $_;
138 }
139 close(F);
140
141 return if (! $html);
142
143 my $file_only = $path;
144 $file_only =~ s/^.*\/([^\/]+)$/$1/g;
145
146 my ($pre_html,$pages,$post_html) = ('<html><head><title>$path :: page ##page_nr##</title></head><body><pre>',$html,'</pre></body></html>');
147
148 ($pre_html,$pages,$post_html) = ($1,$2,$3) if ($html =~ m/^(<html>.+?<pre>)(.+)(<\/pre>.+?)$/si);
149
150 if ($collection) {
151 $pre_html =~ s/<title>(.+?)<\/title>/<title>$collection :: page ##page_nr##<\/title>/si;
152 } else {
153 $pre_html =~ s/<title>(.+?)<\/title>/<title>$1 :: page ##page_nr##<\/title>/si ||
154 $pre_html =~ s/<title><\/title>/<title>$file_only :: page ##page_nr##<\/title>/si;
155 }
156
157 my $page_nr = 1;
158 foreach my $page (split(/\f/s,$pages)) {
159 print STDERR " $page_nr" if ($verbose);
160 my $pre_tmp = $pre_html;
161 $pre_tmp =~ s/##page_nr##/$page_nr<\/title>/s;
162 dump_contents($db, $pre_tmp . $page . $post_html,time(), $path) if ($page !~ m/^\s*$/s);
163 $page_nr++;
164 }
165
166 } else {
167
168 return if (! -f $path || ! m/\.(html*|php|pl|txt|info|log|text)$/i);
169
170 # skip index files
171 return if (m/index_[a-z]\.html*/i || m/index_symbol\.html*/i);
172
173 open(F,"$path") || die "can't open file: $path";
174 print STDERR "$path" if ($verbose);
175 while(<F>) {
176 $contents .= "$_";
177 }
178 $contents .= "\n\n";
179
180 #$contents = filter($contents,$collection);
181
182 # add optional components to path
183 $path .= " $path_add" if ($path_add);
184
185 dump_contents($db, $contents,time(), $path);
186 }
187
188 print STDERR "\n" if ($verbose);
189 # die "zero size content in '$path'" if (! $contents);
190
191 }
192

Properties

Name Value
svn:executable *

  ViewVC Help
Powered by ViewVC 1.1.26