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

Diff of /trunk/spider/progspider

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 72 by dpavlin, Tue Apr 6 15:06:58 2004 UTC revision 84 by dpavlin, Sun Aug 29 21:19:13 2004 UTC
# Line 1  Line 1 
1  #!/usr/local/bin/perl -w  #!/usr/bin/perl -w
2  use strict;  use strict;
3  use File::Find;  use File::Find;
4  use Getopt::Long;  use Getopt::Long;
# Line 50  sub dump_contents($$$) { Line 50  sub dump_contents($$$) {
50  Path-Name: $path  Path-Name: $path
51  Content-Length: $size  Content-Length: $size
52  Last-Mtime: $mtime  Last-Mtime: $mtime
53  Document-Type: HTML  Document-Type: html*
54    
55  EOF  EOF
56          print $contents;          print $contents;
# Line 76  sub file { Line 76  sub file {
76                  }                  }
77                  close(F);                  close(F);
78    
79                    return if (! $html);
80    
81                    my $file_only = $path;
82                    $file_only =~ s/^.*\/([^\/]+)$/$1/g;
83    
84                  my ($pre_html,$pages,$post_html) = ('<html><head><title>$path :: page ##page_nr##</title></head><body><pre>',$html,'</pre></body></html>');                  my ($pre_html,$pages,$post_html) = ('<html><head><title>$path :: page ##page_nr##</title></head><body><pre>',$html,'</pre></body></html>');
85    
86                  ($pre_html,$pages,$post_html) = ($1,$2,$3) if ($html =~ m/^(<html>.+?<pre>)(.+)(<\/pre>.+?)$/si);                  ($pre_html,$pages,$post_html) = ($1,$2,$3) if ($html =~ m/^(<html>.+?<pre>)(.+)(<\/pre>.+?)$/si);
# Line 83  sub file { Line 88  sub file {
88                  if ($collection) {                  if ($collection) {
89                          $pre_html =~ s/<title>(.+?)<\/title>/<title>$collection :: page ##page_nr##<\/title>/si;                          $pre_html =~ s/<title>(.+?)<\/title>/<title>$collection :: page ##page_nr##<\/title>/si;
90                  } else {                  } else {
91                          $pre_html =~ s/<title>(.+?)<\/title>/<title>$1 :: page ##page_nr##<\/title>/si;                          $pre_html =~ s/<title>(.+?)<\/title>/<title>$1 :: page ##page_nr##<\/title>/si ||
92                            $pre_html =~ s/<title><\/title>/<title>$file_only :: page ##page_nr##<\/title>/si;
93                  }                  }
94    
95                  my $page_nr = 1;                  my $page_nr = 1;
# Line 97  sub file { Line 103  sub file {
103    
104          } else {          } else {
105    
106                  return if (! -f $path || ! m/\.html*$/i);                  return if (! -f $path || ! m/\.(html*|php|pl|txt|info|log|text)$/i);
107    
108                  # skip index files                  # skip index files
109                  return if (m/index_[a-z]\.html*/i || m/index_symbol\.html*/i);                  return if (m/index_[a-z]\.html*/i || m/index_symbol\.html*/i);
Legend:
Removed from v.72  
changed lines
  Added in v.84
  ViewVC Help
Powered by ViewVC 1.1.26