--- trunk/spider/progspider 2004/03/18 11:14:49 68
+++ trunk/spider/progspider 2004/04/06 15:06:58 72
@@ -78,12 +78,17 @@
my ($pre_html,$pages,$post_html) = ('$path :: page ##page_nr##',$html,'
');
- ($pre_html,$pages,$post_html) = ($1,$2,$3) if ($html =~ m/^(.+)(.+)(<\/pre>.+)$/si);
+ ($pre_html,$pages,$post_html) = ($1,$2,$3) if ($html =~ m/^(.+?)(.+)(<\/pre>.+?)$/si);
- $pre_html =~ s/(.+?)<\/title>/<title>$1 :: page ##page_nr##<\/title>/si;
+ if ($collection) {
+ $pre_html =~ s/<title>(.+?)<\/title>/<title>$collection :: page ##page_nr##<\/title>/si;
+ } else {
+ $pre_html =~ s/<title>(.+?)<\/title>/<title>$1 :: page ##page_nr##<\/title>/si;
+ }
my $page_nr = 1;
- foreach my $page (split(/\f/,$pages)) {
+ foreach my $page (split(/\f/s,$pages)) {
+ print STDERR " $page_nr" if ($verbose);
my $pre_tmp = $pre_html;
$pre_tmp =~ s/##page_nr##/$page_nr<\/title>/s;
dump_contents($pre_tmp . $page . $post_html,time(), $path) if ($page !~ m/^\s*$/s);