--- comics/fetch.pl.new 2020/06/10 21:32:52 1.29
+++ comics/fetch.pl.new 2024/12/13 16:03:49 1.31
@@ -2,6 +2,12 @@
###############################################################################
# $Log: fetch.pl.new,v $
+# Revision 1.31 2024/12/13 16:03:49 nick
+# This adds the ability to specify a comic as a link only with a default splash image.
+#
+# Revision 1.30 2022/10/04 12:02:03 nick
+# Added --no-check-certificate for wget calls as arcamax was failing its cert check. Meh, whatever. It's just comics.
+#
# Revision 1.29 2020/06/10 21:32:52 nick
# Centered page
#
@@ -64,11 +70,14 @@ use Pod::Usage;
use Getopt::Long;
use JSON::Create 'create_json';
use Date::Calc qw/Date_to_Text_Long Today Day_of_Week Day_of_Week_to_Text/;
+use Data::Dumper;
+
+print("Running");
##
## Some default values
##
-my $ver = '$Id: fetch.pl.new,v 1.29 2020/06/10 21:32:52 nick Exp $';
+my $ver = '$Id: fetch.pl.new,v 1.31 2024/12/13 16:03:49 nick Exp $';
my $comicFile = "comics.conf";
my $comicConfigVer = "Unknown";
my $reportFile = "/home/httpd/html/daily/comics/status_report.json";
@@ -95,6 +104,8 @@ print STDOUT "Starting comic fetch at $D
foreach my $comic ( sort keys %comics ) {
+ print("Checking Comic $comic\n");
+
## Skip if this is Sunday and the comic is weekdays only
next if ( $comic =~ m/config/ );
if (($dates{'wday'} eq "Sunday") &&
@@ -116,18 +127,20 @@ foreach my $comic ( sort keys %comics )
my $file = "$imageDir/$comic-$dates{'day2'}.$comics{$comic}{'ext'}";
my $size = 0;
- my $cmd = "/usr/bin/identify -verbose $file|";
- open(IMG, $cmd) || die ("Can't open: $!\n");
- while(![]()
) {
- if ($_ =~ m/^\s+geometry:\s+(\d+)x\d+.*/i) {
- $size = $1 if ( $size == 0);
- }
- }
- close(IMG);
-
-
- system( "/usr/bin/convert -resize 640 $file $file" )
- if ( $size > 640 )
+ ## Resize downloaded images
+ if($comics{$comic}{'mode'} != 3) {
+ my $cmd = "/usr/bin/identify -verbose $file|";
+ open(IMG, $cmd) || die ("Can't open: $!\n");
+ while(![]()
) {
+ if ($_ =~ m/^\s+geometry:\s+(\d+)x\d+.*/i) {
+ $size = $1 if ( $size == 0);
+ }
+ }
+ close(IMG);
+
+ system( "/usr/bin/convert -resize 800 $file $file" )
+ if ( $size > 800 )
+ }
}
## &writeMainIndex ( \%dates );
@@ -164,6 +177,10 @@ sub downloadComic ($$) {
return directDownload ( \%comics, $comic, $date );
last SWITCH;
}
+ if ( $comics->{$comic}{'mode'} eq 3 ) {
+ return 0;
+ last SWITCH;
+ }
}
return "ERROR: Unknown download method specified for $comics->{$comic}{'fullName'}.";
@@ -253,7 +270,8 @@ sub writeComic ($$) {
my $indexFile = $indexDir . "/index-" . $date->{'year2'} .
$date->{'mon2'} . $date->{'day2'} . "-" .
$sd . ".html";
- $comics->{$comic}{'fullName'} =~ s/&/&/g;
+ $comics->{$comic}{'fullName'} =~ s/&/&/g;
+
my $content = <{$comic}{'fullName'}) ******* -->
@@ -261,11 +279,22 @@ sub writeComic ($$) {
$comics->{$comic}{'fullName'}
-
+
$comics->{$comic}{'url'}
+EOF
+ if ( $comics->{$comic}{'mode'} == 3 ) {
+ print("Mode 3\n");
+ $content .= <
+EOF
+ } else {
+ $content .= <
+EOF
+ }
+ $content .= <
|
@@ -384,22 +413,38 @@ sub directDownload ($$) {
my $cDir = $date->{'mon2'} . $date->{'year2'};
my $cDate = $date->{'day2'};
- my $cmd = "wget -q $file --referer='" . $comics->{$comic}{'url'} ."' --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg";
+ my $cmd = "wget --no-check-certificate -q $file --referer='" . $comics->{$comic}{'url'} ."' --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg";
return system($cmd);
}
#######################################################################
#######################################################################
+sub linkOnly ($$) {
+ my ( $comics, $comic, $date ) = @_;
+
+ return 0;
+}
+#######################################################################
+#######################################################################
sub indexDownload ($$) {
my ( $comics, $comic, $date ) = @_;
my ( @lines, $comicLine, $mainURL );
my $comicIndex = "indexes/index.$comic";
- my $wget_cmd = "wget -q --referer='$comics->{$comic}{'url'}' " .
- "--user-agent=\"$USER_AGENT\" " .
+ print("Getching Index $comicIndex.\n");
+ print("comic url: $comics->{$comic}{'url'}\n");
+
+ print Dumper($comics->{$comic});
+
+ my $wget_cmd = "wget --referer='$comics->{$comic}{'url'}' " .
+ "--no-check-certificate --user-agent=\"$USER_AGENT\" " .
"$comics->{$comic}{'url'} -O $comicIndex";
- system($wget_cmd);
+ print ("Using wget command:\n$wget_cmd\n");
+
+ my $status = system($wget_cmd);
+
+ print ("Return status: $status\n");
if ( ! open FILEN, "<$comicIndex" ) {
return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} .
@@ -424,9 +469,13 @@ sub indexDownload ($$) {
## Find the comic strip URL based on the specified regex in the search
##
+ print "Using search $comics->{$comic}{'search'}\n";
+
foreach my $line (@lines) {
if ( $line =~ m/$comics->{$comic}{'search'}/i ) {
+ print "Found match:\n";
$comicLine = $1; chomp $comicLine;
+ print "+ $comicLine\n";
}
}
@@ -437,11 +486,13 @@ sub indexDownload ($$) {
my $cDate = $date->{'day2'};
if ( $comicLine ) {
+ print "Downloading Comic\n";
if ( $comicLine =~ m/(gif|jpg|png)/i ) { $comics->{$comic}{'ext'} = $1; }
my $comicURL = ( $comicLine =~ m/http/ ) ? $comicLine : $mainURL . $comicLine;
+ print "Final URL: $comicURL\n";
# Strip &
$comicURL =~ s/\&\;/&/g;
- my $cmd = "wget --user-agent=\"$USER_AGENT\" --referer='" . $comics->{$comic}{'url'} . "' -q '$comicURL' -O images/$cDir/$comic-$cDate.$comics->{$comic}{'ext'}";
+ my $cmd = "wget --no-check-certificate --user-agent=\"$USER_AGENT\" --referer='" . $comics->{$comic}{'url'} . "' -q '$comicURL' -O images/$cDir/$comic-$cDate.$comics->{$comic}{'ext'}";
system( $cmd );
return 0;
}