version 1.4, 2011/09/23 01:36:54
|
version 1.22, 2017/12/05 13:37:40
|
Line 1
|
Line 1
|
#!/usr/bin/perl -w |
#!/usr/bin/perl -w |
|
|
|
############################################################################### |
|
# $Log$ |
|
# Revision 1.22 2017/12/05 13:37:40 nick |
|
# Added the CVS config version to the outpuit. |
|
# |
|
# Revision 1.21 2015/10/26 14:25:40 nick |
|
# Fixed a bug that was improperly including the day of week string preventing the weekend comics from fetching proproperly. |
|
# |
|
# Revision 1.20 2015/10/22 12:58:44 nick |
|
# Added the ability for Sunday only comics. Stonesoup is no longer weekdays, this has been added to Sunday only. I also added Foxtrot Classics for weekdays and Foxtrot for Sundays. |
|
# |
|
# Revision 1.19 2015/07/13 12:56:58 nick |
|
# Added Sally Forth and Pearls Before Swine. Adding Sally Forth required a change in the 'wget' command for fetching the index file to include 'user-agent' and 'referer'. |
|
# |
|
# Revision 1.18 2015/05/07 12:31:43 nick |
|
# Added favicon |
|
# |
|
# Revision 1.17 2015/02/19 14:56:10 nick |
|
# Fixed a problem that forced everything to JPG. This would kill GIF animations, but would not display the gifs either because 'convert' appends an index number to the end of the file name for each from of the GIF animation. I fixed this to maintain GIF compatibilty as well as rewritting how the script fetches the size of the file. Additionally, I updated the configuration for Questionable Content to search for GIF or JPG, which is what triggered this entire update. |
|
# |
|
# Revision 1.16 2015/02/05 18:05:58 nick |
|
# Changed the background and added a fancy title. |
|
# |
|
# Revision 1.15 2015/01/19 13:46:19 nick |
|
# *** empty log message *** |
|
# |
|
############################################################################### |
|
|
use strict; |
use strict; |
use File::Path; |
use File::Path; |
use Data::Dumper; |
use Data::Dumper; |
|
use Pod::Usage; |
|
use Getopt::Long; |
|
|
|
use Date::Calc qw/Date_to_Text_Long Today Day_of_Week Day_of_Week_to_Text/; |
|
|
## |
## |
## Some default values |
## Some default values |
## |
## |
my $ver = q/$Id$/; |
my $ver = '$Id$'; |
my $comicFile = "comics.conf"; |
my $comicFile = "comics.conf"; |
|
my $comicConfigVer = "Unknown"; |
my %comics = &readComicConfig ( $comicFile ); |
my %comics = &readComicConfig ( $comicFile ); |
|
my %opts = &fetchOptions( ); |
|
my $days_ago = $opts{'days'} || 0; |
my %dates = &fetchDates(); |
my %dates = &fetchDates(); |
my $baseDir = $comics{'configs'}{'base_directory'} || "."; |
my $baseDir = $comics{'configs'}{'base_directory'} || "."; |
my $imageDir = $baseDir . "/" . ( $comics{'configs'}{'image_directory'} || "images" ) . |
my $imageDir = $baseDir . "/" . ( $comics{'configs'}{'image_directory'} || "images" ) . |
"/$dates{'mon2'}$dates{'year2'}"; |
"/$dates{'mon2'}$dates{'year2'}"; |
my $indexDir = $baseDir . "/" . ( $comics{'configs'}{'index_directory'} || "indexes" ); |
my $indexDir = $baseDir . "/" . ( $comics{'configs'}{'index_directory'} || "indexes" ); |
my $USER_AGENT = "Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.18) Gecko/20110628 Ubuntu/10.10 (maverick) Firefox/3.6.18"; |
my $USER_AGENT = "Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.18) Gecko/20110628 Ubuntu/10.10 (maverick) Firefox/3.6.18"; |
|
my @days = qw/ Sunday Monday Tuesday Wednesday Thursday Friday Saturday /; |
|
|
my $DATE=`date`; chomp $DATE; |
my $DATE=`date`; chomp $DATE; |
print STDOUT "Starting comic fetch at $DATE\n"; |
print STDOUT "Starting comic fetch at $DATE\n"; |
Line 26 print STDOUT "Starting comic fetch at $D
|
Line 61 print STDOUT "Starting comic fetch at $D
|
## |
## |
&checkDir ( [ $imageDir, $indexDir ] ); |
&checkDir ( [ $imageDir, $indexDir ] ); |
|
|
#&writeTitle ( \%dates ); |
&writeTitle ( \%dates ); |
|
|
foreach my $comic ( sort keys %comics ) { |
foreach my $comic ( sort keys %comics ) { |
|
|
|
## Skip if this is Sunday and the comic is weekdays only |
next if ( $comic =~ m/config/ ); |
next if ( $comic =~ m/config/ ); |
|
if (($dates{'wday'} eq "Sunday") && |
|
($comics{$comic}{'sunday'} == 0)) { |
|
print "Skipping '$comic'; Weekdays only.\n"; |
|
next; |
|
} |
|
|
|
## Skip if Sunday only comic and it's not Sunday. |
|
if (($dates{'wday'} ne "Sunday") && |
|
($comics{$comic}{'sunday_only'} == 1)) { |
|
print "Skipping '$comic' ($comics{$comic}{'sunday_only'}); Sunday only.\n"; |
|
next |
|
} |
|
|
$comics{$comic}{'error'} = &downloadComic ( \%comics, $comic, \%dates ); |
$comics{$comic}{'error'} = &downloadComic ( \%comics, $comic, \%dates ); |
&writeComic ( \%comics, $comic, \%dates ); |
&writeComic ( \%comics, $comic, \%dates ); |
} |
|
|
|
my $D = `date +%d`; chomp $D; |
my $file = "$imageDir/$comic-$dates{'day2'}.$comics{$comic}{'ext'}"; |
print "Finding in $imageDir/*-$D.jpg\n"; |
my $size = 0; |
foreach my $file ( glob( "$imageDir/*-$D.jpg" ) ) |
|
{ |
my $cmd = "/usr/bin/identify -verbose $file|"; |
my $size = `/usr/bin/identify $file`; |
open(IMG, $cmd) || die ("Can't open: $!\n"); |
$size =~ s/.*\s(\d+)x\d+.*/$1/; |
while(<IMG>) { |
|
if ($_ =~ m/^\s+geometry:\s+(\d+)x\d+.*/i) { |
|
$size = $1 if ( $size == 0); |
|
} |
|
} |
|
close(IMG); |
|
|
|
|
system( "/usr/bin/convert -resize 640 $file $file" ) |
system( "/usr/bin/convert -resize 640 $file $file" ) |
if ( $size > 640 ) |
if ( $size > 640 ) |
Line 88 sub readComicConfig ($$) {
|
Line 143 sub readComicConfig ($$) {
|
my %comicConfig = ( ); |
my %comicConfig = ( ); |
my %config = ( ); |
my %config = ( ); |
|
|
|
my ($year, $mon, $day) =( localtime(time))[5,4,3]; |
|
$year += 1900; |
|
$mon = sprintf("%02d", ($mon + 1)); |
|
$day = sprintf("%02d", $day); |
|
|
open FILEN, "<$comicFile"; |
open FILEN, "<$comicFile"; |
while (<FILEN>) { |
while (<FILEN>) { |
|
if ($_ =~ m/^#.* \$Id$/) { |
|
$comicConfigVer = $1; |
|
} |
if ( ( $_ !~ m/^#/ ) && ( $_ =~ m/,.*,/) ){ |
if ( ( $_ !~ m/^#/ ) && ( $_ =~ m/,.*,/) ){ |
|
$_ =~ s/__YEAR__/$year/g; |
|
$_ =~ s/__MON__/$mon/g; |
|
$_ =~ s/__DAY__/$day/g; |
|
|
my @res = split /,/, $_; |
my @res = split /,/, $_; |
$comicConfig{$res[0]}{'url'} = $res[1]; |
$comicConfig{$res[0]}{'url'} = $res[1]; |
$comicConfig{$res[0]}{'search'} = $res[2]; |
$comicConfig{$res[0]}{'search'} = $res[2]; |
$comicConfig{$res[0]}{'mode'} = $res[3]; |
$comicConfig{$res[0]}{'mode'} = $res[3]; |
$comicConfig{$res[0]}{'fullName'} = $res[4]; |
$comicConfig{$res[0]}{'fullName'} = $res[4]; |
$comicConfig{$res[0]}{'ext'} = $res[5]; |
$comicConfig{$res[0]}{'ext'} = $res[5]; |
|
$comicConfig{$res[0]}{'sunday'} = sprintf("%d", $res[6] || 1); |
|
$comicConfig{$res[0]}{'sunday_only'} = sprintf("%d", $res[7] || 0); |
$comicConfig{$res[0]}{'error'} = 0; |
$comicConfig{$res[0]}{'error'} = 0; |
} |
} |
elsif ( $_ =~ m/(.*)\s+=\s+(.*)/ ) { |
elsif ( $_ =~ m/(.*)\s+=\s+(.*)/ ) { |
Line 112 sub readComicConfig ($$) {
|
Line 181 sub readComicConfig ($$) {
|
####################################################################### |
####################################################################### |
sub writeComic ($$) { |
sub writeComic ($$) { |
my ( $comics, $comic, $date ) = @_; |
my ( $comics, $comic, $date ) = @_; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} . |
my $sd = substr( join( '', $days[$date->{'dow'}] ), 0, 3 ); |
$date->{'day2'} . ".html"; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . |
|
$date->{'mon2'} . $date->{'day2'} . "-" . |
|
$sd . ".html"; |
my $content = <<EOF; |
my $content = <<EOF; |
|
|
<!-- ********* Begin $comic ($comics->{$comic}{'fullName'}) ******* --> |
<!-- ********* Begin $comic ($comics->{$comic}{'fullName'}) ******* --> |
Line 125 sub writeComic ($$) {
|
Line 196 sub writeComic ($$) {
|
$comics->{$comic}{'url'} |
$comics->{$comic}{'url'} |
</a> |
</a> |
</font><br/> |
</font><br/> |
<img src="../images/$date->{'mon2'}$date->{'year2'}/$comic-$date->{'day2'}.jpg" alt="$comic-$date->{'day2'}" /> |
<img src="../images/$date->{'mon2'}$date->{'year2'}/$comic-$date->{'day2'}.$comics->{$comic}{'ext'}" alt="$comic-$date->{'day2'}" /> |
<br/><br/> |
<br/><br/> |
</td></tr> |
</td></tr> |
<!-- ********* Finish $comic ($comics->{$comic}{'fullName'}) ******* --> |
<!-- ********* Finish $comic ($comics->{$comic}{'fullName'}) ******* --> |
Line 166 sub writeMainIndex ($$) {
|
Line 237 sub writeMainIndex ($$) {
|
####################################################################### |
####################################################################### |
sub writeFooter { |
sub writeFooter { |
my ( $date ) = @_; |
my ( $date ) = @_; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} . |
my $sd = substr( join( '', $days[$date->{'dow'}] ), 0, 3 ); |
$date->{'day2'} . ".html"; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . |
|
$date->{'mon2'} . $date->{'day2'} . "-" . |
|
$sd . ".html"; |
my $sysDate = `date`; |
my $sysDate = `date`; |
|
|
open INDEX, ">>$indexFile"; |
open INDEX, ">>$indexFile"; |
Line 176 sub writeFooter {
|
Line 249 sub writeFooter {
|
<center> |
<center> |
<font size="2"> |
<font size="2"> |
Generated on: <font color="green">$sysDate</font><br/> |
Generated on: <font color="green">$sysDate</font><br/> |
Version: <font color="green">$ver</font></font> |
Version: <font color="green">$ver</font><br /> |
|
Config Version: <font color="green">$comicConfigVer</font><br /> |
|
CVS: <a href="http://demandred.dyndns.org/cgi-bin/cvsweb/comics/">http://demandred.dyndns.org/cgi-bin/cvsweb/comics/</a> |
<p> |
<p> |
<a href="http://validator.w3.org/check?uri=referer"><img |
<a href="http://validator.w3.org/check?uri=referer"><img |
src="http://www.w3.org/Icons/valid-xhtml10-blue" alt="Valid XHTML 1.0 Transitional" height="31" width="88" border="0" /></a> |
src="http://www.w3.org/Icons/valid-xhtml10-blue" alt="Valid XHTML 1.0 Transitional" height="31" width="88" border="0" /></a> |
Line 203 sub checkDir ($$) {
|
Line 278 sub checkDir ($$) {
|
####################################################################### |
####################################################################### |
sub writeTitle ($$) { |
sub writeTitle ($$) { |
my ( $date ) = @_; |
my ( $date ) = @_; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} . |
my $sd = substr( join( '', $days[$date->{'dow'}] ), 0, 3 ); |
$date->{'day2'} . ".html"; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . |
my $today = $date->{'mon'} . "/" . $date->{'day'} . "/" . $date->{'year'}; |
$date->{'mon2'} . $date->{'day2'} . "-" . |
|
$sd . ".html"; |
|
my $today = $days[$date->{'dow'}] . " " . $date->{'mon'} . "/" . $date->{'day'} . "/" . $date->{'year'}; |
|
my $today_long = Date_to_Text_Long(Today()); |
|
|
open INDEX, ">$indexFile"; |
open INDEX, ">$indexFile"; |
print INDEX <<EOF; |
print INDEX <<EOF; |
Line 214 sub writeTitle ($$) {
|
Line 292 sub writeTitle ($$) {
|
<html xmlns="http://www.w3.org/1999/xhtml"> |
<html xmlns="http://www.w3.org/1999/xhtml"> |
<head> |
<head> |
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> |
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> |
|
<link href="/daily/comics/comics.css" type="text/css" rel="stylesheet" media="screen"> |
|
<link rel="shortcut icon" href="./favicon.ico"> |
<title>Daily Comics for $today</title> |
<title>Daily Comics for $today</title> |
</head> |
</head> |
<body bgcolor="#FFFFFF"> |
<body bgcolor="#FFFFFF"> |
<h1>Daily Comics for $today</h1> |
|
<table align="center" cellpadding="5" cellspacing="0"> |
<table align="center" cellpadding="5" cellspacing="0"> |
|
<tr><td> |
|
<table cellpadding="0" cellspacing="0" border="0"> |
|
<tr><td align="Left"><img src="images/daily_comics_heading01.png"></td></tr> |
|
<tr><td align="left">$today_long</td></tr> |
|
<tr><td> </td></tr> |
|
</td</tr> |
|
|
EOF |
EOF |
close (INDEX); |
close (INDEX); |
} |
} |
Line 235 sub directDownload ($$) {
|
Line 321 sub directDownload ($$) {
|
my $cDir = $date->{'mon2'} . $date->{'year2'}; |
my $cDir = $date->{'mon2'} . $date->{'year2'}; |
my $cDate = $date->{'day2'}; |
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 -q $file --referer=\"" . $comics->{$comic}{'url'} ."\" --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg"; |
|
|
return system($cmd); |
return system($cmd); |
} |
} |
|
|
Line 246 sub indexDownload ($$) {
|
Line 333 sub indexDownload ($$) {
|
my ( @lines, $comicLine, $mainURL ); |
my ( @lines, $comicLine, $mainURL ); |
my $comicIndex = "indexes/index.$comic"; |
my $comicIndex = "indexes/index.$comic"; |
|
|
`wget -q $comics->{$comic}{'url'} -O $comicIndex`; |
my $wget_cmd = "wget -q --referer=\"$comics->{$comic}{'url'}\" " . |
|
"--user-agent=\"$USER_AGENT\" " . |
|
"$comics->{$comic}{'url'} -O $comicIndex"; |
|
system($wget_cmd); |
|
|
if ( ! open FILEN, "<$comicIndex" ) { |
if ( ! open FILEN, "<$comicIndex" ) { |
return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} . |
return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} . |
Line 266 sub indexDownload ($$) {
|
Line 356 sub indexDownload ($$) {
|
## Find the comic strip URL based on the specified regex in the search |
## Find the comic strip URL based on the specified regex in the search |
## |
## |
foreach my $line (@lines) { |
foreach my $line (@lines) { |
if ( $line =~ m/$comics->{$comic}{'search'}/ ) { |
if ( $line =~ m/$comics->{$comic}{'search'}/i ) { |
$comicLine = $1; chomp $comicLine; |
$comicLine = $1; chomp $comicLine; |
} |
} |
} |
} |
|
|
## |
## |
## Save the file to the appropriate directory |
## Save the file to the appropriate directory |
Line 280 sub indexDownload ($$) {
|
Line 370 sub indexDownload ($$) {
|
if ( $comicLine ) { |
if ( $comicLine ) { |
if ( $comicLine =~ m/(gif|jpg|png)/i ) { $comics->{$comic}{'ext'} = $1; } |
if ( $comicLine =~ m/(gif|jpg|png)/i ) { $comics->{$comic}{'ext'} = $1; } |
my $comicURL = ( $comicLine =~ m/http/ ) ? $comicLine : $mainURL . $comicLine; |
my $comicURL = ( $comicLine =~ m/http/ ) ? $comicLine : $mainURL . $comicLine; |
my $cmd = "wget --user-agent=\"$USER_AGENT\" --referer=\"" . $comics->{$comic}{'url'} . "\" -q $comicURL -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg"; |
my $cmd = "wget --user-agent=\"$USER_AGENT\" --referer=\"" . $comics->{$comic}{'url'} . "\" -q $comicURL -O images/$cDir/$comic-$cDate.$comics->{$comic}{'ext'}"; |
system( $cmd ); |
system( $cmd ); |
return 0; |
return 0; |
} |
} |
Line 313 sub parseComic ($$) {
|
Line 403 sub parseComic ($$) {
|
sub fetchDates () { |
sub fetchDates () { |
my %dates = (); |
my %dates = (); |
|
|
($dates{'day'}, $dates{'mon'}, $dates{'year'}, $dates{'dow'}) = (localtime)[3,4,5,6]; |
($dates{'day'}, $dates{'mon'}, $dates{'year'}, $dates{'dow'}) = (localtime(time - (86400 * $days_ago )))[3,4,5,6]; |
|
|
## If you missed a day or two, reflect it here: |
|
# $dates{'day'}-=1; ## <-- 5 days ago |
|
|
|
$dates{'year'} += 1900; |
$dates{'year'} += 1900; |
$dates{'year2'} = substr $dates{'year'}, 2, 2; |
$dates{'year2'} = substr $dates{'year'}, 2, 2; |
$dates{'day2'} = ( $dates{'day'} < 10 ) ? "0" . $dates{'day'} : $dates{'day'}; |
$dates{'day2'} = ( $dates{'day'} < 10 ) ? "0" . $dates{'day'} : $dates{'day'}; |
$dates{'mon'}++; |
$dates{'mon'}++; |
$dates{'mon2'} = ( $dates{'mon'} < 10 ) ? "0".$dates{'mon'} : $dates{'mon'}; |
$dates{'mon2'} = ( $dates{'mon'} < 10 ) ? "0".$dates{'mon'} : $dates{'mon'}; |
|
my @days = qw/ Sunday Monday Tuesday Wednesday Thursday Friday Saturday /; |
|
$dates{'wday'} = $days[$dates{'dow'}]; |
|
|
return %dates; |
return %dates; |
} |
} |
|
|
|
############################################################################### |
|
## |
|
## &fetchOptions( ); |
|
## |
|
## Grab our command line arguments and toss them in to a hash |
|
## |
|
############################################################################### |
|
sub fetchOptions { |
|
my %opts; |
|
|
|
&GetOptions( |
|
"days:i" => \$opts{'days'}, |
|
"help|?" => \$opts{'help'}, |
|
"man" => \$opts{'man'}, |
|
) || &pod2usage( ); |
|
&pod2usage( ) if defined $opts{'help'}; |
|
&pod2usage( { -verbose => 2, -input => \*DATA } ) if defined $opts{'man'}; |
|
|
|
return %opts; |
|
} |
|
|
|
__END__ |
|
|
|
=head1 NAME |
|
|
|
fetch.pl - Fetches comics and places them all locally in a single html file. |
|
|
|
=head1 SYNOPSIS |
|
|
|
fetch.pl [options] |
|
|
|
Options: |
|
--days,d Fetch comics from X days ago |
|
--help,? Display the basic help menu |
|
--man,m Display the detailed man page |
|
|
|
=head1 DESCRIPTION |
|
|
|
=head1 HISTORY |
|
|
|
=head1 AUTHOR |
|
|
|
Nicholas DeClario <nick@declario.com> |
|
|
|
=head1 BUGS |
|
|
|
This is a work in progress. Please report all bugs to the author. |
|
|
|
=head1 SEE ALSO |
|
|
|
=head1 COPYRIGHT |
|
|
|
=cut |
|
|
|
|