version 1.9, 2013/02/25 13:48:21
|
version 1.26, 2018/04/22 14:03:54
|
Line 1
|
Line 1
|
#!/usr/bin/perl -w |
#!/usr/bin/perl -w |
|
|
|
############################################################################### |
|
# $Log$ |
|
# Revision 1.26 2018/04/22 14:03:54 nick |
|
# Changed the default for Sunday comics that was causing issues with some comics. |
|
# |
|
# Revision 1.25 2018/02/12 13:30:58 nick |
|
# Added an easier to compare date string to determine if the status json file was updated today and report if it wasn't. |
|
# |
|
# Revision 1.24 2018/02/06 14:31:06 nick |
|
# A status report is now generated in JSON that can easily be scanned so that |
|
# I can be alerted when there are failures that I miss if I don't read the |
|
# comics that day. |
|
# |
|
# Revision 1.23 2018/01/26 13:05:27 nick |
|
# Added a new config option to remove all newline from the resulting index.html |
|
# file. This allows for easier parsing for certain comics. I then updated |
|
# the URLs to search for and enabled the newline removal for a handful |
|
# of uComics. |
|
# |
|
# I believe I've also properly fixed the Comic Config version displayed on |
|
# the webpage itself. |
|
# |
|
# 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 Pod::Usage; |
use Getopt::Long; |
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/; |
|
|
## |
## |
## 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 $reportFile = "/home/httpd/html/daily/comics/status_report.json"; |
my %comics = &readComicConfig ( $comicFile ); |
my %comics = &readComicConfig ( $comicFile ); |
my %opts = &fetchOptions( ); |
my %opts = &fetchOptions( ); |
my $days_ago = $opts{'days'} || 0; |
my $days_ago = $opts{'days'} || 0; |
Line 22 my $indexDir = $baseDir . "/" . ( $co
|
Line 74 my $indexDir = $baseDir . "/" . ( $co
|
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 @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 34 print STDOUT "Starting comic fetch at $D
|
Line 85 print STDOUT "Starting comic fetch at $D
|
&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}{'not_sunday'} == 1)) { |
|
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 ); |
} |
|
|
|
print "Finding in $imageDir/*-$dates{'day2'}.jpg\n"; |
my $file = "$imageDir/$comic-$dates{'day2'}.$comics{$comic}{'ext'}"; |
foreach my $file ( glob( "$imageDir/*-$dates{'day2'}.jpg" ) ) |
my $size = 0; |
{ |
|
my $size = `/usr/bin/identify $file`; |
my $cmd = "/usr/bin/identify -verbose $file|"; |
$size =~ s/.*\s(\d+)x\d+.*/$1/; |
open(IMG, $cmd) || die ("Can't open: $!\n"); |
|
while(<IMG>) { |
|
if ($_ =~ 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 53 foreach my $file ( glob( "$imageDir/*-$d
|
Line 125 foreach my $file ( glob( "$imageDir/*-$d
|
|
|
&writeFooter( \%dates ); |
&writeFooter( \%dates ); |
|
|
|
print STDOUT "Status written to $reportFile.\n" |
|
if (&writeStatusReportJSON(\%comics, $reportFile)); |
|
|
$DATE=`date`; chomp( $DATE ); |
$DATE=`date`; chomp( $DATE ); |
print STDOUT "Completed comic fetch at $DATE\n"; |
print STDOUT "Completed comic fetch at $DATE\n"; |
|
|
Line 92 sub readComicConfig ($$) {
|
Line 167 sub readComicConfig ($$) {
|
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/^#.* \$[Ii][Dd]: fetch.pl.new,v 1.23 2018/01/26 13:05:27 nick Exp $/) { |
|
if ($_ =~ m/^#.* \$[Ii][dD]: .*,v\ (.*)\ \d{4}\/.*\$$/) { |
|
$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]}{'not_sunday'} = sprintf("%d", $res[6] || 0); |
|
$comicConfig{$res[0]}{'sunday_only'} = sprintf("%d", $res[7] || 0); |
|
$comicConfig{$res[0]}{'remove_newlines'} = sprintf("%d", $res[8] || 0); |
$comicConfig{$res[0]}{'error'} = 0; |
$comicConfig{$res[0]}{'error'} = 0; |
} |
} |
elsif ( $_ =~ m/(.*)\s+=\s+(.*)/ ) { |
elsif ( $_ =~ m/(.*)\s+=\s+(.*)/ ) { |
Line 114 sub readComicConfig ($$) {
|
Line 205 sub readComicConfig ($$) {
|
|
|
####################################################################### |
####################################################################### |
####################################################################### |
####################################################################### |
|
sub writeStatusReportJSON ($$) { |
|
my ( $comicsRef, $filename ) = @_; |
|
my %comics = %$comicsRef; |
|
my $shortDate = sprintf("%d%02d%02d", (localtime)[5] + 1900, |
|
(localtime)[4] + 1, |
|
(localtime)[3]); |
|
my %json = ('date' => $shortDate, 'comics' => []); |
|
my $totalErrors = 0; |
|
|
|
foreach my $comic (sort keys %comics) { |
|
next unless $comics{$comic}{'fullName'}; |
|
if ($comics{$comic}{'error'}) { |
|
my %error = ('comicName' => "$comics{$comic}{'fullName'}", |
|
'error' => "$comics{$comic}{'error'}", |
|
'status' => "Error"); |
|
push $json{'comics'}, \%error; |
|
$totalErrors += 1; |
|
} else { |
|
my %status = ('comicName' => "$comics{$comic}{'fullName'}", |
|
'error' => 0, |
|
'status' => "Successfull"); |
|
push $json{'comics'}, \%status; |
|
} |
|
} |
|
$json{'totalErrors'} = $totalErrors; |
|
|
|
open SR, ">$filename" or die ("ERROR: Failed to create status report: $!\n"); |
|
print SR create_json (\%json); |
|
close(SR); |
|
} |
|
|
|
####################################################################### |
|
####################################################################### |
sub writeComic ($$) { |
sub writeComic ($$) { |
my ( $comics, $comic, $date ) = @_; |
my ( $comics, $comic, $date ) = @_; |
my $indexFile = $indexDir . "/index-" . $days[$date->{'dow'}] . |
my $sd = substr( join( '', $days[$date->{'dow'}] ), 0, 3 ); |
"-" . $date->{'year2'} . $date->{'mon2'} . |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . |
$date->{'day2'} . ".html"; |
$date->{'mon2'} . $date->{'day2'} . "-" . |
|
$sd . ".html"; |
my $content = <<EOF; |
my $content = <<EOF; |
|
|
<!-- ********* Begin $comic ($comics->{$comic}{'fullName'}) ******* --> |
<!-- ********* Begin $comic ($comics->{$comic}{'fullName'}) ******* --> |
Line 130 sub writeComic ($$) {
|
Line 255 sub writeComic ($$) {
|
$comics->{$comic}{'url'} |
$comics->{$comic}{'url'} |
</a> |
</a> |
</font><br/> |
</font><br/> |
<img src="../images/$date->{'mon2'}$date->{'year2'}/$comic-$date->{'day2'}.jpg" alt="$comic-$date->{'day2'}" /> |
<img src="../images/$date->{'mon2'}$date->{'year2'}/$comic-$date->{'day2'}.$comics->{$comic}{'ext'}" alt="$comic-$date->{'day2'}" /> |
<br/><br/> |
<br/><br/> |
</td></tr> |
</td></tr> |
<!-- ********* Finish $comic ($comics->{$comic}{'fullName'}) ******* --> |
<!-- ********* Finish $comic ($comics->{$comic}{'fullName'}) ******* --> |
Line 171 sub writeMainIndex ($$) {
|
Line 296 sub writeMainIndex ($$) {
|
####################################################################### |
####################################################################### |
sub writeFooter { |
sub writeFooter { |
my ( $date ) = @_; |
my ( $date ) = @_; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} . |
my $sd = substr( join( '', $days[$date->{'dow'}] ), 0, 3 ); |
$date->{'day2'} . ".html"; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . |
|
$date->{'mon2'} . $date->{'day2'} . "-" . |
|
$sd . ".html"; |
my $sysDate = `date`; |
my $sysDate = `date`; |
|
|
open INDEX, ">>$indexFile"; |
open INDEX, ">>$indexFile"; |
Line 182 sub writeFooter {
|
Line 309 sub writeFooter {
|
<font size="2"> |
<font size="2"> |
Generated on: <font color="green">$sysDate</font><br/> |
Generated on: <font color="green">$sysDate</font><br/> |
Version: <font color="green">$ver</font><br /> |
Version: <font color="green">$ver</font><br /> |
|
Config Version: <font color="green">$comicConfigVer</font><br /> |
CVS: <a href="http://demandred.dyndns.org/cgi-bin/cvsweb/comics/">http://demandred.dyndns.org/cgi-bin/cvsweb/comics/</a> |
CVS: <a href="http://demandred.dyndns.org/cgi-bin/cvsweb/comics/">http://demandred.dyndns.org/cgi-bin/cvsweb/comics/</a> |
<p> |
<p> |
<a href="http://validator.w3.org/check?uri=referer"><img |
<a href="http://validator.w3.org/check?uri=referer"><img |
Line 209 sub checkDir ($$) {
|
Line 337 sub checkDir ($$) {
|
####################################################################### |
####################################################################### |
sub writeTitle ($$) { |
sub writeTitle ($$) { |
my ( $date ) = @_; |
my ( $date ) = @_; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} . |
my $sd = substr( join( '', $days[$date->{'dow'}] ), 0, 3 ); |
$date->{'day2'} . ".html"; |
my $indexFile = $indexDir . "/index-" . $date->{'year2'} . |
|
$date->{'mon2'} . $date->{'day2'} . "-" . |
|
$sd . ".html"; |
my $today = $days[$date->{'dow'}] . " " . $date->{'mon'} . "/" . $date->{'day'} . "/" . $date->{'year'}; |
my $today = $days[$date->{'dow'}] . " " . $date->{'mon'} . "/" . $date->{'day'} . "/" . $date->{'year'}; |
|
my $today_long = Date_to_Text_Long(Today()); |
|
|
open INDEX, ">$indexFile"; |
open INDEX, ">$indexFile"; |
print INDEX <<EOF; |
print INDEX <<EOF; |
Line 220 sub writeTitle ($$) {
|
Line 351 sub writeTitle ($$) {
|
<html xmlns="http://www.w3.org/1999/xhtml"> |
<html xmlns="http://www.w3.org/1999/xhtml"> |
<head> |
<head> |
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> |
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> |
|
<link href="/daily/comics/comics.css" type="text/css" rel="stylesheet" media="screen"> |
|
<link rel="shortcut icon" href="./favicon.ico"> |
<title>Daily Comics for $today</title> |
<title>Daily Comics for $today</title> |
</head> |
</head> |
<body bgcolor="#FFFFFF"> |
<body bgcolor="#FFFFFF"> |
<h1>Daily Comics for $today</h1> |
|
<table align="center" cellpadding="5" cellspacing="0"> |
<table align="center" cellpadding="5" cellspacing="0"> |
|
<tr><td> |
|
<table cellpadding="0" cellspacing="0" border="0"> |
|
<tr><td align="Left"><img src="images/daily_comics_heading01.png"></td></tr> |
|
<tr><td align="left">$today_long</td></tr> |
|
<tr><td> </td></tr> |
|
</td</tr> |
|
|
EOF |
EOF |
close (INDEX); |
close (INDEX); |
} |
} |
Line 241 sub directDownload ($$) {
|
Line 380 sub directDownload ($$) {
|
my $cDir = $date->{'mon2'} . $date->{'year2'}; |
my $cDir = $date->{'mon2'} . $date->{'year2'}; |
my $cDate = $date->{'day2'}; |
my $cDate = $date->{'day2'}; |
|
|
my $cmd = "wget -q $file --referer=\"" . $comics->{$comic}{'url'} ."\" --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg"; |
my $cmd = "wget -q $file --referer=\"" . $comics->{$comic}{'url'} ."\" --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg"; |
|
|
return system($cmd); |
return system($cmd); |
} |
} |
|
|
Line 252 sub indexDownload ($$) {
|
Line 392 sub indexDownload ($$) {
|
my ( @lines, $comicLine, $mainURL ); |
my ( @lines, $comicLine, $mainURL ); |
my $comicIndex = "indexes/index.$comic"; |
my $comicIndex = "indexes/index.$comic"; |
|
|
`wget -q $comics->{$comic}{'url'} -O $comicIndex`; |
my $wget_cmd = "wget -q --referer=\"$comics->{$comic}{'url'}\" " . |
|
"--user-agent=\"$USER_AGENT\" " . |
|
"$comics->{$comic}{'url'} -O $comicIndex"; |
|
system($wget_cmd); |
|
|
if ( ! open FILEN, "<$comicIndex" ) { |
if ( ! open FILEN, "<$comicIndex" ) { |
return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} . |
return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} . |
" (" . $comics->{$comic}{'url'} . ")"; |
" (" . $comics->{$comic}{'url'} . ")"; |
} |
} |
@lines = <FILEN>; |
while (<FILEN>) { |
|
my $line = $_; |
|
$line =~ s/\R|\ \ +|\t//g if ( $comics->{$comic}{'remove_newliens'} ); |
|
push @lines, $line; |
|
} |
close (FILEN); |
close (FILEN); |
|
|
unlink ("$comicIndex"); |
unlink ("$comicIndex"); |
Line 272 sub indexDownload ($$) {
|
Line 419 sub indexDownload ($$) {
|
## Find the comic strip URL based on the specified regex in the search |
## Find the comic strip URL based on the specified regex in the search |
## |
## |
foreach my $line (@lines) { |
foreach my $line (@lines) { |
if ( $line =~ m/$comics->{$comic}{'search'}/ ) { |
if ( $line =~ m/$comics->{$comic}{'search'}/i ) { |
$comicLine = $1; chomp $comicLine; |
$comicLine = $1; chomp $comicLine; |
} |
} |
} |
} |
|
|
## |
## |
## Save the file to the appropriate directory |
## Save the file to the appropriate directory |
Line 286 sub indexDownload ($$) {
|
Line 433 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 326 sub fetchDates () {
|
Line 473 sub fetchDates () {
|
$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; |
} |
} |