geturl

#!/usr/bin/perl

# geturl url
#   Yet another quick hack, this time to fetch all of the data at
#   a URL.

# +------+-----------------------------------------------------------
# | Main |
# +------+

# Grab the parameter
my $url = $ARGV[0];

# Grab time info in a way useful for output
my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);
$year += 1900;
$mon += 1;
if ($mon < 10) { $mon = "0$mon"; }
if ($mday < 10) { $mday = "0$mday"; }
if ($hour < 10) { $hour = "0$hour"; }
if ($min < 10) { $min = "0$min"; }
if ($sec < 10) { $sec = "0$sec"; }

# Generate a directory name
my $prefix = $url;
$prefix =~ s/http:\/\///;
$prefix =~ s/https:\/\///;
$prefix =~ s/[^A-Za-z0-9-_.]/_/g;

my $dir = "$prefix-$year$mon$mday$hour$min$sec";
print STDERR "DIR is $dir\n";

my $command = "cd pages; mkdir $dir; cd $dir; wget --no-clobber --page-requisites --adjust-extension --convert-links --restrict-file-names=unix '$url'";
print STDERR "Command is $command\n";