lyadmin/perl-script/bookdl.pl

118 lines
2.1 KiB
Perl

#!/usr/bin/perl
binmode STDOUT, ":utf8";
use warnings;
use strict;
use JSON;
my $DOMAIN;
my $THREAD_NO;
my $thread_no;
my $URL_PREFIX;
my $fn;
my $OUT_DIR;
my $USAGE;
my $ACMD;
my %jh;
my @a1;
$DOMAIN = "lainchan.org";
$URL_PREFIX = "https://$DOMAIN/lit/res/";
$OUT_DIR = "./dl/";
$USAGE = "Usage: bookdl.pl [http://someurl/]thread_id";
# die if no arguments
die "$USAGE" unless scalar @ARGV > 0;
$ACMD = $ARGV[0];
($thread_no) = $ACMD =~ /.*\/([0-9]+).{0,5}/;
# die if didnt provide thread number
die "$USAGE" unless $thread_no;
# Download the JSON from lainchan with list
# of book filenames
do {
my $url = $URL_PREFIX.$thread_no.".json";
printf("%s\n", $url);
`wget $url -O $thread_no.json`;
};
$fn = "$thread_no.json";
# Read JSON with list of files
open FILE, "<", $fn or die "could not open file";
do{
my $json_str;
local $/=undef;
$json_str = <FILE>;
chomp $json_str;
%jh = %{JSON->new()->decode($json_str)};
};
close FILE;
# Now we need to parse the JSON we just read
# into an array of tuples
# this anonymous function returns a list
# of tuples of the below form:
# (file_name, file_url)
@a1 = sub{
my @a0;
my @a2;
my $f1;
# filters for file types we
# dont want to downloads
sub f0 {
return $_[0]->{"ext"} &&
!($_[0]->{"ext"} =~ /jpe?g/) &&
!($_[0]->{"ext"} =~ /png/) &&
!($_[0]->{"ext"} =~ /gif/) &&
!($_[0]->{"ext"} =~ /webm/)
}
# create an array of files
# that meet our file ext requirement
# from the posts attribute
@a0 = grep {f0($_)} @{$jh{"posts"}};
# do the same filter on the
# extra_files attribute
@a2 = grep {
f0($_)
} map {
@{$_->{"extra_files"}}
} grep {
$_->{"extra_files"}
} @{$jh{"posts"}};
# Return our tuple
return map {
[
sprintf("%s%s", $_->{"filename"}, $_->{"ext"}), # file_name
sprintf("%s%s%s", $URL_PREFIX, $_->{"tim"}, $_->{"ext"}) # file_url
]
} (@a0, @a2);
}->();
# Print a list of wget commands from our tuples
for my $i1 (@a1){
printf("wget -nv -nc %s -O '%s%s'\n", scalar $i1->[1], $OUT_DIR, scalar $i1->[0]);
}