From 707b4522d24729258442d1eb7c6a0b34ec3dc338 Mon Sep 17 00:00:00 2001
From: gashapwn <gashapwn@tildezero.lan>
Date: Mon, 29 Mar 2021 13:21:34 +0000
Subject: [PATCH] bookdl.pl - cleaned up filter function. added code to
 download thread. added comments

---
 perl-script/bookdl.pl | 61 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 36 insertions(+), 25 deletions(-)

diff --git a/perl-script/bookdl.pl b/perl-script/bookdl.pl
index 652d295..b90a7b2 100644
--- a/perl-script/bookdl.pl
+++ b/perl-script/bookdl.pl
@@ -7,10 +7,12 @@ use strict;
 
 use JSON;
 
+my $DOMAIN;
 my $THREAD_NO;
+my $thread_no;
 my $URL_PREFIX;
 
-my $FN;
+my $fn;
 my $OUT_DIR;
 
 my $USAGE;
@@ -21,23 +23,34 @@ my %jh;
 my @a1;
 
 $DOMAIN = "lainchan.org";
-# $URL_PREFIX = "https://lainchan.org/lit/src/";
-$URL_PREFIX = "https://$DOMAIN/lit/src/";
-$THREAD_NO = 4619;
-# $THREAD_NO = 6105;
-# $THREAD_NO = 4345;
-# $THREAD_NO = 4953;
-$FN = "$THREAD_NO.json";
+$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";
+open FILE, "<", $fn or die "could not open file";
 do{
     my $json_str;
 
@@ -50,7 +63,12 @@ do{
 };
 close FILE;
 
-# anonymous function that returns a list
+# 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{
@@ -61,24 +79,17 @@ close FILE;
 
     # filters for file types we
     # dont want to downloads
-    sub f1 {
-	return $_[0]->{"ext"} && !($_[0]->{"ext"} =~ /jpe?g/);
-    }
-    sub f2 {
-	return !($_[0]->{"ext"} =~ /png/);
-    }
-    sub f3 {
-	return !($_[0]->{"ext"} =~ /gif/);
-    }
-    sub f4 {
-	return !($_[0]->{"ext"} =~ /webm/);
-    }
     sub f0 {
-	return f1($_[0]) && f2($_[0]) && f3($_[0]) && f4($_[0])	
+	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
@@ -102,5 +113,5 @@ close FILE;
 
 # Print a list of wget commands from our tuples
 for my $i1 (@a1){
-    printf("wget -nc %s -O '%s%s'\n", scalar $i1->[1], $OUT_DIR, scalar $i1->[0]);
+    printf("wget -nv -nc %s -O '%s%s'\n", scalar $i1->[1], $OUT_DIR, scalar $i1->[0]);
 }