From: Don Armstrong <don@donarmstrong.com>
Date: Fri, 16 Apr 2010 04:22:28 +0000 (+0000)
Subject: handle manga escapes in get_one_manga
X-Git-Url: https://git.donarmstrong.com/?a=commitdiff_plain;h=d4e59a710e1c3033c1c815904d876a368723892e;p=bin.git

handle manga escapes in get_one_manga
---

diff --git a/get_one_manga b/get_one_manga
index cc0cbd0..9bc60aa 100755
--- a/get_one_manga
+++ b/get_one_manga
@@ -49,6 +49,7 @@ Display this manual.
 =cut
 
 
+use URI::Escape;
 use WWW::Mechanize;
 use IO::Dir;
 use IO::File;
@@ -102,6 +103,8 @@ for my $manga (@manga_to_get) {
 	mkdir($manga);
     }
     # figure out where to start getting stuff
+    # we need to escape ! apparently; there are probably other characters as well
+    my $manga_escaped = uri_escape($manga,'!');
     my @chapter_links = $m->find_all_links(url_abs_regex => qr{\Q$manga\E\/\d+});
     for my $chapter_link (reverse @chapter_links) {
 	my ($chapter) = $chapter_link->url() =~ m/([\d.-]+)\/?$/;
@@ -114,7 +117,7 @@ for my $manga (@manga_to_get) {
 	    mm_get($m,$link->url_abs());
 	    while ($m->uri() =~ m{\Q$chapter\E/(\d\d[^\/]*)/?$}) {
 		my $image = $m->find_image(alt_regex => qr{Loading\.+\s+media});
-		my $next_link = $m->find_link(url_regex => qr{\Q$manga\E/\Q$chapter\E/(\d\d[^\/]*)});
+		my $next_link = $m->find_link(url_regex => qr{\Q$manga_escaped\E/\Q$chapter\E/(\d\d[^\/]*)});
 		mm_get($m,$image->url_abs());
 		print "getting ".$image->url_abs()."\n";
 		my ($page) = $image->url_abs =~ m/([^\/]+)$/;