commit 70dfde6e6d1bc071379528ff85e97452ba341a7e
parent a09b98b4d50d664bce1dd9f206d4802754dd7abe
Author: René Wagner <rwagner@rw-net.de>
Date: Thu, 26 Nov 2020 16:42:45 +0100
strip HTML tags from description
this removes all tags, we might want to convert
<li> tags and links to gemini markup later
all other fields despite description are left as they are
Diffstat:
2 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
@@ -30,3 +30,6 @@ Fetching feeds from gemini is currently not supported -> https://todo.sr.ht/~rwa
- Perl >= 5.28 with modules
- URI::Escape
- XML::FeedPP
+ - DateTime
+ - DateTime::Format::ISO8601
+ - HTML::Strip
diff --git a/orrg.pl b/orrg.pl
@@ -1,16 +1,17 @@
#!/usr/bin/perl
# Copyright René Wagner 2020
# licenced under BSD 3-Clause licence
-# https://git.sr.ht/~rwa/willgemini.support
+# https://git.sr.ht/~rwa/orrg
use strict;
no warnings 'experimental';
use URI::Escape;
use XML::FeedPP;
+use HTML::Strip;
use DateTime;
use DateTime::Format::ISO8601;
use POSIX qw(strftime);
-use v5.10;
+
# enable UTF-8 mode for everything
use utf8;
binmode STDOUT, ':utf8';
@@ -78,7 +79,10 @@ sub create_response
push @body, 'published '. strftime('%Y-%m-%dT%H:%M:%SZ', gmtime($dt->epoch));
}
push @body, '';
- $it->description eq '' or push @body, $it->description;
+ if ($it->description ne '') {
+ my $hs = HTML::Strip->new();
+ push @body, $hs->parse($it->description);
+ }
$it->link eq '' or push @body, ('=> '.$it->link.' open entry in browser', '');
}