BlogAlba/scripts/old-rss-import-script

72 lines
2.4 KiB
Plaintext
Raw Normal View History

2015-03-08 22:11:15 +00:00
#!/usr/bin/env perl
# blog.Alba - no-frills markdown blogging system
package Maff::Blog::Import;
use strict;
use warnings;
use diagnostics;
use feature qw/say/;
use POSIX qw/strftime/;
use Date::Parse qw/str2time/;
use Encode qw/encode/;
use File::Spec;
use HTML::Entities qw/decode_entities/;
use HTML::WikiConverter;
use LWP::Simple qw/get/;
use URI::Escape qw/uri_unescape/;
use XML::RSS::Parser::Lite;
our (%blog,%links);
our $basedir=File::Spec->rel2abs(__FILE__);$basedir=~s/import\.pl$//;
my $cfg="$basedir/blog.conf";
unless(my $ret = do $cfg) {
die "Couldn't parse config file $cfg!" if $@;
die "Couldn't load config file $cfg!" unless defined $ret and $ret;
}
my $blogRSS="http://blog.maff.me.uk/feed/rss2";
sub writepost {
my ($file,$post)=@_;
open TPL, "<$basedir/post/.tpl.md" or warn "Couldn't open post $basedir/post/.tpl.md!" and return 0;
my ($title,$tags)=($post->get('title'),$post->get('category'));
my $date=timefmt($post->get('pubDate'));
my $slug=lc uri_unescape $1 if $post->get('url')=~/^.*(?:(?:\d{2})\/)+([\w\d%\.\/\-_\(\)]+)$/i;
$slug=~s/[%\d\/\.,\(\)]/-/g;$slug=~s/\-\-+/-/g;$slug=~s/\-*$//;$slug=lc $slug;
my $html2md=new HTML::WikiConverter(dialect => 'Markdown', encoding => 'utf8', escape_entities => 0);
my $body = $html2md->html2wiki(encode 'utf8', decode_entities $post->get('description'));$body=~s/^ / /gm;
my $md="";
while(<TPL>) {
s/\|ptitle\|/$title/;
s/\|ptags\|/$tags/;
s/\|pdate\|/$date/;
s/\|slug\|/$slug/;
next if /\|pbody\|/;
$md.=$_;
}
close TPL;$md.=$body;
open MD, ">$basedir/post/$file.md" or warn "Couldn't open post $basedir/post/$file.md" and return 0;
print MD $md;
close MD;
say "..converted to Markdown and saved to post/$file.md";
}
sub timefmt {
my ($epoch,$context)=@_;
$epoch=str2time $epoch;
return strftime "%Y-%m-%d %H:%M",localtime $epoch;
}
print "Fetching $blogRSS..";
my $origfeed=get($blogRSS) or die "Couldn't fetch $blogRSS";
$origfeed=~s/<\/category><category>/, /g;
my $parser=new XML::RSS::Parser::Lite;$parser->parse($origfeed);
say "found blog '".$parser->get('title')."'\nDescription: ".decode_entities $parser->get('description')."\nConverting to blog.Alba Markdown using template $basedir/post/.tpl.md.\n";
for(my $i=1;$i<=$parser->count();$i++) {
my $item=$parser->get($parser->count()-$i);
print "Found post ".$item->get('title');
writepost $i, $item;
}
say "Import complete. Please check all posts in $basedir/post/ and then run gen.pl to generate your new blog.";