Created
September 21, 2012 07:55
-
-
Save ryochin/3760259 to your computer and use it in GitHub Desktop.
recover incomplete feed url for Fresh Reader broken OPML
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl -- | |
# fill real rss feed url for Fresh Reader broken OPML | |
use strict; | |
use warnings; | |
use Path::Class qw(file); | |
use CGI; | |
use Feed::Find; | |
use utf8; | |
use Encode (); | |
my $file = shift @ARGV or die; | |
my $fh = file( $file )->openr or die $!; | |
my $n = 0; | |
while( defined( my $line = $fh->getline ) ){ | |
chomp $line; | |
$line = Encode::decode_utf8( $line ); | |
$n++; | |
if( $line !~ m{xmlUrl="(.+?(rss|xml|atom|rdf|opml)|(/(feed|rss)/?))"} ){ # " | |
if( $line !~ /Delicious/ and $line =~ s{xmlUrl="([^"]+?)"}{xmlUrl="__URL__"}o ){ # " | |
my $url = $1; | |
if( my @feed = Feed::Find->find( $url ) ){ | |
my $feed = CGI::escapeHTML( $feed[0] ); | |
$line =~ s{__URL__}{$feed}; | |
} | |
else{ | |
( my $title = $line ) =~ s{^.+?text="([^"]+?)".+?$}{$1}; # " | |
printf STDERR "feed not found: %d: %s: %s\n", $n, Encode::encode_utf8( $title ), $url; | |
next; | |
} | |
} | |
} | |
print Encode::encode_utf8( $line ), "\n"; | |
} | |
__END__ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment