1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
package XML::RSS::Headline::Fark;
use strict;
use warnings;
use base qw(XML::RSS::Headline);
use URI::Escape qw(uri_unescape);
=head1 NAME
XML::RSS::Headline::Fark - XML::RSS::Headline Example Subclass
=head1 VERSION
2.2
=cut
our $VERSION = 2.2;
=head1 SYNOPSIS
Strip out the extra Fark redirect URL and strip out the various [blahblah]
blocks in the headline
use XML::RSS::Feed;
use XML::RSS::Headline::Fark;
use LWP::Simple qw(get);
my $feed = XML::RSS::Feed->new(
name => "fark",
url => "http://www.pluck.com/rss/fark.rss",
hlobj => "XML::RSS::Headline::Fark",
);
while (1) {
$feed->parse(get($feed->url));
print $_->headline . "\n" for $feed->late_breaking_news;
sleep($feed->delay);
}
Here is the before output in #news on irc.perl.org
<rssbot> - [Sad] Elizabeth Edwards diagnosed with breast cancer
<rssbot> http://go.fark.com/cgi/fark/go.pl?IDLink=1200026&location=http://www.msnbc.msn.com/id/6408022
and here is the updated output
<rssbot> - Elizabeth Edwards diagnosed with breast cancer
<rssbot> http://www.msnbc.msn.com/id/6408022
=head1 MUTAITED METHOD
=over 4
=item B<< $headline->item( $item ) >>
Init the object for a parsed RSS item returned by L<XML::RSS>.
=back
=cut
sub item {
my ( $self, $item ) = @_;
$self->SUPER::item($item); # set url and description
my $headline = $self->headline;
$headline =~ s/\[.+?\]\s+//;
$self->headline($headline);
my $url = $self->url;
my $stripit = qr/
http\:\/\/
go\.fark\.com\/
cgi\/fark\/go\.pl\?
IDLink\=\d+\&
location\=
/x;
$url =~ s/$stripit//;
$self->url( uri_unescape($url) );
}
=head1 AUTHOR
Jeff Bisbee, C<< <jbisbee at cpan.org> >>
=head1 BUGS
Please report any bugs or feature requests to
C<bug-xml-rss-feed at rt.cpan.org>, or through the web interface at
L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=XML-RSS-Feed>.
I will be notified, and then you'll automatically be notified of progress on
your bug as I make changes.
=head1 SUPPORT
You can find documentation for this module with the perldoc command.
perldoc XML::RSS::Headline::Fark
You can also look for information at:
=over 4
=item * AnnoCPAN: Annotated CPAN documentation
L<http://annocpan.org/dist/XML-RSS-Feed>
=item * CPAN Ratings
L<http://cpanratings.perl.org/d/XML-RSS-Feed>
=item * RT: CPAN's request tracker
L<http://rt.cpan.org/NoAuth/Bugs.html?Dist=XML-RSS-Feed>
=item * Search CPAN
L<http://search.cpan.org/dist/XML-RSS-Feed>
=back
=head1 ACKNOWLEDGEMENTS
Special thanks to Rocco Caputo, Martijn van Beers, Sean Burke, Prakash Kailasa
and Randal Schwartz for their help, guidance, patience, and bug reports. Guys
thanks for actually taking time to use the code and give good, honest feedback.
=head1 COPYRIGHT & LICENSE
Copyright 2006 Jeff Bisbee, all rights reserved.
This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.
=head1 SEE ALSO
L<XML::RSS::Feed>, L<XML::RSS::Headline>, L<XML::RSS::Headline::PerlJobs>, L<XML::RSS::Headline::UsePerlJournals>, L<POE::Component::RSSAggregator>
=cut
1;
|
