#!/usr/bin/perl
#
# Blogs.pm:
# List of blogs and how to treat links coming off them.
#
# Copyright (c) 2002 Chris Lightfoot. All rights reserved.
# Email: chris@ex-parrot.com; WWW: http://www.ex-parrot.com/~chris/
#
# $Id: Blogs.pm,v 1.14 2003/03/24 23:48:26 chris Exp $
#

package BIMBO::Blogs;

use URI::URL;

%sites = (
    slashdot =>
        [
            # URL of site
            "http://slashdot.org/",
            # Short name of site
            "Slashdot",
            # Subroutine to accept/reject URLs.
            sub ($) {
                my $u = url($_[0]);
                return ($u->host !~ m#(animefu\.com|penny-arcade\.com|bigempire\.com|themes\.org|thinkgeek\.com|oldmanmurray\.|dice\.com|freshmeat\.net|slashdot\.org|osdn\.|cmdrtaco\.|sourceforge\.net|everything2\.com|doubleclick\.net)#i);
            }
        ],

    memepool =>
        [
            "http://memepool.com/",
            "Memepool",
            sub ($) {
                my $u = url($_[0]);
                return !($u->host =~ m#memepool\.com#i);
            }
        ],

    charliestross =>
        [
            "http://www.antipope.org/charlie/blosxom.cgi",
            "Charlie Stross's web log",
            sub ($) {
                my $u = url($_[0]);
                return ($_[0] !~ m#antipope\.org/charlie/blosxom\.cgi# and $u->host !~ m#quicktopic\.com#
                        # I'm sure the book is great but we don't want to buy it from here.
                        and $u->host !~ m#amazon\.(co\.uk|com)#         
                        # Who wants to read pages of Google search results?
                        and $u->host !~ m#www\.google\.(co\.uk|com)#);
            }
        ],

    megpickard =>
        [
            "http://www.notsosoft.com/blog/",
            "Meg Pickard's web log",
            sub ($) {
                # Only external links.
                return ($_[0] !~ m#^http://.*notsosoft\.com/#);
            }
        ],

    bbcnews =>
        [
            "http://news.bbc.co.uk/2/low.html",
            "BBC World News",
            sub ($) {
                # only news stories within the BBC.
                return ($_[0] =~ m#^http://news.bbc.co.uk/2/low/[^/]+/\d+.stm#);
            }
        ],

    b3ta =>
        [
            "http://www.b3ta.com/",
            "B Three T A",
            sub ($) {
                my $u = url($_[0]);
                return !($u->host =~ m#b3ta\.com#i);
            }
        ],

    meghourihan =>
        [
            "http://www.megnut.com/",
            "Meg Hourihan's web log",
            sub ($) {
                my $u = url($_[0]);
                return !($u->host =~ m#megnut\.com#i
                         or $u->host =~ /amazon/); # sod buying books
            }
        ],

    salon =>
        [
            "http://www.salon.com/",
            "Salon magazine",
            sub ($) {
                # only want Salon stories, which have a date in the URL.
                # looks like `Tom Tomorrow' is premium content, which sucks.
                return ($_[0] =~ m#http://www.salon.com/.*/\d\d\d\d/\d\d/\d\d#
                        and $_[0] !~ m# http://www\.salon\.com/comics/tomo/#
                        and $_[0] !~ /print\.html$/ # don't want to grab both printable and non-printable version
                        and $_[0] !~ /index_np\.html$/); # ditch premium content
            }
        ],

    straightdope =>
        [
            "http://www.straightdope.com/",
            "The Straight Dope",
            sub ($) {
                return ($_[0] =~ m#http://www\.straightdope\.com/(mailbag|classics|columns)/.*\.html#);
            }
        ],

    slate =>
        [
            "http://slate.msn.com/",
            "Microsoft Slate",
            sub ($) {
                # only stories within Slate (the URL format has changed...)
                return ($_[0] =~ m#^http://slate\.msn\.com\/id\/\d+\/$#);
            }
        ],

    onlineblog =>
        [
            "http://www.onlineblog.com/",
            "Guardian Online web log",
            sub ($) {
                # only external links.
                my $u = url($_[0]);
                return ($u->host !~ /onlineblog\.com/i);
            }
        ],

    scottrosenberg =>
        [
            "http://blogs.salon.com/0000014/",
            "Scott Rosenberg's Links and Comment",
            sub ($) {
                # only external links
                my $u = url($_[0]);
                return ($u->host !~ /salon\.com$/);
            }
        ],

    usrbingirl =>
        [
            "http://www.stormwerks.com/linked/",
            "/usr/bin/girl",
            sub ($) {
                # only external links
                my $u = url($_[0]);
                return ($u->host !~ /stormwerks\.com$/);
            }
        ],

    newscientistnews =>
        [
            "http://www.newscientist.com/news/",
            "New Scientist news",
            sub ($) {
                return ($_[0] =~ m#newscientist\.com/news/news\.jsp\?id=ns\d+#);
            }
        ],

    wired =>
        [
            "http://www.wired.com/",
            "Wired",
            sub ($) {
                my $u = url($_[0]);
                # Wired stories and external links.
                return ($_[0] =~ m#^http://.*\.hotwired\.com/r/wn_html_link/http://www\.wired\.com/news/# or $u->host !~ /(doubleclick|wired|lycos)\.(com|net)/
                or $_[0] =~ m#^http://www\.wired\.com/news/.*\.html$#);
            }
        ],

    rebecca =>
        [
            "http://www.rebeccablood.net/",
            "What's in Rebecca's pocket?",
            sub ($) {
                my $u = url($_[0]);
                # Only external links.
                return ($u->host !~ /rebeccablood\.net$/);
            }
        ],

    googlenews =>
        [
            "http://news.google.com/",
            "Google News",
            sub ($) {
                my $u = url($_[0]);
                return ($u->host !~ /google\.com$/);
            }
        ],

    atlanticcurrent =>
        [
            "http://www.theatlantic.com/issues/current/",
            "The Atlantic Online (current issue)",
            sub ($) {
                return $_[0] =~ m#^http://www\.theatlantic\.com/issues/\d+/\d+/.*\.htm$#;
            }
        ],

    atlantic =>
        [
            "http://www.theatlantic.com/",
            "The Atlantic Online",
            sub ($) {
                return $_[0] =~ m#^http://www\.theatlantic\.com/(unbound|issues)/.*\.htm$#;
            }
        ],

    oblomovka =>
        [
            "http://www.oblomovka.com/",
            "Danny O'Brien's web log",
            sub ($) {
                my $u = url($_[0]);
                return ($u->host !~ /oblomovka\.com$/)
            }
        ],

    # OK. Blogging is a stupid popularity contest. So let's ``leverage'' MIT's
    # efforts to ``measure'' it.
    blogdex =>
        [
            "http://blogdex.media.mit.edu/",
            "MIT Blogdex",
            sub ($) {
                # only want links off blogdex....
                return ($_[0] !~ m#^http://blogdex\.media\.mit\.edu/#i
                        and $_[0] !~ m#^http://(www\.)?blogdex\.net/#i);
            }
        ],

    metafilter =>
        [
            "http://www.metafilter.com/",
            "MetaFilter",
            sub ($) {
                # links off metafilter
                return ($_[0] !~ m#^http://[^./]+\.metafilter\.com/#i);
            }
        ]
    );

1;