#!/usr/bin/perl
# spurs2000.pl - avantgo spurs news
use LWP::Simple;
use HTML::Parser;
use Data::Dumper;
my $frontpage = get("http://www.spurs2000.com/") or die $!;
$frontpage =~ /(news_\w\w\w_\d\d\d\d)/;
my $newsdirmon = $1;
my $newsdirhtml = get("http://www.spurs2000.com/news/$newsdirmon/") or die $!;
# print $newsdirhtml;
sub starttag {
my($tagname, $attr) = @_;
if ($tagname eq 'a' && $attr->{href} =~ /news/) {
$newspage = $attr->{href};
}
}
sub endtag {
my($tagname) = @_;
}
my $newsidxhtml = get("http://www.spurs2000.com/news/$newsdirmon/");
# print $newsidxhtml;
my $p2 = HTML::Parser->new( api_version => 3,
start_h => [\&starttag2, "tagname, attr"],
end_h => [\&endtag, "tagname"],
marked_sections => 1,
);
$p2->parse($newsidxhtml);
my @newslinks;
sub starttag2 {
my($tagname, $attr) = @_;
if ($tagname eq 'a' && $attr->{href} =~ /news2/) {
push @newslinks, $attr->{href};
}
}
@newslinks = reverse(@newslinks); # most recent first
# print Dumper(\@newslinks);
my @headlines;
my $dateseen = 0;
# get each headline
foreach my $newslink (@newslinks) {
my $story = get("http://www.spurs2000.com/news/$newsdirmon/$newslink");
my $p3 = HTML::Parser->new( api_version => 3,
# start_h => [\&starttag3, "tagname, attr"],
# end_h => [\&endtag, "tagname"],
text_h => [\&text, "dtext"],
marked_sections => 1,
);
$p3->parse($story);
# print $newslink;
}
sub starttag3 {
my($tagname, $attr) = @_;
}
sub text {
my($origtext, $a2) = @_;
# print "====$a2====\n";
# print $origtext . "\n---------------------------\n";
if ($origtext =~ m#\d\d/\d\d/\d\d\d\d#si) {
# print "DATESEEN $origtext\n";
$dateseen = 1;
} elsif (($dateseen == 1) && ($origtext !~ /^\s+$/)) {
push @headlines, $origtext;
$dateseen = 0;
}
}
# print Dumper(\@headlines);
print 'Spurs 2000 HeadlinesSpurs 2000 Headlines
';
foreach (@headlines) {
my $newslink = shift @newslinks;
print "$_
\n";
}
print '';