scrape-bug-summary

#!/usr/bin/perl -w

# $Id$
#
# Simple script to scrape the bug summaries from Bugzilla for inclusion in the changelog.
# 
# It will write out two files - a plain text for sending email, and an HTMLized version.

use strict;
use lib qw(CPAN);
use HTML::Entities;
use LWP::Simple;

sub main {

	my $url  = 'http://bugs.slimdevices.com/show_bug.cgi?id=%d';

	my $file = $ARGV[0] || die "Usage $0 <file>\n";

	open FH, $file or die $!;

	open OUTHTML, ">bugs.html" or die $!;
	open OUTTEXT, ">bugs.txt"  or die $!;

	while (my $bug = <FH>) {

		chomp $bug;

		print "Fetching summary for bug $bug..\n";

		my $content = get(sprintf($url, $bug));
		my $summary = '';

		for my $line (split /\n/, $content) {

			if ($line =~ m|Bug $bug: (.+?)</div>$|) {

				$summary = $1;
				last;
			}
		}

		unless ($summary) {
			print "Couldn't find a summary for bug $bug - please check it manually.\n";
		}

		printf(OUTTEXT "\t#%.4d - %s\n\n", $bug, decode_entities($summary));

		# <li><a href="http://bugs.slimdevices.com/show_bug.cgi?id=121">#121</a> - 
		printf(OUTHTML "\t\t<li><a href=\"%s\">#%.4d</a> - %s</li>\n", sprintf($url, $bug), $bug, $summary);
	}

	close FH;
	close OUTTEXT;
	close OUTHTML;
}

main();

__END__