Return to errata_scraper.pl CVS log

Up to [local] / openbsd / errata_scraper

Annotation of openbsd/errata_scraper/errata_scraper.pl, Revision 1.5

1.1       andrew      1: #!/usr/bin/perl
1.5     ! andrew      2: # $AFresh1: errata_scraper.pl,v 1.4 2011/05/29 01:04:30 andrew Exp $
1.1       andrew      3: ########################################################################
                      4: # Copyright (c) 2011 Andrew Fresh <andrew@afresh1.com>
                      5: #
                      6: # Permission to use, copy, modify, and distribute this software for any
                      7: # purpose with or without fee is hereby granted, provided that the above
                      8: # copyright notice and this permission notice appear in all copies.
                      9: #
                     10: # THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
                     11: # WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
                     12: # MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
                     13: # ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
                     14: # WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
                     15: # ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
                     16: # OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
                     17: ########################################################################
                     18: use strict;
                     19: use warnings;
                     20:
1.2       andrew     21: use Mojo::UserAgent;
                     22:
1.3       andrew     23: my $base_uri = 'http://www.openbsd.org/';
1.2       andrew     24:
1.3       andrew     25: my $ua = Mojo::UserAgent->new;
                     26:
                     27: my $ls = $ua->get( $base_uri . 'errata.html' )->res->dom('a[href^="errata"]');
                     28:
                     29: foreach my $l ( @{$ls}[ -2, -1 ] ) {
                     30:     print 'Errata for OpenBSD ', $l->text, "\n";
                     31:     foreach my $e (
1.5     ! andrew     32:         reverse @{ $ua->get( $base_uri . $l->attr('href') )->res->dom('li')
1.3       andrew     33:         } )
                     34:     {
1.5     ! andrew     35:         my $title;
        !            36:         if (my $t = $e->at('strong')) {
        !            37:             $title = $t->all_text;
        !            38:             $t->replace('');
        !            39:         }
        !            40:         else {
        !            41:             next;
        !            42:         }
        !            43:         my $patch;
        !            44:         if (my $p = $e->at('a[href$=".patch.sig"],a[href$=".patch"]')) {
        !            45:             $patch = $p->attr('href');
        !            46:             $p->replace('');
        !            47:         }
        !            48:         my $arch = $e->at('i')->tap(sub { $_[0]->replace('') } )->text;
1.4       andrew     49:         my $descr = $e->all_text;
1.2       andrew     50:         $descr =~ s/\s+/ /gs;
1.4       andrew     51:         $descr =~ s/\s(\.(?:\s|$))/$1/gs;
                     52:         $descr =~ s/\.+$/./gs;
1.2       andrew     53:
                     54:         print 'Title: ', $title, "\n";
                     55:         print 'Arch:  ', $arch,  "\n";
1.5     ! andrew     56:         print 'Patch: ', $patch, "\n" if $patch;
1.2       andrew     57:         print 'Descr: ', $descr, "\n";
                     58:         print "\n";
1.1       andrew     59:     }
1.3       andrew     60: }