Fri, 24 Sep 2004 02:58:01 +0000
Mozilla Firefox Live Bookmark: convertidor
From the convierte-de-bookmarks.html-a-RSS dept. (7484)
Como ya es la tradición de Latinomixed.com, aquí les llega un script que convierte del archivo de Firefox bookmarks.html a un archivo tipo RSS que puede ser usado como Live Bookmark. Claro, abra aquellos que usaran páginas como del.icio.us para compartir sus bookmarks, pero para todos los demás este script puede servirles de uso. Noten que este lo hice en par de horas de hackeo y necesita unas cuantas cositas.
Telecargen el archivo completo de aquí.
Para usarlo necesitaras los módulos HTML::Parser y XML::RSS de CPAN
[Actualizado: 2004-11-22 17:25 EST] La nueva versión ha sido publicada y contiene todas las funciones que uno pudiera esperar. Ahora los enlaces tienen nombres completos y el código es mas limpio. Cojanlo de aquí. Luego se actualizará esta página para reflejar dichos cambios.
1t#!/usr/bin/perl -w
2t# 2004-09-22 21:57 EDT $Revision: 1.2 $
3t# Luis Mondesi
4t# Converts a bookmarks.html(firefox/mozilla/netscape) file
5t# to bookmarks.rss (1.0)
6t#
7t# There is no need to edit anything below. To run simply do:
8t#
9t# bookmark2rss.pl /path/to/bookmarks.html
10t#
11t# The resulting output will be printed to STDOUT
12t#
13t# TODO
14t# - should live bookmarks be included? hint: instead of "href" look for FEEDURL attribute
15t
16tuse strict;
17t$|++;
18t# standard Perl modules
19tuse Getopt::Long;
20tGetopt::Long::Configure('bundling');
21t# non-standard modules
22tuse HTML::Parser 3.00 ();
23tuse XML::RSS;
24t# create XML::RSS object
25tmy $rss = new XML::RSS (version => '1.0');
26t
27tmy $SITE = ""; # --site
28tmy $DESC = "My Bookmarks";
29tmy $DATE = ""; # TODO get date()
30tmy $SUBJECT = "bookmarks";
31tmy $CREATOR = ""; # --creator
32tmy $PUBLISHER = "$CREATOR";
33tmy $COPYRIGHT = "";
34tmy $LOCALE = "en-us"; # --language
35tmy $UPDATED = "daily"; # --update-period
36tmy $FREQ = "1"; # --update-frequency
37tmy $UPDATEBASE = "1901-01-01T00:00+00:00";
38tmy $OUTPUT="";
39t
40tGetOptions(
41t # flags
42t # strings
43t 's|site=s' => $SITE,
44t 'd|desc=s' => $DESC,
45t 'subject=s' => $SUBJECT,
46t 'creator=s' => $CREATOR, # email?
47t 'publisher=s' => $PUBLISHER,
48t 'copyright=s' => $COPYRIGHT,
49t 'l|language=s' => $LOCALE,
50t 'updated=s' => $UPDATED,
51t 'update-frequency=s' => $FREQ,
52t 'update-base' => $UPDATEBASE,
53t 'o|output=s' => $OUTPUT,
54t # numbers
55t);
56t
57tsub a_start_handler
58t{
59t my($self, $tag, $attr) = @_;
60t return unless $tag eq "a";
61t return unless exists $attr->;
62t
63t my $url = $attr->;
64t #print "A $urln";
65t # TODO get text as title for this link
66t #$bookmarks = $url;
67t $rss->add_item( title => "$url", link => "$url" );
68t
69t $self->handler(text => [], '@' );
70t $self->handler(start => &img_handler);
71t $self->handler(end => &a_end_handler, "self,tagname", $url);
72t}
73tsub img_handler
74t{
75t my($self, $tag, $attr) = @_;
76t return unless $tag eq "img";
77t push(@, $attr-> || "[IMG]");
78t}
79tsub a_end_handler
80t{
81t my($self, $tag) = @_;
82t my $text = join("", @);
83t $text =~ s/^s+//;
84t $text =~ s/s+$//;
85t $text =~ s/s+/ /g;
86t #print "T $textn";
87t
88t $self->handler("text", undef);
89t $self->handler("start", &a_start_handler);
90t $self->handler("end", undef);
91t}
92tsub add_items
93t{
94t #foreach my $url ( keys %bookmarks )
95t #{
96t # my $text = $bookmarks;
97t# $rss->add_item(
98t# title => "$url",
99t# link => "$url",
100t# description => "$text",
101t# dc => {
102t# subject => "Bookmark",
103t# creator => "Created by",
104t# },
105t# );
106t #}
107t}
108tsub usage_die
109t{
110t print STDERR "Usage: $0 bookmarks.htmln";
111t exit(1);
112t}
113t$rss->channel(
114t title => "$SITE",
115t link => "http://$SITE",
116t description => "$DESC",
117t dc => {
118t date => "$DATE",
119t subject => "$SUBJECT",
120t creator => "$CREATOR",
121t publisher => "$PUBLISHER",
122t rights => "$COPYRIGHT",
123t language => "$LOCALE",
124t },
125t syn => {
126t updatePeriod => "$UPDATED",
127t updateFrequency => "$FREQ",
128t updateBase => "$UPDATEBASE",
129t },
130t);
131t
132t# create a HTML::Parser object
133tmy $p = HTML::Parser->new(api_version => 3,
134t start_h => [&a_start_handler, "self,tagname,attr"],
135t report_tags => [qw(a img)],
136t );
137t$p->parse_file(shift || usage_die) || usage_die($!);
138t
139t# print RSS
140tif ( $OUTPUT ne "" )
141t{
142t ## It seems that this is buggy, it prints:
143t ## Wide character in print at /usr/share/perl5/XML/RSS.pm line 1606.
144t # $rss->save("$OUTPUT");
145t open (OUTPUT,">:utf8","$OUTPUT") || die $!;
146t print OUTPUT $rss->as_string;
147t close(OUTPUT);
148t} else {
149t print STDOUT $rss->as_string;
150t}
Advertisement
