#!/usr/bin/perl -w
#
-# webcollage, Copyright (c) 1999-2011 by Jamie Zawinski <jwz@jwz.org>
+# webcollage, Copyright © 1999-2013 by Jamie Zawinski <jwz@jwz.org>
# This program decorates the screen with random images from the web.
# One satisfied customer described it as "a nonstop pop culture brainbath."
#
my $progname = $0; $progname =~ s@.*/@@g;
-my $version = q{ $Revision: 1.156 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
+my $version = q{ $Revision: 1.160 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
my $copyright = "WebCollage $version, Copyright (c) 1999-2011" .
" Jamie Zawinski <jwz\@jwz.org>\n" .
" http://www.jwz.org/webcollage/\n";
-my @search_methods = ( 24, "googlephotos", \&pick_from_google_image_photos,
- 13, "googleimgs", \&pick_from_google_images,
- 13, "googlenums", \&pick_from_google_image_numbers,
- 16, "flickr_recent", \&pick_from_flickr_recent,
- 13, "flickr_random", \&pick_from_flickr_random,
- 10, "twitpic", \&pick_from_twitpic_images,
- 8, "livejournal", \&pick_from_livejournal_images,
- 3, "yahoorand", \&pick_from_yahoo_random_link,
+my @search_methods = ( 26, "googlephotos", \&pick_from_google_image_photos,
+ 15, "googleimgs", \&pick_from_google_images,
+ 15, "googlenums", \&pick_from_google_image_numbers,
+ 17, "flickr_recent", \&pick_from_flickr_recent,
+ 14, "flickr_random", \&pick_from_flickr_random,
+# twitpic went stale. don't have time to fix it right now.
+# 10, "twitpic", \&pick_from_twitpic_images,
+ 9, "livejournal", \&pick_from_livejournal_images,
+ 4, "yahoorand", \&pick_from_yahoo_random_link,
# This one doesn't work very well: too many non-img links.
- 0, "twitter", \&pick_from_twitter_images,
+ 0, "twitter", \&pick_from_twitter_images,
# This is a cute way to search for a certain webcams.
# Not included in default methods, since these images
"ljplus.ru" => 1,
"yandex.ru" => 1,
"imgur.com" => 1,
+ "yfrog.com" => 1,
"yimg.com" => 1, # This is where dailynews.yahoo.com stores
"eimg.com" => 1, # its images, so pick_from_yahoo_news_text()
#
my %entity_table = (
"apos" => '\'',
- "quot" => '"', "amp" => '&', "lt" => '<', "gt" => '>',
- "nbsp" => ' ', "iexcl" => '¡', "cent" => '¢', "pound" => '£',
- "curren" => '¤', "yen" => '¥', "brvbar" => '¦', "sect" => '§',
- "uml" => '¨', "copy" => '©', "ordf" => 'ª', "laquo" => '«',
- "not" => '¬', "shy" => '', "reg" => '®', "macr" => '¯',
- "deg" => '°', "plusmn" => '±', "sup2" => '²', "sup3" => '³',
- "acute" => '´', "micro" => 'µ', "para" => '¶', "middot" => '·',
- "cedil" => '¸', "sup1" => '¹', "ordm" => 'º', "raquo" => '»',
- "frac14" => '¼', "frac12" => '½', "frac34" => '¾', "iquest" => '¿',
- "Agrave" => 'À', "Aacute" => 'Á', "Acirc" => 'Â', "Atilde" => 'Ã',
- "Auml" => 'Ä', "Aring" => 'Å', "AElig" => 'Æ', "Ccedil" => 'Ç',
- "Egrave" => 'È', "Eacute" => 'É', "Ecirc" => 'Ê', "Euml" => 'Ë',
- "Igrave" => 'Ì', "Iacute" => 'Í', "Icirc" => 'Î', "Iuml" => 'Ï',
- "ETH" => 'Ð', "Ntilde" => 'Ñ', "Ograve" => 'Ò', "Oacute" => 'Ó',
- "Ocirc" => 'Ô', "Otilde" => 'Õ', "Ouml" => 'Ö', "times" => '×',
- "Oslash" => 'Ø', "Ugrave" => 'Ù', "Uacute" => 'Ú', "Ucirc" => 'Û',
- "Uuml" => 'Ü', "Yacute" => 'Ý', "THORN" => 'Þ', "szlig" => 'ß',
- "agrave" => 'à', "aacute" => 'á', "acirc" => 'â', "atilde" => 'ã',
- "auml" => 'ä', "aring" => 'å', "aelig" => 'æ', "ccedil" => 'ç',
- "egrave" => 'è', "eacute" => 'é', "ecirc" => 'ê', "euml" => 'ë',
- "igrave" => 'ì', "iacute" => 'í', "icirc" => 'î', "iuml" => 'ï',
- "eth" => 'ð', "ntilde" => 'ñ', "ograve" => 'ò', "oacute" => 'ó',
- "ocirc" => 'ô', "otilde" => 'õ', "ouml" => 'ö', "divide" => '÷',
- "oslash" => 'ø', "ugrave" => 'ù', "uacute" => 'ú', "ucirc" => 'û',
- "uuml" => 'ü', "yacute" => 'ý', "thorn" => 'þ', "yuml" => 'ÿ',
+ "quot" => '"', "amp" => '&', "lt" => '<',
+ "gt" => '>', "nbsp" => ' ', "iexcl" => '',
+ "cent" => "\xA2", "pound" => "\xA3", "curren" => "\xA4",
+ "yen" => "\xA5", "brvbar" => "\xA6", "sect" => "\xA7",
+ "uml" => "\xA8", "copy" => "\xA9", "ordf" => "\xAA",
+ "laquo" => "\xAB", "not" => "\xAC", "shy" => "\xAD",
+ "reg" => "\xAE", "macr" => "\xAF", "deg" => "\xB0",
+ "plusmn" => "\xB1", "sup2" => "\xB2", "sup3" => "\xB3",
+ "acute" => "\xB4", "micro" => "\xB5", "para" => "\xB6",
+ "middot" => "\xB7", "cedil" => "\xB8", "sup1" => "\xB9",
+ "ordm" => "\xBA", "raquo" => "\xBB", "frac14" => "\xBC",
+ "frac12" => "\xBD", "frac34" => "\xBE", "iquest" => "\xBF",
+ "Agrave" => "\xC0", "Aacute" => "\xC1", "Acirc" => "\xC2",
+ "Atilde" => "\xC3", "Auml" => "\xC4", "Aring" => "\xC5",
+ "AElig" => "\xC6", "Ccedil" => "\xC7", "Egrave" => "\xC8",
+ "Eacute" => "\xC9", "Ecirc" => "\xCA", "Euml" => "\xCB",
+ "Igrave" => "\xCC", "Iacute" => "\xCD", "Icirc" => "\xCE",
+ "Iuml" => "\xCF", "ETH" => "\xD0", "Ntilde" => "\xD1",
+ "Ograve" => "\xD2", "Oacute" => "\xD3", "Ocirc" => "\xD4",
+ "Otilde" => "\xD5", "Ouml" => "\xD6", "times" => "\xD7",
+ "Oslash" => "\xD8", "Ugrave" => "\xD9", "Uacute" => "\xDA",
+ "Ucirc" => "\xDB", "Uuml" => "\xDC", "Yacute" => "\xDD",
+ "THORN" => "\xDE", "szlig" => "\xDF", "agrave" => "\xE0",
+ "aacute" => "\xE1", "acirc" => "\xE2", "atilde" => "\xE3",
+ "auml" => "\xE4", "aring" => "\xE5", "aelig" => "\xE6",
+ "ccedil" => "\xE7", "egrave" => "\xE8", "eacute" => "\xE9",
+ "ecirc" => "\xEA", "euml" => "\xEB", "igrave" => "\xEC",
+ "iacute" => "\xED", "icirc" => "\xEE", "iuml" => "\xEF",
+ "eth" => "\xF0", "ntilde" => "\xF1", "ograve" => "\xF2",
+ "oacute" => "\xF3", "ocirc" => "\xF4", "otilde" => "\xF5",
+ "ouml" => "\xF6", "divide" => "\xF7", "oslash" => "\xF8",
+ "ugrave" => "\xF9", "uacute" => "\xFA", "ucirc" => "\xFB",
+ "uuml" => "\xFC", "yacute" => "\xFD", "thorn" => "\xFE",
+ "yuml" => "\xFF",
# HTML 4 entities that do not have 1:1 Latin1 mappings.
- "bull" => "*", "hellip"=> "...", "prime" => "'", "Prime" => "\"",
- "frasl" => "/", "trade" => "[tm]", "larr" => "<-", "rarr" => "->",
- "harr" => "<->", "lArr" => "<=", "rArr" => "=>", "hArr" => "<=>",
- "empty" => "Ø", "minus" => "-", "lowast"=> "*", "sim" => "~",
- "cong" => "=~", "asymp" => "~", "ne" => "!=", "equiv" => "==",
- "le" => "<=", "ge" => ">=", "lang" => "<", "rang" => ">",
- "loz" => "<>", "OElig" => "OE", "oelig" => "oe", "Yuml" => "Y",
- "circ" => "^", "tilde" => "~", "ensp" => " ", "emsp" => " ",
- "thinsp"=> " ", "ndash" => "-", "mdash" => "--", "lsquo" => "`",
- "rsquo" => "'", "sbquo" => "'", "ldquo" => "\"", "rdquo" => "\"",
- "bdquo" => "\"", "lsaquo"=> "<", "rsaquo"=> ">",
+ "bull" => "*", "hellip"=> "...", "prime" => "'", "Prime" => "\"",
+ "frasl" => "/", "trade" => "[tm]", "larr" => "<-", "rarr" => "->",
+ "harr" => "<->", "lArr" => "<=", "rArr" => "=>", "hArr" => "<=>",
+ "empty" => "\xD8", "minus" => "-", "lowast"=> "*", "sim" => "~",
+ "cong" => "=~", "asymp" => "~", "ne" => "!=", "equiv" => "==",
+ "le" => "<=", "ge" => ">=", "lang" => "<", "rang" => ">",
+ "loz" => "<>", "OElig" => "OE", "oelig" => "oe", "Yuml" => "Y",
+ "circ" => "^", "tilde" => "~", "ensp" => " ", "emsp" => " ",
+ "thinsp"=> " ", "ndash" => "-", "mdash" => "--", "lsquo" => "`",
+ "rsquo" => "'", "sbquo" => "'", "ldquo" => "\"", "rdquo" => "\"",
+ "bdquo" => "\"", "lsaquo"=> "<", "rsaquo"=> ">",
);
$img = $src;
+ $img = "http:$img" if ($img =~ m@^//@s); # Oh come on
+
# Sometimes these images are hosted on twitpic, sometimes on Amazon.
if ($img =~ m@^/@) {
$base =~ s@^(https?://[^/]+)/.*@$1@s;
# of images only updates once a minute; so we'll remember the last N entries
# on it and randomly select from those, to get a wider variety each time.
-my $twitter_img_url = "http://twitter.com/statuses/public_timeline.rss";
+my $twitter_img_url = "http://api.twitter.com/1/statuses/" .
+ "public_timeline.json" .
+ "?include_entities=true" .
+ "&include_rts=true" .
+ "&count=200";
my $twitter_cache_size = 1000;
+
my @twitter_cache = (); # fifo, for ordering by age
my %twitter_cache = (); # hash, for detecting dups
$last_search = $twitter_img_url; # for warnings
my ( $base, $body ) = get_document ($twitter_img_url, undef, $timeout);
-
# Update the cache.
if ($body) {
- $body =~ s/\n/ /gs;
- $body =~ s/(<item)\b/\n$1/gsi;
+ $body =~ s/[\r\n]+/ /gs;
- my @items = split (/\n/, $body);
- shift @items;
+ # Parsing JSON is a pain in the ass. So we halfass it as usual.
+ $body =~ s/^\[|\]$//s;
+ $body =~ s/(\[.*?\])/{ $_ = $1; s@\},@\} @gs; $_; }/gsexi;
+ my @items = split (/},{/, $body);
foreach (@items) {
- next unless (m@<link>([^<>]*)</link>@si);
- my $page = html_unquote ($1);
+ my ($name) = m@"screen_name":"([^\"]+)"@si;
+ my ($img) = m@"media_url":"([^\"]+)"@si;
+ my ($page) = m@"display_url":"([^\"]+)"@si;
+ next unless ($name && $img && $page);
+ foreach ($img, $page) {
+ s/\\//gs;
+ $_ = "http://$_" unless (m/^http/si);
+ }
next if ($twitter_cache{$page}); # already have it
- my ($title) = m@<title\b[^<>]*>(.*?)</title>@si;
- next unless $title;
-
- my ($url) = ($title =~ m@\b(https?://[^\s\[\]()<>\"\']+[a-z\d/])@si);
- next unless $url;
-
- LOG ($verbose_filter, " candidate: $page - $url");
+ LOG ($verbose_filter, " candidate: $page - $img");
push @twitter_cache, $page;
- $twitter_cache{$page} = $url;
+ $twitter_cache{$page} = $img;
}
}
$suppress_audit = 1;
- my ( $base2, $body2 ) = get_document ($url, $base, $timeout);
-
- if (!$base2 || !$body2) {
- $body2 = undef;
- return ();
- }
-
- my $img = pick_image_from_body ($base2, $body2);
- $body2 = undef;
-
- if ($img) {
- return ($base2, $img);
- } else {
- return ();
- }
+ return ($page, $url);
}
\f
#
############################################################################
-my $flickr_img_url = "http://www.flickr.com/photos/";
+my $flickr_img_url = "http://www.flickr.com/explore/";
# Like LiveJournal, the Flickr page of images tends to update slowly,
# so remember the last N entries on it and randomly select from those.
my $count = 0;
my $count2 = 0;
foreach (split (/\n/, $body)) {
+
my ($page, $thumb) = m@<A \s [^<>]* \b HREF=\"([^<>\"]+)\" [^<>]* > \s*
- <IMG \s [^<>]* \b SRC=\"([^<>\"]+)\" @xsi;
+ <IMG \s [^<>]* \b
+ data-defer-src = \"([^<>\"]+)\" @xsi;
next unless defined ($thumb);
$page = html_unquote ($page);
$thumb = html_unquote ($thumb);
- next unless ($thumb =~ m@^http://farm\d*\.static\.flickr\.com/@);
+ next unless ($thumb =~ m@^http://farm\d*\.static\.?flickr\.com/@);
my $base = "http://www.flickr.com/";
$page =~ s@^/@$base@;
error ("\$driftnet_dir unset?") unless ($driftnet_dir);
my $id = $driftnet_magic;
- my $re = qr/$driftnet_dir/;
error ("$id: $file not in $driftnet_dir?")
- unless ($file =~ m@^$re@o);
+ unless ($file =~ m@^\Q$driftnet_dir@o);
open (my $in, '<', $file) || error ("$id: $file: $!");
my $body = '';
my $v = ($verbose_exec ? "-v" : "");
my $pick = `xscreensaver-getimage-file $v "$dir"`;
+ $pick =~ s/\s+$//s;
$pick = "$dir/$pick" unless ($pick =~ m@^/@s); # relative path
LOG ($verbose_load, "picked file $pick ($id)");
error ("\$local_dir unset?") unless ($local_dir);
my $id = $local_magic;
- my $re = qr/$local_dir/;
error ("$id: $file not in $local_dir?")
- unless ($file =~ m@^$re@o);
+ unless ($file =~ m@^\Q$local_dir@o);
open (my $in, '<', $file) || error ("$id: $file: $!");
local $/ = undef; # read entire file
projects / xscreensaver / blobdiff