#!/usr/bin/perl -w # A HTTP Proxy for thomann.de price information ############################################################################### # # Rational: About a year ago thomann.de decided to change its website # and encode all price information in images. This is of course # extremely problematic for low-vision or blind users. # In a personal mail they explained to me they do it to prevent # automated price comparison, and they claimed their technique is # safe against automatic bots. Well... # If a *BLIND* person can come up with the script below on their own, # I bet my ass off that anyone with an interest in # automated information retrieval would be able to do the same. # Seems like the management of thomann.de was fooled very much # by their webmaster. # And they shouldn't do what they are doing anyway. # So I made this script public for anyone who needs it. # Its in the public domain. Use, change, distribute as you wish. # # Usage: # You need Perl, the HTTP::Proxy module (libhttp-proxy-perl on Debian) and # perlmagick. # Then just run this script if you want to visit thomann.de. # Configure your web browser of choice to use the Proxy # (its at localhost:3128) and just visit http://thomann.de # If the proxy finds a digit image it retrieves it and compares it to # the very simplistic database below. # # FUTURE PLANS: Rescale all images to a common size and use some form of # fuzzy compare (FANN?) to avoid having to save all bitmap variations # in the source and also make this a bit more generic (ONR). # # DISCLAIMER: While I have done my best to guess the numbers right, # I do not guarantee this is error-free. Dont trust the price # you're reading. In any case, you shouldn't buy from thomann.de # anyways since they obviously dont want you to use their service. # # Notes: This is a work in progress, not all digits are defined yet. ############################################################################### use strict; use HTTP::Proxy; use HTTP::Proxy::BodyFilter::htmlparser; use HTTP::Proxy::HeaderFilter::simple; use HTML::Parser; use LWP::UserAgent; use Image::Magick; my %chars = (" XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXX XXXXX XXXX XXX XXX XX XXX X XX X XX X X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX X XX X XXX XX XXX XX XXXXX XXX XXXXXXX XXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX " => 0, " XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXX XXXXXX XXX XXXX XX XXX XX XX X XX X X XX X XX XX X XX XX X XX XX X XX XX X X XXX X X XXX XXXXXXXXX XXX XXXXXXXXX XXXX XXXXXXXX XXXX XXXXXXX XXXXX XXXXXX XXXXXX XXXXX XXXXXX XXXX XXXXXXX XXXX XXXXXXXX XXX XXXXXXXXX XX XXXXXXXXX XX XXXXXXXXXX X XXXXXXXXXXX X XXXXXXXXXXX X XXXXXXXXXXXX X XX X XX X XX X XX X XX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX " => 2, " XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX X X X X X X X X X X X X XXXXXXXXXXX XX XXXXXXXXXXX XX XXXXXXXXXX XX XXXXXXXXXX XXX XXXXXXXXXX XXX XXXXXXXXX XXX XXXXXXXXX XXXX XXXXXXXXX XXXX XXXXXXXX XXXX XXXXXXXX XXXXX XXXXXXXX XXXXX XXXXXXX XXXXX XXXXXXX XXXXXX XXXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXXX XXXXXX XXXXXXX XXXXX XXXXXXX XXXXX XXXXXXXX XXXX XXXXXXXX XXXX XXXXXXXX XXXX XXXXXXXXX XXX XXXXXXXXX XXX XXXXXXXXX XXX XXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX " => 7, " XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXX XXXXXX XXX XXXX XX XXX XX XX X XX X X XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX XX XXX XX XXX XXX XXXX XXX XXXX XX XXX XX XXX XX XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX X XX XX XXX XX XXX XXXX XXXX XXXXXX XXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX " => 8, " XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXX XXXXX XXX XXX XX XX XX X X X X X X X XX X X XX X X XX X X XX X X XX X X XX X X XXXXXXXXXXX X XXX X XX X XX X X X X X X X XX X X XX X X XX X X XX X X XX X X XX X X XX X X X X X XX XX XX XX XXXX XXX XXXXXX XXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX " => 6, " XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXX XXXXX XXXX XXX XXX XX XX X XX X XX X X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX X X XX X XX X XX X XX X XXX X XXXX X XXXXXXXXXXX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX X X XX X XX X XXX XX XXXX XXX XXXXXXX XXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX " => 9, " XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXX XX XXXXXXX XX XXXXXX XX XXXX XX XX XX XX XX XX XX XX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXX XX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX " => 1, " XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXX XXXXXX XXX XXXX XX XXX XX XX X XX X X XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX XXXXXXXXXX XXX XXXXXX XXX XXXXXX XXXX XXXXXX XXXXX XXXXXX XXX XXXXXX XXX XXXXXXXXXXX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX X XX XX XXX XX XXX XXXX XXXX XXXXXX XXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXX " => 3, " XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXX XXXX XXXXXXXXX XXXX XXXXXXXX XXXX XXXXXXXX XXXX XXXXXXX XXXX XXXXXXX XXXX XXXXXXX XXXX XXXXXX XXXX XXXXXX XXXX XXXXXX X XXXX XXXXX X XXXX XXXXX X XXXX XXXXX X XXXX XXXX XX XXXX XXXX XX XXXX XXXX XX XXXX XXX XXX XXXX XXX XXX XXXX XXX XXX XXXX XX X XX X XX X XX X XX X XXXXXXXXXXXX XXXX XXXXXXXXXXXX XXXX XXXXXXXXXXXX XXXX XXXXXXXXXXXX XXXX XXXXXXXXXXXX XXXX XXXXXXXXXXXX XXXX XXXXXXXXXXXX XXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX " => 4, " XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XX X XX X XX X XX X XX X XX X XX XXXXXXXXXXX XX XXXXXXXXXXX XX XXXXXXXXXXX XX X XXXX XX XX XX X XX X XX X XX X XX X X XXXXXXXXXXX X XXXXXXXXXXX X XXXXXXXXXXX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX XX X XX X X XX X XX X XXX XX XXXX XXX XXXXXXX XXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX " => 5, " XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XX X XX X XX X XX X XX X XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX " => "-", " XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXXXXXXXXXX XXXX X XXXX X XXXX X XXX XX XXX XX XXX XX XXX XXX XXX XXX XXX XXXX XXX XXXX XX XXXX XX XXXXX XX XXXXX XXXXXXXXXXXX XXXXXXXXXXXX " => ","," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XX XX X XXX X X XXX X X XXX X X XXX X X XXX X X XXX X X XXX X XX XX XXXXXXXXX XXXXXXXXX XXXXXXXXX " =>0," XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXX XXX X XXX XXX XXX XXX XXX XXX XXX XXX XXX XXX XXX XXX XXX X X XXXXXXXX XXXXXXXX XXXXXXXX " =>1," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XX XX X XXX X X XXX X XXXXXX X XXXXX XX XXXX XXX XXX XXXX XX XXXXX X X XXXXXXXXX XXXXXXXXX XXXXXXXXX " =>2," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XX XX X XXX X X XXX X XXXXXX X XXXX XX XXXXXX X X XXX X X XXX X XX XX XXXXXXXXX XXXXXXXXX XXXXXXXXX " =>3," XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXX XXX XXXX XXX XXX X XXX XX XX XXX X XXX XXX X X XXXXX XXX XXXXX XXX XXXXX XXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX " =>4," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XX X XX XXXXX XX XXXXX XX XX XXXXXX X XXXXXX X X XXX X X XXX X XX XX XXXXXXXXX XXXXXXXXX XXXXXXXXX "=>5," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XXX XX XX XXXXX X XXXXXX X XX X XXX X X XXX X X XXX X X XXX X XX XX XXXXXXXXX XXXXXXXXX XXXXXXXXX " => 6," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX X X XXXXXX X XXXXXX X XXXXX XX XXXXX XX XXXX XXX XXXX XXX XXX XXXX XXX XXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX " =>7," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XX XX X XXX X X XXX X X XXX X XX XX X XXX X X XXX X X XXX X XX XX XXXXXXXXX XXXXXXXXX XXXXXXXXX "=>8," XXXXXXXXX XXXXXXXXX XXXXXXXXX XXXXXXXXX XX XX X XXX X X XXX X X XXX X X XXX X XX X XXXXXX X XXXXX XX XX XXX XXXXXXXXX XXXXXXXXX XXXXXXXXX " =>9," XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XXXXXX XX X XX XX XX XX X XXX X XXX "=>","," XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX X X XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX XXXXXXX " =>"-", " XXXXXXX XXXXXXX XXXXXXX XX XX X X X X X X X X X X X X X X X XX XX XXXXXXX XXXXXXX " => 0, " XXXXXX XXXXXX XXXXXX XX XX X XX XX XX XX XX XX XX XX XX X X XXXXXX XXXXXX " => 1, " XXXXXXX XXXXXXX XXXXXXX XX XX X XX X XXXX X XXX XX XX XXX X XXXX X X XXXXXXX XXXXXXX " => 2, " XXXXXXX XXXXXXX XXXXXXX XX XX X XX X XXXX X XX XX XXXX X X XX X XX XX XXXXXXX XXXXXXX " => 3, " XXXXXXX XXXXXXX XXXXXXX XXX XX XX XX X X XX XX XX X XXX XX XXX XX XXXXXXX XXXXXXX " => 4," XXXXXXX XXXXXXX XXXXXXX X X X XXXX X XX XXXX X XXXX X X XX X XX XX XXXXXXX XXXXXXX " =>5," XXXXXXX XXXXXXX XXXXXXX XX XX X XXXX X XX X X X X X X X X X XX XX XXXXXXX XXXXXXX " => 6, " XXXXXXX XXXXXXX XXXXXXX X X XXXX X XXX XX XXX XX XX XXX XX XXX X XXXX XXXXXXX XXXXXXX " => 7, " XXXXXXX XXXXXXX XXXXXXX XX XX X X X X X X XX XX X X X X X X XX XX XXXXXXX XXXXXXX " => 8," XXXXXXX XXXXXXX XXXXXXX XX XX X X X X X X X X X XX X XXXX X XX XX XXXXXXX XXXXXXX "=>9," XXXXX XXXXX XXXXX XXXXX XXXXX XXXXX X X XXXXX XXXXX XXXXX XXXXX XXXXX " => "-", " XXXX XXXX XXXX XXXX XXXX XXXX XXXX XXXX X X X X X X X XX " => ","); my $ua = LWP::UserAgent->new; $ua->agent ("Destupidifier/0.1"); my $htmlparser = HTML::Parser->new( api_version => 3 ); $htmlparser->handler( default => sub { my ( $self, $text ) = @_; $self->{output} .= $text }, "self,text"); $htmlparser->handler( start => sub { my ( $self, $tag, $text ) = @_; if ($tag eq "img" and $text =~ /src=".*digit.*"/) { my ($src) = $text =~ /src="(.*?)"/; my $req = new HTTP::Request ('GET' => $src, HTTP::Headers->new ('Content-Type' => 'application/x-www-form-urlencoded')); my $res = $ua->request ($req); $res->is_error && print "Can't get page $src"; my $tempname = "/tmp/$$." . time . ".tmp"; open (FH, ">$tempname") || die $!; print FH $res->content (); close FH; my $p = new Image::Magick; $p->Read($tempname); my ($width, $height) = $p->Get('width', 'height'); my $str = "\n"; for( my $j = 0; $j < $height; $j++ ) { for( my $i = 0; $i < $width; $i++ ) { my @pixel = $p->GetPixel( x=>$i, y=>$j ); if ($pixel[0] eq 1) { $str .= "X"; } else { $str .= " "; }; }; $str .= "\n"; }; if (defined $chars{$str}) { my $alt = $chars{$str}; $text =~ s,>$, alt="$alt">,; } else { print STDOUT $str; }; }; $self->{output} .= $text }, "self,tagname,text"); my $proxy = HTTP::Proxy->new(port => 3128); my $htmlfilter = HTTP::Proxy::BodyFilter::htmlparser->new($htmlparser, rw => 1); $proxy->push_filter(mime => 'text/html', response => $htmlfilter); $proxy->start();