ok besten dank , habe es mir jetzt schön zurecht gebastelt...
ps weiß einer welche funktion dieses script in einer mir fremden sprache hat ?
#!/usr/local/bin/perl
# google_compare.cgi
# Your Google API developer's key
my $google_key='insert key here';
# Location of the GoogleSearch WSDL file
my $google_wdsl = "./GoogleSearch.wsdl";
use strict;
use SOAP::Lite;
use LWP::Simple qw(get);
use CGI qw{:standard};
my $googleSearch = SOAP::Lite->service("file:$google_wdsl");
# setup our browser output.
print "Content-type: text/html\n\n";
print "<html><title>Google Compare Results</title><body>\n";
# ask and we shell receive.
my $query = param('query');
unless ($query) {
print "<h1>No query defined.</h1></body></html>\n\n";
exit; # If there's no query there's no program.
}
# spit out the original before we encode.
print "<h1>Your original query was '$query'.</h1>\n";
$query =~ s/\s/\+/g ; #changing the spaces to + signs
$query =~ s/\"/%22/g; #changing the quotes to %22
# Create some hashes of queries for various search engines.
# We have four types of queries ("plain", "com", "edu", and "org"),
# and three search engines ("Google", "AlltheWeb", and "Altavista".
# Each engine has a name, query, and regular expression used to
# scrape the results.
my $query_hash = {
plain => {
Google => { name => "Google", query => $query, },
AlltheWeb => {
name => "AlltheWeb",
regexp => "Displaying results <b>.*<\/b> of <b>(.*)<\/b>",
query => "http://www.alltheweb.com/search?cat=web&q=$query",
},
Altavista => {
name => "Altavista",
regexp => "We found (.*) results",
query => "http://www.altavista.com/sites/search/web?q=$query",
}
},
com => {
Google => { name => "Google", query => "$query site:com", },
AlltheWeb => {
name => "AlltheWeb",
regexp => "Displaying results <b>.*<\/b> of <b>(.*)<\/b>",
query => "http://www.alltheweb.com/search?cat=web&q=$query+domain%3Acom",
},
Altavista => {
name => "Altavista", regexp => "We found (.*) results",
query => "http://www.altavista.com/sites/search/web?q=$query+domain%3Acom",
}
},
org => {
Google => { name => "Google", query => "$query site
rg", },
AlltheWeb => {
name => "AlltheWeb",
regexp => "Displaying results <b>.*<\/b> of <b>(.*)<\/b>",
query => "http://www.alltheweb.com/search?cat=web&q=$query+domain%3Aorg",
},
Altavista => {
name => "Altavista", regexp => "We found (.*) results",
query => "http://www.altavista.com/sites/search/web?q=$query+domain%3Aorg",
}
},
net => {
Google => { name => "Google", query => "$query site:net", },
AlltheWeb => {
name => "AlltheWeb",
regexp => "Displaying results <b>.*<\/b> of <b>(.*)<\/b>",
query => "http://www.alltheweb.com/search?cat=web&q=$query+domain%3Anet",
},
Altavista => {
name => "Altavista", regexp => "We found (.*) results",
query => "http://www.altavista.com/sites/search/web?q=$query+domain%3Anet",
}
}
};
# now, we loop through each of our query types,
# under the assumption there's a matching
# hash that contains our engines and string.
foreach my $query_type (keys (%$query_hash)) {
print "<h2>Results for a '$query_type' search:</h2>\n";
# now, loop through each engine we have and get/print the results.
foreach my $engine (values %{$query_hash->{$query_type}}) {
my $results_count;
# if this is Google, we use the API and not port 80.
if ($engine->{name} eq "Google") {
my $result = $googleSearch->doGoogleSearch(
$google_key, $engine->{query}, 0, 1,
"false", "", "false", "", "latin1", "latin1");
$results_count = $result->{estimatedTotalResultsCount};
# the google api doesn't format numbers with commas.
my $rresults_count = reverse $results_count;
$rresults_count =~ s/(\d\d\d)(?=\d)(?!\d*\.)/$1,/g;
$results_count = scalar reverse $rresults_count;
}
# it's not google, so we GET like everyone else.
elsif ($engine->{name} ne "Google") {
my $data = get($engine->{query}) or print "ERROR: $!";
$data =~ /$engine->{regexp}/; $results_count = $1 || 0;
}
# and print out the results.
print "<strong>$engine->{name}</strong>: $results_count<br />\n";
}
}
