Появилась задача определить по какой поисковой фразе пришел посетитель на сайт из поисковых систем (Yandex, Google, Mail.ru и т.п.).
Готовых компонентов на Perl я не нашел, да и на форумах примеры в основном на PHP и все в качестве “набросков”.
Пособирав информацию, получился простой компонент. Возможно он будет полезен. Список поисковых систем заимствован отсюда
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
package Parse::SEKeywords; use strict; use URI::Escape qw(uri_unescape); use Exporter; our @ISA = qw(Exporter); our @EXPORT = qw(get_se_keyword); our $SE = [ { "name" =>"Картинки.Mail", "pattern" =>"go.mail.ru/search_images", "param" =>"q" }, { "name" => "Mail", "pattern" => "go.mail.ru", "param" => "q" }, { "name" => "Google Images", "pattern" => "images.google.", "param" => "q" }, { "name" => "Google", "pattern" => "google.", "param" => "q" }, { "name" => "Google", "pattern" => "google.", "param" => "as_q" }, { "name" => "Live Search", "pattern" => "search.live.com", "param" => "q" }, { "name" => "RapidShare Search Engine", "pattern" => "rapidshare-search-engine", "param" => "s" }, { "name" => "Rambler", "pattern" => "rambler.ru", "param" => "query" }, { "name" => "Rambler", "pattern" => "rambler.ru", "param" => "words" }, { "name" => "Yahoo!", "pattern" => "search.yahoo.com", "param" => "p" }, { "name" => "Nigma", "pattern" => "nigma.ru/index.php", "param" => "s" }, { "name" => "Nigma", "pattern" => "nigma.ru/index.php", "param" => "q" }, { "name" => "MSN", "pattern" => "search.msn.com/results", "param" => "q" }, { "name" => "Ask", "pattern" => "ask.com/web", "param" => "q" }, { "name" => "QIP", "pattern" => "search.qip.ru/search", "param" => "query" }, { "name" => "RapidAll", "pattern" => "rapidall.com/search.php", "param" => "query" }, { "name" => "Яндекс.Картинки", "pattern" => "images.yandex.ru/", "param" => "text" }, { "name" => "Яндекс.Mobile", "pattern" => "m.yandex.ru/search", "param" => "query" }, { "name" => "Яндекс", "pattern" => "hghltd.yandex.net", "param" => "text" }, { "name" => "Яндекс", "pattern" => "yandex.ru", "param" => "text" } ]; sub get_se_keyword { my $referer = shift; my ($domain, $qs) = $referer =~ /^(.*?)\?(.*)$/; my %params = map { split/\=/ } split /\&/, $qs; my ($search_engine) = grep { $domain =~ /\Q$_->{pattern}\E/ } @$SE; return undef unless $search_engine; my $query_key = grep { $search_engine->{param} eq $_ } keys %params; return undef unless $query_key; my $query_s = uri_unescape( $params{ $search_engine->{param} } ); return wantarray ? ($query_s, $search_engine) : $query_s; } 1; |
Как использовать:
|
1 2 3 4 5 6 7 8 |
use Parse::SEKeywords; my $key = get_se_keyword( $ENV{'HTTP_REFERER'} ); print "Keyword: ".$key."\n"; my ($key, $se) = get_se_keyword( $ENV{'HTTP_REFERER'} ); print "Keyword: ".$key."\n"; print "Search Engine: ".$se->{name}."\n"; |