{"id":264613,"date":"2015-08-31T11:43:02","date_gmt":"2015-08-31T07:43:02","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=264613"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=264613","title":{"rendered":"\u041f\u0440\u043e\u0432\u0435\u0440\u044f\u0435\u043c \u0432\u0441\u0435 \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u044b \u0441\u0430\u0439\u0442\u0430 \u0432 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u0435 html"},"content":{"rendered":"

\t <\/p>\n

\u0418\u043d\u0442\u0440\u043e<\/h4>\n

\u0426\u0435\u043b\u044c \u2014 \u0441\u043e\u0437\u0434\u0430\u0442\u044c \u0432\u0435\u043b\u043e\u0441\u0438\u043f\u0435\u0434<\/s> \u0441\u043a\u0440\u0438\u043f\u0442, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u043f\u0440\u043e\u0431\u0435\u0436\u0438\u0442\u0441\u044f \u043f\u043e \u0441\u0430\u0439\u0442\u0443 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u0442 \u043a\u0430\u0436\u0434\u0443\u044e \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u0443 \u0441\u0430\u0439\u0442\u0430 \u043d\u0430 \u0432\u0430\u043b\u0438\u0434\u043d\u043e\u0441\u0442\u044c html.
\u042f \u0441\u043b\u044b\u0448\u0430\u043b, \u0447\u0442\u043e \u0435\u0441\u043b\u0438 \u043d\u0430\u043f\u0430\u0434\u0430\u0435\u0442 \u043f\u0435\u0440\u0444\u0435\u043a\u0446\u0438\u043e\u043d\u0438\u0437\u043c, \u0442\u043e \u043d\u0430\u0434\u043e \u043f\u043e\u043b\u0435\u0436\u0430\u0442\u044c, \u043e\u0442\u0434\u043e\u0445\u043d\u0443\u0442\u044c \u0438 \u044d\u0442\u043e \u043f\u0440\u043e\u0439\u0434\u0435\u0442.
\u041f\u043e\u0434\u0443\u043c\u0430\u0435\u0448\u044c, \u0432 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u0435 \u043e\u0448\u0438\u0431\u043a\u0430\u2026
\u041d\u043e \u0435\u0441\u043b\u0438 \u0432\u0441\u0435 \u0436\u0435 \u043d\u0435 \u043f\u0440\u043e\u0445\u043e\u0434\u0438\u0442, \u0442\u043e <\/a><\/p>\n

\u0421\u0442\u0430\u0432\u0438\u043c \u0434\u043e\u043a\u0435\u0440 \u0438 \u043a\u043e\u043d\u0442\u0435\u0439\u043d\u0435\u0440 \u0441 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u043e\u043c<\/h2>\n

\u0420\u0430\u043d\u044c\u0448\u0435 \u043f\u043e\u0441\u0442\u0430\u0432\u0438\u0442\u044c \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0439 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440 \u0431\u044b\u043b\u043e \u0434\u0435\u043b\u043e\u043c \u043c\u0443\u0442\u043e\u0440\u043d\u044b\u043c<\/a>.
\u041d\u0435 \u0442\u043e, \u0447\u0442\u043e \u0431\u044b \u0441\u043b\u043e\u0436\u043d\u044b\u043c, \u0430 \u0442\u0440\u0435\u0431\u0443\u044e\u0449\u0438\u043c \u0432\u0440\u0435\u043c\u0435\u043d\u0438.
\u0421 \u043f\u0440\u0438\u0445\u043e\u0434\u043e\u043c \u0434\u043e\u043a\u0435\u0440\u0430 \u043e\u043d \u0443\u0441\u0442\u0430\u043d\u0430\u0432\u043b\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u0437\u0430 \u0441\u0435\u043a\u0443\u043d\u0434\u044b.
\u0421\u0442\u0430\u0432\u0438\u043c \u0434\u043e\u043a\u0435\u0440: <\/p>\n

yum install docker <\/code><\/pre>\n
  \u041f\u043e\u0441\u043b\u0435 \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u043a\u0438 \u0434\u043e\u043a\u0435\u0440\u0430 \u0431\u0435\u0440\u0435\u043c \u0441\u0435\u0431\u0435 \u0433\u043e\u0442\u043e\u0432\u044b\u0439 \u043e\u0431\u0440\u0430\u0437 \u0441 \u0441\u043e\u0431\u0440\u0430\u043d\u043d\u044b\u043c \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u043e\u043c<\/a>:  <\/p>\n
docker pull magnetikonline\/html5validator <\/code><\/pre>\n
  \u041a\u043e\u0433\u0434\u0430 \u043e\u0431\u0440\u0430\u0437 \u0437\u0430\u043a\u0430\u0447\u0430\u0435\u0442\u0441\u044f, \u0442\u043e \u0437\u0430\u043f\u0443\u0441\u043a\u0430\u0435\u043c \u0435\u0433\u043e:  <\/p>\n
docker run -p 8080:80 -p 8888:8888 --name validator --restart=always  -d magnetikonline\/html5validator <\/code><\/pre>\n
  \u0418 \u0441\u0442\u0430\u0440\u0442\u0443\u0435\u043c:  <\/p>\n
docker start validator <\/code><\/pre>\n
  \u041f\u043e\u0441\u043b\u0435 \u0437\u0430\u043f\u0443\u0441\u043a\u0430 \u043c\u043e\u0436\u043d\u043e \u0437\u0430\u0439\u0442\u0438 \u043d\u0430 http:\/\/localhost:8888<\/a> \u0438 \u0443\u0432\u0438\u0434\u0435\u0442\u044c:<\/p>\n
  <\/p>\n
  \u041b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0439 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440 \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442! \u0415\u0433\u043e \u043c\u043e\u0436\u043d\u043e \u043d\u0430\u0442\u0440\u0430\u0432\u0438\u0442\u044c \u043d\u0430 \u043a\u0430\u043a\u043e\u0439-\u043d\u0438\u0431\u0443\u0434\u044c \u0441\u0430\u0439\u0442. 
  \u0418 \u043f\u0440\u043e\u0432\u0435\u0440\u044f\u0435\u043c \u0441 \u043a\u043e\u043c\u0430\u043d\u0434\u043d\u043e\u0439 \u0441\u0442\u0440\u043e\u043a\u0438:<\/p>\n
curl 'localhost:8888?doc=http:\/\/www.w3schools.com' <\/code><\/pre>\n
  <\/p>\n
\u0418 \u0432\u043e\u0442 \u0442\u0430\u043a\u043e\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442:<\/h4>\n
  <\/p>\n
  \u041a\u0430\u043a \u0432\u0438\u0434\u043d\u043e, \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440 \u043d\u0430\u0448\u0435\u043b 3 \u043e\u0448\u0438\u0431\u043a\u0438. <\/p>\n
\u041f\u0430\u0443\u0447\u043e\u043a<\/h2>\n
  
  \u0422\u0435\u043f\u0435\u0440\u044c \u043d\u0430\u0434\u043e \u043d\u0430\u043f\u0438\u0441\u0430\u0442\u044c \u0441\u043a\u0440\u0438\u043f\u0442, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0431\u044b \u043e\u0431\u043e\u0448\u0435\u043b \u0432\u0441\u0435 \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u044b \u0441\u0430\u0439\u0442\u0430. 
  \u0417\u0430 \u043e\u0441\u043d\u043e\u0432\u0443 \u044f \u0432\u0437\u044f\u043b \u0432\u043e\u0442 \u0442\u0430\u043a\u043e\u0439 web crawler\/scraper<\/a> \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 Mojo.
  \u0418 \u043d\u0435\u043c\u043d\u043e\u0433\u043e \u0438\u0437\u043c\u0435\u043d\u0438\u043b:<\/p>\n
#!\/usr\/bin\/env perl use 5.010; use open qw(:locale); use strict; use utf8; use warnings qw(all); use Mojo::UserAgent; use List::MoreUtils 'true'; use Term::ANSIColor;  # \u0410\u0434\u0440\u0435\u0441 \u0441\u0430\u0439\u0442\u0430 \u0434\u043b\u044f \u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0438 my $site_to_check = 'http:\/\/habrahabr.ru';  # \u0410\u0434\u0440\u0435\u0441 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u0430 my $local_validator = 'http:\/\/192.168.1.217:8888';  # FIFO queue my @urls = ( Mojo::URL->new($site_to_check) );  # User agent following up to 5 redirects my $ua = Mojo::UserAgent->new( max_redirects => 5 );  # Track accessed URLs my $active = 0; my %uniq;  sub parse {     my ($tx) = @_;      # Request URL     my $url = $tx->req->url;      # Extract and enqueue URLs     for my $e ( $tx->res->dom('a[href]')->each ) {          # Validate href attribute         my $link = Mojo::URL->new( $e->{href} );         next if 'Mojo::URL' ne ref $link;          # "normalize" link         $link = $link->to_abs( $tx->req->url )->fragment(undef);         next unless $link->protocol =~ \/^https?$\/x;          # Don't go deeper than \/a\/b\/c         next if @{ $link->path->parts } > 3;          # Access every link only once         next if ++$uniq{ $link->to_string } > 1;          # Don't visit other hosts         next if $link->host ne $url->host;          push @urls, $link;         my $get   = $ua->get( $local_validator . "?doc=$link" )->res->body;         my @answ  = split \/ \/, $get;         my $count = true { \/class="error"\/ } @answ;         print color("green"), $link, color("reset");         print "  \u041a\u043e\u043b-\u0432\u043e \u043e\u0448\u0438\u0431\u043e\u043a \u0432 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u0435: ",           color("red"), "$count \\n", color("reset");      }      return; }  sub get_callback {     my ( undef, $tx ) = @_;      # Parse only OK HTML responses     $tx->res->code == 200       and $tx->res->headers->content_type =~ m{^text\/html\\b}ix       and parse($tx);      # Deactivate     --$active;      return; }  Mojo::IOLoop->recurring(     0 => sub {          # Keep up to 4 parallel crawlers sharing the same user agent         for ( $active .. 4 - 1 ) {              # Dequeue or halt if there are no active crawlers anymore             return ( $active or Mojo::IOLoop->stop )               unless my $url = shift @urls;              # Fetch non-blocking just by adding             # a callback and marking as active             ++$active;             $ua->get( $url => \\&get_callback );         }     } );  # Start event loop if necessary Mojo::IOLoop->start unless Mojo::IOLoop->is_running; <\/code><\/pre>\n
  \u0421\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u0433\u0438\u0442\u0445\u0430\u0431<\/a>  <\/p>\n
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0440\u0430\u0431\u043e\u0442\u044b:<\/h4>\n
       \t<\/p>\n
<\/div>\n
 \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438  http:\/\/habrahabr.ru\/post\/265709\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
     \t  <\/p>\n
\u0418\u043d\u0442\u0440\u043e<\/h4>\n
  \u0426\u0435\u043b\u044c \u2014 \u0441\u043e\u0437\u0434\u0430\u0442\u044c \u0432\u0435\u043b\u043e\u0441\u0438\u043f\u0435\u0434<\/s> \u0441\u043a\u0440\u0438\u043f\u0442, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u043f\u0440\u043e\u0431\u0435\u0436\u0438\u0442\u0441\u044f \u043f\u043e \u0441\u0430\u0439\u0442\u0443 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u0442 \u043a\u0430\u0436\u0434\u0443\u044e \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u0443 \u0441\u0430\u0439\u0442\u0430 \u043d\u0430 \u0432\u0430\u043b\u0438\u0434\u043d\u043e\u0441\u0442\u044c html. 
  \u042f \u0441\u043b\u044b\u0448\u0430\u043b, \u0447\u0442\u043e \u0435\u0441\u043b\u0438 \u043d\u0430\u043f\u0430\u0434\u0430\u0435\u0442 \u043f\u0435\u0440\u0444\u0435\u043a\u0446\u0438\u043e\u043d\u0438\u0437\u043c, \u0442\u043e \u043d\u0430\u0434\u043e \u043f\u043e\u043b\u0435\u0436\u0430\u0442\u044c, \u043e\u0442\u0434\u043e\u0445\u043d\u0443\u0442\u044c \u0438 \u044d\u0442\u043e \u043f\u0440\u043e\u0439\u0434\u0435\u0442. 
  \u041f\u043e\u0434\u0443\u043c\u0430\u0435\u0448\u044c, \u0432 \u0432\u0430\u043b\u0438\u0434\u0430\u0442\u043e\u0440\u0435 \u043e\u0448\u0438\u0431\u043a\u0430\u2026
  \u041d\u043e \u0435\u0441\u043b\u0438 \u0432\u0441\u0435 \u0436\u0435 \u043d\u0435 \u043f\u0440\u043e\u0445\u043e\u0434\u0438\u0442, \u0442\u043e <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-264613","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/264613","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=264613"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/264613\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=264613"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=264613"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=264613"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}