Парсинг , Граббинг Группы вконтакте

Собрать всех участников ( их ID ) какой-либо группы с сайта vkontakte.ru

для примера возьмем группу "Я ненавижу автомобили"

http://vk.com/search?c[section]=people&c[group]=1409939

function GetAllMembersPage($oid = 1409939, $offset = 0)
 {
  $this-> code = $this-> GetMembersPage($oid, $offset);

  if(preg_match_all ('~
В группе (.*) участников.
~', $this-> code, $m))
  {
    $members_count = strip_tags($m[1][0]);
    $members_count = (int)str_replace (' ', '',  $members_count);
    echo "нашли В группе $members_count участников";
    //print_r($m);
  }

  $users_data[] = $this-> GetMembers();
  $offset = 20;
  while ($offset < $members_count)
  {
   echo "i=$i
";
   echo "offset=$offset
";

   $this-> GetMembersPage($oid, $offset);

   $users_data[] = $this-> GetMembers();
   $offset = $offset +20;
  }

   //print_r($users_data);

   foreach($users_data as $d)
   {
  foreach($d[1] as $k=>$v)
  {
   $users_data_w1[ $d[1][$k] ] = $d[2][$k];
   $users_data_w_id[ $d[1][$k] ] = $d[1][$k];
  }
   }

   $users_data_w_id = array_unique ($users_data_w_id);

   $this-> write_string("members_id.txt", '', "w");
   foreach($users_data_w_id as $id)
   {
     $this-> write_string("members_id.txt", trim($id)."\n", "a");
   }


 }




 //********************************
 //*
 //*  http://vk.com/al_page.php?act=show_members_box&al=1&gid=1409939&tab=members
 //*  http://vk.com/al_page.php?act=show_members_box&al=1&gid=1409939&tab=members&offset=190
 //*
 //*******************************
 function GetMembersPage($gid = 1409939, $offset=0)
 {
  $p = array
  (
  "act" => "show_members_box",
  "al" => "1",
  "tab" => "members",
  "gid" => $gid,
  "offset" => $offset,
  );

  $post_fields  = http_build_query($p);
  $curl_data['post'] = $post_fields;
  $curl_data['followlocation'] = true;
  $curl_data['echo_header'] = true;
  $curl_data['referer'] = $this->site."";
  $curl_data['url'] = $this->site."/al_page.php";


  $this->code = $this->curl($curl_data);
  //print_r($this->code);
  $this-> write_string("show_members_box_log.htm", $this->code);
  return $this->code;
 }



function GetMembers()
{
  if(preg_match_all ('~(.*)~U', $this-> code, $m))
  {
   //print_r($m);
   return $m;
  }
  else
  {
   return false;
  }
}

На выходе имеем файл "members_id.txt"
вида

/skarrr
/id305045
/deviatio
/id538322
/arrtemy
/lerarunge
/id846721
/id1099400
/stigma
/stanislavre
/id1295336
/id1359451
/id1362725
/id1466790
/cor_serpentis
/id3801455
/id3917827
/id3960713
/jjozhkashut
/id4620731
/id4675099
/id4772386
/id5549687
/id7528496
/nastroy_voice
/slavin.anton
/id8381743
/id8888177
/id8919195
/id9414070
/id12545362
/id12614309
/id13689235
/eugeniy_victorovich
/id15446689
/id15749772
/id17258303
/id19105109
/amerius
/id21486556
/id22178446
/id24001470
/id24663151
/id25468242
/dokkdokk
/x_nemo_x
/id30769974
/pripyat_v_serdce
/id38287278
/id49674719
/yeticlub
/id54853271
/opium83w
/id68409528
/id68413777
/qwertypoint
/id94558605
/id128952800
/id132524251
/id135713564

скачать исходник:
http://rghost.ru/27066891

пасс: parsing-posting.blogspot.com

php скрипт постинга в Elgg

Неплохой движок. Бесплатный. Русифицирован и создано много сообществ в поддержку и развитие проекта.

Уникальные признаки:

"Powered by Elgg" inurl:"pg/dashboard"
"Powered by Elgg" inurl:"pg/register"

Например, если нам нужны будут блоги для постинга прокладок или доров. Для этого к признаку сразу добавляем Blogs и получаем уже необходимые нам ресурсы с установленным модулем Blogs:

"Powered by Elgg" inurl:"pg/blog"
inurl:"user/auth/forgot" + Blogs


Легкая автоматизация, набиваем посты:

function post()
 {
   $headers = $this->set_headers();
   $curl_data['headers'] =  $headers;
   $curl_data['followlocation'] = true;
   $curl_data['echo_header'] = true;

   $curl_data['url'] = $this->site."/mod/blog/everyone.php";
   $curl_data['referer'] = $this->site.'/pg/dashboard/';

   $this->code = $this->curl($curl_data);

   $curl_data['url'] = $this->site."/pg/blog/".$this->username."/new/";
   $curl_data['referer'] = $this->site."/mod/blog/everyone.php";

   $this->code = $this->curl($curl_data);

   if(strpos($this->code, 'blogPostForm'))
   {

     # выбираем поля для постинга
    $input_field = $this->get_input_field_post();

    if($input_field[__elgg_token] )
    {
     $input_field[submit] = $this->action;

     $input_field[blogtitle] = $this->post_title;
     $input_field[blogbody] = $this->body;
     $input_field[blogtags] = $this->tags;
     $input_field[comments_select] = 'on';
     $input_field[access_id] = 2;

     $p = array 
     (
     '__elgg_token' => $input_field[__elgg_token],
     '__elgg_ts' => $input_field[__elgg_ts],
     'access_id' => '2',
     'comments_select' => 'on',
     'blogtitle' => $this->post_title,
     'blogbody' => $this->body,
     'blogtags' => $this->tags,
     'submit' => $this->action,
     );

     $curl_data['post'] = http_build_query($p);
     $headers = $this->set_headers();
     $headers[] = "Referer: ".$this->site."/pg/blog/".$this->username."/new/";
     $curl_data['headers'] =  $headers;

     $curl_data['followlocation'] = true;
     $curl_data['echo_header'] = true;
     $curl_data['referer'] = $this->site."/pg/blog/".$this->username."/new/";
     $curl_data['url'] = $this->site."/action/blog/add";
     $this->code = $this->curl($curl_data);

     if (stripos($this->code, 'Your blog post was successfully posted')
      or stripos($this->code, '302 Found')
      or stripos($this->code, '302 Moved Temporarily')
      )
     {
       echo "Post Published";
       $this->get_my_blog_post_url();
       return true;
     } else
     {
      echo "Not Allowed, случилась какая-то хуйета";
      return false;
     }
    }
   }
   else
   {
    $curl_data['url'] = $this->site."/pg/pages/new/";
    $curl_data['referer'] = $this->site.'/mod/pages/world.php';

    $this->code = $this->curl($curl_data);

     # выбираем поля для постинга
    $input_field = $this->get_input_field_post();

    if($input_field[__elgg_token] )
    {
     $input_field[submit] = $this->action;

     $input_field[blogtitle] = $this->post_title;
     $input_field[blogbody] = $this->body;
     $input_field[blogtags] = $this->tags;
     $input_field[comments_select] = 'on';
     $input_field[access_id] = 2;

     $p = array (


     '__elgg_token' => $input_field[__elgg_token],
     '__elgg_ts' => $input_field[__elgg_ts],
     'access_id' => '2',
     'comments_select' => 'on',
     'container_guid' => $input_field[container_guid],
     'owner_guid' => $input_field[owner_guid],
     'parent_guid' => $input_field[parent_guid],
     'write_access_id' => '-2',
     'title' => $this->post_title,
     'description' => $this->body,
     'tags' => $this->tags,


     );

     $curl_data['post'] = http_build_query($p);
     $headers = $this->set_headers();
     $headers[] = "Referer: ".$this->site."/pg/pages/new/";
     $curl_data['headers'] =  $headers;

     $curl_data['followlocation'] = true;
     $curl_data['echo_header'] = true;
     $curl_data['referer'] = $this->site."/pg/pages/new/";
     $curl_data['url'] = $this->site."/action/pages/edit";

     $this->code = $this->curl($curl_data);

     if (stripos($this->code, 'Pages saved')
      or stripos($this->code, '302 Found')
      or stripos($this->code, '302 Moved Temporarily')
      )
     {
       echo "Page Published";
       $this->get_my_page_post_url();
       return true;
     } 
     else
     {
      echo "Not Allowed, случилась какая-то хуйета";
      return false;
     }
    }
   }
 }