public function findPlayer($player)
{
$results = array();
print_r($this->getSearchUrl($player));
$curl = new CURL();
$curl->addSession($this->getSearchUrl($player));
$curl->setOpt(CURLOPT_RETURNTRANSFER, 1);
$curl->setOpt(CURLOPT_REFERER, 'http://lh.beta.smallballstats.info');
$page = $curl->exec();
$curl->clear();
$page = json_decode($page);
foreach ($page->responseData->results as $result) {
array_push($results, array('url' => $result->unescapedUrl, 'title' => $result->titleNoFormatting, 'content' => $result->contentNoFormatting));
}
sleep(1);
$curl = new CURL();
$curl->addSession($this->getSearchUrl($player, 4));
$curl->setOpt(CURLOPT_RETURNTRANSFER, 1);
$curl->setOpt(CURLOPT_REFERER, 'http://lh.beta.smallballstats.info');
$page = $curl->exec();
$curl->clear();
$page = json_decode($page);
foreach ($page->responseData->results as $result) {
array_push($results, array('url' => $result->unescapedUrl, 'title' => $result->titleNoFormatting, 'content' => $result->contentNoFormatting));
}
print_r($results);
die;
}
public function getPlayByPlay()
{
$url = $this->getPlayByPlayUrl($this->id);
$curl = new CURL();
$curl->addSession($url);
$page = $curl->exec();
$curl->clear();
$this->playByPlay = new SimpleXMLElement($page);
return $this->playByPlay;
}
public function getAll()
{
$result = array();
$html = file_get_html("http://www.eps.uam.es/esp/alumnos/lab_horario.php?horario_id=17&semestre=S2");
$e = $html->find('select');
$e = $e[0];
$curl = new CURL();
$opts = array(CURLOPT_RETURNTRANSFER => true, CURLOPT_FOLLOWLOCATION => true);
foreach ($e->find('option') as $g) {
$result[] = array("id" => $g->value, "name" => $g->innertext);
$id = $g->value;
$curl->addSession("http://www.eps.uam.es/esp/alumnos/lab_horario.php?local_id={$id}&horario_id=17&semestre=S2", $opts);
}
// Ejecuta todas las peticiones en paralelo
$pages = $curl->exec();
$curl->clear();
for ($i = 0; $i < sizeof($pages); $i++) {
$result[$i]["data"] = Laboratorio::get($result[$i]["id"], $page);
}
return $result;
}
function grabproxy($header, $agentstr)
{
// hidemyass.com got hax'd by hysterix!
// these are the 'ghetto tables'; md5's
// of an image we compare to when grabing proxies
// so we can grab the port number with ease.
// shit loads faster than scanning each pixel
// in each image, and easier to implement.
// pretty hax if you ask me, obviously they
// don't want people doing this! The first rule of fight club....
// Also, if you do the md5 locally to just the file it is different from these.
// I believe this is the md5 of the header as well as the image together,
// don't think they are wrong when they don't compare on your system
$ghetto_tables = array('2741898dc5492442a60c48fd8af5f914' => '80', '27760f111201b87996e9d5f1f55e1e2b' => '81', '8c4d39d1386fdb4dc6312a00387ae8be' => '444', '38925677a3ab9071d81b50d0e4d14ce0' => '1080', '5969ad3f3cb42fc2cfc32e667b64db4d' => '1260', '37357c1363a6edac318a513c8a16733a' => '2301', '380ac73e41c1c9f4b460b6aa74fbaea5' => '3124', '70846fe60a6915b3979033fe53f46402' => '3128', '9407ba7a72999731d6cefdc41a7522b4' => '33655', '53fc62ce0db7912b5be729849ef11dff' => '34387', '9229f0e355a3311d1f6b196ffce7cb74' => '6588', 'c1865c575ac4645f47b603deaf98ca60' => '6654', 'a580f19646451c4d832303b596fe6248' => '6666', '2980cfed592e0e31f9b0f30e24e23bf2' => '8000', '9739217797951fd6525313a762007561' => '8080', '0b269894b8fc6b74adb92840528b4e33' => '8118', '14509909876456e7539e95a9a104fcdc' => '8888', '3afb17a502f997278ec096e3347edace' => '9090', '7109cafc0782511575f4dc40e932d2e7' => '9188', '963b608d579bd4a2110e41b11eb6a12a' => '51898', '703a56c126717b1e6791915eee0ed3d8' => '65208');
// Gather an array of proxy lists (About 400 proxies in this list)
$ass_hiders[0] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/1/";
$ass_hiders[1] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/2/";
$ass_hiders[2] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/3/";
$ass_hiders[3] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/4/";
$ass_hiders[4] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/5/";
$ass_hiders[5] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/6/";
$ass_hiders[6] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/7/";
$ass_hiders[7] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/8/";
$ass_hiders[8] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/9/";
$ass_hiders[9] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/10/";
$ass_hiders[10] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/11/";
$ass_hiders[11] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/12/";
$ass_hiders[12] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/13/";
$ass_hiders[13] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/14/";
$ass_hiders[14] = "http://hidemyass.com/proxy-list/All-Countries/fast/hide-planetlab/15/";
$randkey = array_rand($ass_hiders);
// Select a random $ass_hiders page
$failed = false;
//$random_hole = rand(1, count($ass_hiders));
//foreach ($ass_hiders as $ass_hider) { // UR DOIN IT WRONG
$curl = new CURL();
// create the curl instance
$opts = setBrowser(0, 0, $header, $agentstr);
// do not set first variable to 1; we don't need infinite looping
$curl->retry = MAX_RETRYS;
$curl->addSession($ass_hiders[$randkey], $opts[0]);
ob_start();
// this is a hack if i've ever seen one
$result = $curl->exec();
// this is the site returned
ob_end_clean();
// without this, php likes to output a 1 to the screen (something to do with the header info probably)
// unset curl
$curl->clear();
// remove the curl instance
unset($curl);
if (is_array($result)) {
$result = $result[0] . $result[1];
}
$matches = array();
$yanoob = array();
$html = str_get_html($result);
$arrInput = array();
foreach ($html->find('table') as $t) {
$x = 0;
$matches = array();
foreach ($t->find('tr') as $rows) {
foreach ($rows->find('td') as $columns) {
$str = $columns->outertext;
// Strip out IP's and load into array $matches
/* keep the wall of shame up */
//$pattern = '|(\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b)|U';
//$pattern = '/^(1\d{0,2}|2(\d|[0-5]\d)?)\.(1\d{0,2}|2(\d|[0-5]\d)?)
// \.(1\d{0,2}|2(\d|[0-5]\d)?)\.(1\d{0,2}|2(\d|[0-5]\d)?)$/';
//$pattern = '/^(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]\d|\d)(?:[.](?:25[0-5]|2[0-4]\d|1\d\d|[1-9]\d|\d)){3}$/';
$pattern = '|(\\b\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\b)|U';
if (preg_match($pattern, $str, $yatmparr)) {
// we found an ip
$yanoob[0] = $yatmparr[0];
// prepare the ip for the array
unset($yatmparr);
}
foreach ($columns->find('img') as $yaimg) {
$tehport = $yaimg->alt;
if (strcmp($tehport, "port") == 0) {
// grab the port url
$portsrc = $yaimg->src;
$assUrl = split_url($ass_hiders[$randkey]);
$portUrl = split_url($portsrc);
if (isset($portUrl['scheme'])) {
// path absolute, use as-is
$theport = $arrPost['url'];
} else {
// no host, path relative, slap this on the back of the original url; great success!
$newpath = str_replace_once("/", "", $portUrl['path']);
// remove the leading slash if it xists
$theport = $assUrl['scheme'] . "://" . $assUrl['host'] . "/" . $newpath . '?' . $portUrl['query'];
}
$curl = new CURL();
// create the curl instance
$opts = setBrowser(0, 0, $header, $agentstr);
// do not set first variable to 1
$curl->retry = MAX_RETRYS;
$curl->addSession($theport, $opts[0]);
ob_start();
// this is a hack if i've ever seen one
$result = $curl->exec();
// this is the png returned
ob_end_clean();
// without this, php likes to output a 1 to the screen (something to do with the header info probably)
// unset curl
$curl->clear();
// remove the curl instance
unset($curl);
if (is_array($result)) {
$result = $result[0] . $result[1];
}
//print_r($result);
// ingenuity wins out again; hysterix -1 ; hidemyass - 0
// they can slow us down but they cant stop us
$portnum = retPortNum($result, $ghetto_tables);
if (isset($portnum)) {
// everything worked; we only want ip's with ports
$yanoob[1] = $portnum;
array_push($matches, $yanoob);
}
}
}
}
}
}
$html->clear();
// if you dont include these two statements, the damn
unset($html);
// simple html dom becomes simple memory leaker 2.0 because
unset($result);
// of a f*****g "php5 circular references memory leak" - nigger t**s
unset($agentstr);
//Grab a random IP from array $matches
$randkey = array_rand($matches, 1);
$newprox = $matches[$randkey];
return $newprox;
}
protected function setPlayerNcaaIdsForTeam($team, $year)
{
$this->CI->load->library('Parse/NcaaParse');
$cookie = $this->CI->ncaaparse->getCookie();
$curl = new CURL();
$curl->addSession(sprintf('http://web1.ncaa.org/stats/StatsSrv/careerteam?academicYear=%s&coachId=-100&division=1&doWhat=display&idx=&orgId=%s&playerId=-100&sortOn=0&sportCode=MBA', $year, $team->getNcaaId()));
$curl->setOpt(CURLOPT_COOKIE, $cookie);
$curl->setOpt(CURLOPT_REFERER, 'http://web1.ncaa.org/stats/StatsSrv/careersearch');
$page = $curl->exec();
$curl->clear();
$this->CI->load->library('domparser');
$html = $this->CI->domparser->str_get_html($page);
$players = array('' => '');
$playersArray = array();
foreach ($html->find('table.statstable', 1)->find('tr') as $key => $row) {
if ($key > 2) {
$id = $row->find('td', 0)->find('a', 0)->getAttribute('href');
preg_match('/[0-9]+/', $id, $match);
$id = $match[0];
$player = sprintf('%s (%s / %s)', trim($row->find('td', 0)->plaintext), trim($row->find('td', 1)->plaintext), trim($row->find('td', 3)->plaintext));
$name = explode(',', trim($row->find('td', 0)->plaintext));
$playerArray = array('ncaaId' => $id, 'firstName' => trim($name[1]), 'lastName' => trim($name[0]), 'class' => trim($row->find('td', 1)->plaintext), 'position' => trim($row->find('td', 3)->plaintext));
$players[$id] = $player;
$playersArray[$id] = $playerArray;
}
}
$this->players = $players;
$this->playersArray = $playersArray;
return $players;
}
function grab_rosinst($yaheader, $agentstr)
{
$proxyUrl = "http://rosinstrument.com/proxy/plab100.xml";
$curl = new CURL();
// create the curl instance
$opts = $this->setBrowser(0, 0, $yaheader, $agentstr);
// do not set first variable to 1; we don't need infinite looping
$curl->retry = MAX_RETRYS;
$curl->addSession($proxyUrl, $opts[0]);
$result = $curl->exec();
// this is the site returned
$curl->clear();
// remove the curl instance
unset($curl);
// unset curl
if (is_array($result)) {
$result = $result[0];
if (isset($result[1])) {
$result .= $result[1];
}
}
$goodmatches = array();
$matches = array();
$yacntr = 0;
$pattern = '/<title>(.*?)<\\/title>/';
// grabs netblk-41-215-180-130.iconnect.zm:8080 or 66.190.144.90:27445
preg_match_all($pattern, $result, $matches);
for ($i = 0; $i < count($matches[1]); $i++) {
$arrtmp = explode(":", $matches[1][$yacntr]);
$goodmatches[$yacntr][0] = $arrtmp[0];
$goodmatches[$yacntr][1] = $arrtmp[1];
$yacntr++;
}
unset($goodmatches[0]);
unset($goodmatches[1]);
unset($result);
unset($agentstr);
if (empty($goodmatches)) {
// bark at them
return 0;
} else {
return $goodmatches;
// return something
}
}
public function getCookie()
{
$curl = new CURL();
$curl->addSession('http://web1.ncaa.org/stats/StatsSrv/careersearch');
$curl->setOpt(CURLOPT_RETURNTRANSFER, 1);
$curl->setOpt(CURLOPT_HEADER, 1);
$page = $curl->exec();
$curl->clear();
preg_match('|Set-Cookie: (.*);|U', $page, $cookies);
return $cookies[1];
}
public function getPlayer($player)
{
if (is_numeric($player)) {
$player = $this->CI->_player->findOneByNcaaId($player);
}
if (!$player->getName() || !($player->getAtBats() || $player->getInningsPitched())) {
return false;
}
print_r($player);
print_r("\n\n");
$teams = $player->getTeams();
$searchType = $player->getInningsPitched() ? 'pitchers' : 'hitters';
$url = sprintf('http://www.boydsworld.com/cgi/%s.pl?player=%s&style=Contains&submit=Search&team=%s', $searchType, $player->getName(), $teams[0]->getName());
$curl = new CURL();
$curl->addSession($url);
$curl->setOpt(CURLOPT_RETURNTRANSFER, false);
$curl->setOpt(CURLOPT_HEADER, false);
$curl->setOpt(CURLOPT_REFERER, 'http://www.boydsworld.com/data/hitters.html');
$curl->setOpt(CURLOPT_VERBOSE, true);
$page = $curl->exec();
$curl->clear();
print_r($page);
print_r("\n\n");
}
function get_url($link, $config)
{
$url[0] = $link;
if ($config['pars'] == 'curl') {
$curl = new CURL();
$curl->retry = 4;
$opts = array(CURLOPT_RETURNTRANSFER => true);
$curl->addSession($url[0], 0, $opts);
$result = $curl->exec();
$curl->clear();
} elseif ($config['pars'] == 'mcurl') {
$curl = new MCurl();
$curl->threads = 100;
$curl->timeout = 15;
$curl->sec_multiget($url, $result);
} else {
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $link);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_FAILONERROR, true);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 2);
curl_setopt($ch, CURLOPT_HTTPHEADER, array('Accept: application/json', 'X-Requested-With: XMLHttpRequest', 'Connection: Keep-Alive'));
$data = curl_exec($ch);
if ($data === false) {
$err = curl_errno($ch);
$errmsg = curl_error($ch);
$result[0] = '';
} else {
$result[0] = $data;
}
curl_close($ch);
}
return $result[0];
}
}
if (strcasecmp($arrPost['method'], "post") == 0) {
// need to post to site
$opts2 = setBrowser($proxyvar, $arrPost['post'], $header, $agent);
// set browser information
$cntSuccess++;
} elseif (strcasecmp($arrPost['method'], "get") == 0) {
// need to get to site
$opts2 = setBrowser($proxyvar, 1, $header, $agent);
// set browser information
$urlToPost = $urlToPost . "?" . $arrPost['post'];
$cntSuccess++;
}
$curl2 = new CURL();
$curl2->retry = MAX_RETRYS;
$curl2->addSession($urlToPost, $opts2[0]);
//grab the site
ob_start();
// this is a hack if i've ever seen one
$result2 = $curl2->exec();
ob_end_clean();
// without this, php likes to output a 1 to the screen (something to do with the header info probably
$time = date("c");
$curl2->clear();
unset($curl2);
//echo "<br />result:<br />";
//print_r($result2); // server response
// do they want logging?
if (ENABLE_LOG == true) {
if (DEBUG_LEVEL == 0 || DEBUG_LEVEL == 1) {
// begin logging
function multiget($inurls, &$res, $config, $transit, $roster, $lang, $multi = 0)
{
global $db, $cache;
$timeout = 10;
$tcurl = $config['pars'];
$num = $config['multiget'];
$urlss = array_chunk($inurls, $num, TRUE);
foreach ($urlss as $id => $urls) {
if ($tcurl == 'curl') {
$curl = new CURL();
$curl->retry = 2;
$opts = array(CURLOPT_RETURNTRANSFER => true, CURLOPT_CONNECTTIMEOUT => $timeout);
foreach ($urls as $key => $link) {
$curl->addSession($link, $key, $opts);
}
$result = $curl->exec();
$curl->clear();
} elseif ($tcurl == 'mcurl') {
$curl = new MCurl();
$curl->threads = 100;
$curl->timeout = 15;
$curl->sec_multiget($urls, $result);
} else {
foreach ($urls as $id => $link) {
$ch[$id] = curl_init();
curl_setopt($ch[$id], CURLOPT_URL, $link);
curl_setopt($ch[$id], CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch[$id], CURLOPT_FAILONERROR, true);
curl_setopt($ch[$id], CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt($ch[$id], CURLOPT_HTTPHEADER, array("X-Requested-With: XMLHttpRequest", "Accept: text/html, */*", "User-Agent: Mozilla/3.0 (compatible; easyhttp)", "Connection: Keep-Alive"));
}
$mh = curl_multi_init();
foreach ($ch as $id => $h) {
curl_multi_add_handle($mh, $h);
}
$running = null;
do {
curl_multi_exec($mh, $running);
} while ($running > 0);
foreach ($ch as $id => $h) {
$result[$id] = curl_multi_getcontent($h);
}
foreach ($ch as $id => $h) {
curl_multi_remove_handle($mh, $h);
}
curl_multi_close($mh);
unset($ch);
}
if ($multi != 0) {
foreach ($result as $name => $val) {
$res[$name] = $val;
}
} else {
foreach ($result as $name => $val) {
$json = json_decode($val, TRUE);
if ($json['status'] == 'ok' && $json['status_code'] == 'NO_ERROR') {
$transit = insert_stat($json, $roster[$name], $config, $transit);
$res[$name] = pars_data2($json, $name, $config, $lang, $roster[$name]);
$cache->set($name, $res[$name], ROOT_DIR . '/cache/players/');
}
}
}
unset($result, $json);
}
}
function multiget($urls, &$result, $tcurl = 'curl')
{
if ($tcurl == 'curl') {
$curl = new CURL();
$opts = array(CURLOPT_RETURNTRANSFER => true);
foreach ($urls as $key => $link) {
$curl->addSession($link, $key, $opts);
}
$result = $curl->exec();
$curl->clear();
} else {
$curl = new MCurl();
$curl->threads = 100;
$curl->timeout = 15;
unset($results);
$curl->sec_multiget($urls, $result);
}
}