function get_next_page_url($url)
{
$html = new simple_html_dom();
$html->load_file($url);
$next_page = $html->find('.next_page');
$next_page_link = null;
foreach ($next_page as $next_page_link) {
$next_page_link = $next_page_link->href;
}
return 'https://www.goodreads.com' . $next_page_link;
}
public function initCategoryParser($link)
{
$this->_category_link = $link;
$html = new simple_html_dom();
$link = $this->_domain . $link;
$html->load_file($link);
$this->_counter++;
if ($this->_endOfLink($html) || $this->_counter > $this->_pages_to_get) {
return array('last_link' => $this->_category_link, 'links' => $this->_links, 'parsing_data' => $this->_new_parsing_date);
} else {
$this->_parseHtml($html);
}
return array('last_link' => $this->_category_link, 'links' => $this->_links, 'parsing_data' => $this->_new_parsing_date);
}
function getDetail($url)
{
Yii::import('ext.simple_html_dom');
$html = new simple_html_dom();
// $context = stream_context_create($this->user_agent);
// $html->load_file($url, false, $context);
$html->load_file($url);
$db = $html->find('table td[class=bor f2 db]', 0);
if (isset($db->plaintext)) {
return substr($db->plaintext, strlen($db->plaintext) - 2);
} else {
return 0;
}
}
public function getdata()
{
//echo"shreejana";die;
set_time_limit(0);
include 'simple_html_dom.php';
$target_url = 'Nepal Rastra Bank.htm';
$html = new simple_html_dom();
$html->load_file($target_url);
$table = $html->find('/html/body/table[2]/tbody/tr[2]/td[2]/table[2]/tbody');
$table = $table[0];
$i = 0;
//increment array
foreach ($table->find('tr') as $row) {
$date = $row->find('td[1]');
$date = $date[0]->plaintext;
if (preg_match("/[0-9]+[-][0-9]+[-][0-9]+/", $date)) {
$j = 1;
//increment values
foreach ($table->find('tr[1]/td') as $head) {
$currency = trim($head->plaintext);
if ($currency == "Swedish Kr." || $currency == "Danish Kr." || $currency == "HKG\$") {
$rates[$i]['date'] = $date;
$rates[$i]['curname'] = $currency;
$rate = $row->find('td[' . $j . ']');
$rate = trim($rate[0]->plaintext);
$rates[$i]['buyingrate'] = $rate;
$rates[$i]['sellingrate'] = null;
$j++;
$i++;
} elseif ($currency == "Date") {
$j++;
} else {
$rates[$i]['date'] = $date;
$rates[$i]['curname'] = $currency;
$rate = $row->find('td[' . $j . ']');
$rate = trim($rate[0]->plaintext);
$rates[$i]['buyingrate'] = $rate;
$j++;
$rate = $row->find('td[' . $j . ']');
$rate = trim($rate[0]->plaintext);
$rates[$i]['sellingrate'] = $rate;
$j++;
$i++;
}
}
}
}
var_dump($rates);
}
function insert_urls($conn)
{
$target_url = $_POST['t_url'];
// t_url is taken from user input through the text box
$html = new simple_html_dom();
if (!$html->load_file($target_url)) {
$i = 1;
foreach ($html->find('img') as $image) {
$image_url = $image->src;
$pp_image = imagecreatefromstring(file_get_contents($image_url));
imagejpeg($pp_image, 'temp_images/img' . $i . '.jpeg');
// Saves the image as a jpeg file
$detector = new svay\FaceDetector('detection.dat');
if ($detector->faceDetect('temp_images/img' . $i . '.jpeg')) {
// If the detector detects a face
$sql = "INSERT INTO images (url) VALUES ('{$image_url}')";
// Insert that url into the database
$stmt = $conn->prepare($sql);
$stmt->execute();
}
$i++;
}
} else {
echo '<br /><div id="strongtext"><p><strong>Palun sisesta mõni muu aadress.</strong></p></div>';
var_dump($html->load_file($target_url));
}
$temp_files = glob('temp_images/*');
// After the foreach loop is done checking all of the images
foreach ($temp_files as $temp_file) {
if (is_file($temp_file)) {
unlink($temp_file);
}
}
echo '<script>alertFunction();</script>';
// Alert the user that the script has finished working
}
public function getArticleFromUrl($url)
{
$url = $this->_domain . trim($url, '/');
$this->_url = $url;
$this->_url_hash = md5($url);
$this->_articles[$this->_url_hash] = array('url' => $url);
$article_html = new simple_html_dom();
$article_html->load_file($url);
if (is_null($article_html)) {
return;
}
$this->_article_html = $article_html;
$this->_getMetaFromArticle();
$this->_getCategoryFromArticle();
$this->_getArticle();
return $this->_articles;
echo '<pre>';
print_r($this->_articles);
echo '</pre>';
}
function getChanges($job, $project)
{
$commitblacklist = array('Merge branch', 'Merge pull', 'Revert', 'Cleanup');
$url = "http://ci.earth2me.net/viewLog.html?buildId={$job}&tab=buildChangesDiv&buildTypeId={$project}&guest=1";
$html = new simple_html_dom();
$html->load_file($url);
$output = "Change Log:<ul>";
foreach ($html->find('.changelist') as $list) {
foreach ($list->find('.comment') as $comment) {
$text = $comment->innertext;
foreach ($commitblacklist as $matchtext) {
if (stripos($text, $matchtext) !== FALSE) {
$text = "";
}
}
if ($text != "") {
$output .= "<li>{$text}</li>\n";
}
}
}
$output .= "</ul>";
file_put_contents('status.log', "Collected changes! ", FILE_APPEND);
return $output;
}
<?php
//Author: Zakaria Hmaidouch
//Website: zhma.info
//Import simplehtmldom lib, from http://simplehtmldom.sourceforge.net
require 'libs/simple_html_dom.php';
$file = 'data.html';
$html = new simple_html_dom();
// Taget URL
$url = 'http://www.zhma.info';
$counter = 1;
$html->load_file($url);
// Data to target
$titles = $html->find('div[class=portfolio-item] h5');
// Open the file to get existing content
$current = @file_get_contents($file);
$current = '<html>
<head>
<title>Data Scraping</title>
</head>
<body>';
foreach ($titles as $title) {
// Append a new data to the file
$current .= "<b>Project {$counter}:</b> {$title->innertext}<br>";
// Write the contents back to the file
file_put_contents($file, $current);
$counter++;
}
$current .= '</body>
</html>';
<?php
include 'simple_html_dom.php';
$html = new simple_html_dom();
$content = $html->load_file('IAC.html');
$ret = $html->find('tr');
$fullInfo = [];
$currentOrigin = '';
$currentDestination = '';
foreach ($ret as $line) {
if ($line->class == 'destination') {
$link = $line->find('a');
foreach ($link as $curLink) {
$currentDestination = $curLink->innertext;
}
}
if ($line->class == 'important origin') {
$link = $line->find('a');
foreach ($link as $curLink) {
$currentOrigin = $curLink->innertext;
}
}
if ($line->class == 'line even') {
// new flight
$flightInfo = ['origin' => $currentOrigin, 'destination' => $currentDestination];
foreach ($line->children as $child) {
$flightInfo[$child->attr['class']] = $child->plaintext;
}
$temp = [];
foreach ($flightInfo as $key => $value) {
if (in_array($key, ['remarks', 'valid'])) {
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('http://open.live.bbc.co.uk/weather/feeds/en/918702/3dayforecast.rss');
# get an element representing the second paragraph
$element = $html->find('description');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - SA News</title>\n<item>\n<title>SA News</title>\n<description>";
echo $element[1];
echo "</description>\n</item>\n</channel>\n<head/>\n</rss>";
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('http://astrology.horoscope.com/horoscope/dailyhoroscope/tomorrow-career-horoscope.aspx?sign=2');
# get an element representing the second paragraph
$element = $html->find('div[class=fontdef1]');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - Career Horoscopes Taurus</title>\n<item>\n<title>Career Horoscopes Taurus</title>\n<description>";
echo $element[0]->innertext;
echo "</description>\n</item>\n</channel>\n<head/>\n</rss>";
header('Cache-Control: no-cache, must-revalidate');
header('Content-type: application/json');
ini_set("user_agent", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.21 (KHTML, like Gecko) Chrome/19.0.1042.0 Safari/535.21");
ini_set("max_execution_time", 0);
ini_set("memory_limit", "10000M");
ini_set('display_errors', '1');
$currenturl = "";
$isposted = false;
if (!empty($_POST)) {
$currenturl = $_POST['url'];
$isposted = true;
}
if ($isposted) {
include 'simple_html_dom.php';
$htmldom = new simple_html_dom();
$htmldom->load_file($currenturl);
$title = $htmldom->find('title');
echo nl2br('{ "page" : ');
echo nl2br('{ "title" : "' . utf8_encode(trim($title[0]->innertext)) . '",');
$images = $htmldom->find("img");
$bodyitems = $htmldom->find("body p text");
$paragraphs = $bodyitems;
echo nl2br('"images" : [');
$numImages = count($images);
$icount = 0;
foreach ($images as $image) {
if ($icount + 1 == $numImages) {
$cditem = "";
} else {
$cditem = ",";
}
<?php
// example of how to use advanced selector features
include './lib/simple_html_dom/simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('./search.html');
$classg = $html->find('div[class=g]');
foreach ($classg as $g) {
foreach ($g->find('a[class=fl]') as $flclass) {
$flclass->outertext = "";
}
echo $g->outertext;
}
$html->clear();
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('https://www.nationallottery.co.za/powerball_home/results.asp?type=1');
# get an element representing the second paragraph
$element = $html->find('span[class=onGreenBackground]');
$element2 = $html->find('img');
$element3 = $html->find('td');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - Powerball Results</title>\n<item>\n<title>Powerball Results</title>\n<description>";
echo "The winning Powerball numbers for ";
echo $element[0]->innertext;
echo " are ";
$number1 = str_replace("<img src=\"../images/power_balls/ball_", "", $element2[20]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number1);
echo ", ";
$number2 = str_replace("<img src=\"../images/power_balls/ball_", "", $element2[21]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number2);
echo ", ";
$number3 = str_replace("<img src=\"../images/power_balls/ball_", "", $element2[22]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number3);
echo ", ";
$number4 = str_replace("<img src=\"../images/power_balls/ball_", "", $element2[23]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number4);
echo ", ";
$number5 = str_replace("<img src=\"../images/power_balls/ball_", "", $element2[24]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number5);
echo ", powerball: ";
$number6 = str_replace("<img src=\"../images/power_balls/power_", "", $element2[25]);
$idCidPoli = str_replace('onPesquisaClick(this, ', '', $cidade->onclick);
$idCidPoli = str_replace(',', '', $idCidPoli);
$idCidPoli = str_replace('"', '', $idCidPoli);
$idCidPoli = str_replace('\'', '', $idCidPoli);
$idCidPoli = str_replace(');', '', $idCidPoli);
//guarda a posição do espaço que separa o id do prefeito ou vereador do id do municipio
$espaco = strripos($idCidPoli, ' ');
//guarda o id do prefeito ou do vereador que é 11 ou 13
$codigoCargo = substr($idCidPoli, 0, $espaco);
//guarda o id da cidade
$codigoMunicipio = substr($idCidPoli, $espaco + 1);
//modifica a url do ajax que é exibida na tela
$urlAjaxPrefeitoVereador = "http://divulgacand2012.tse.jus.br/divulgacand2012/pesquisarCandidato.action?siglaUFSelecionada=" . $siglaUF . "&codigoMunicipio=" . $codigoMunicipio . "&codigoCargo=" . $codigoCargo . "&codigoSituacao=0";
$htmlCidade = new simple_html_dom();
//carrega o html que possui todos prefeitos ou vereadores da cidade
$htmlCidade->load_file($urlAjaxPrefeitoVereador);
//pega os input com o id e a ultima atualização do politico
$candidato = $htmlCidade->find('tr[class="odd gradeX"] input');
$htmlCidade->clear();
unset($htmlCidade);
//array para guardar ids dos candidatos e ids da ultima atualização do candidato
$array = array("sqCandidato", "dtUltimaAtualizacao");
$i = 0;
$j = 0;
foreach ($candidato as $elemento) {
if (strcmp($elemento->name, "sqCandidato") == 0) {
$array["sqCandidato"][$i] = $elemento->value;
$i++;
} else {
$array["dtUltimaAtualizacao"][$j] = $elemento->value;
$j++;
$target_url = $_GET['q'];
$qi = $_GET['qi'];
$present = 0;
$question_id = 0;
include 'autoloader.php';
use NlpTools\Classifiers\MultinomialNBClassifier;
use NlpTools\Documents\TokensDocument;
use NlpTools\Documents\TrainingSet;
use NlpTools\FeatureFactories\DataAsFeatures;
use NlpTools\Models\FeatureBasedNB;
use NlpTools\Stemmers\PorterStemmer;
use NlpTools\Tokenizers\WhitespaceTokenizer;
use NlpTools\Utils\StopWords;
include_once 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file($target_url);
include_once 'connect.inc.php';
//echo "<br/>";
foreach ($html->find('h1') as $link) {
$ans = $link->getAttribute('itemprop');
if ($ans == "name") {
foreach ($link->find('a') as $link1) {
echo "<div class='col-lg-offset-1 bg-primary col-lg-10' style='border-bottom:1px solid;'>";
echo '<h1>' . $link1->text() . "</h1><br/>";
echo "</div>";
$query = "SELECT * from `question` where quest='" . $link1->text() . "'";
$query_run = mysql_query($query);
if (mysql_num_rows($query_run) == 1) {
$present = 1;
while ($row = mysql_fetch_array($query_run)) {
$question_id = $row['q_id'];
public function indexAction()
{
if ($this->_request->isPost()) {
$params = $this->_request->getParams();
$date = $params['date'];
if ($date != "") {
$date_arr_temp = explode("-", $date);
$date_insert = $date_arr_temp[2] . "-" . $date_arr_temp[1] . "-" . $date_arr_temp[0];
$html = new simple_html_dom();
$link_load = "http://www.minhngoc.net.vn/ket-qua-xo-so/{$date}.html";
$html->load_file($link_load);
if (!empty($html)) {
$bangdo_mn = $html->find(".bkqmiennam", 0);
$bangdo_mb = $html->find(".bkqtinhmienbac", 0);
$this->view->bangdo_mn = $bangdo_mn;
$this->view->bangdo_mb = $bangdo_mb;
$title_date = $html->find(".bkqmiennam", 0)->children(0)->find("table", 0)->find("tr", 1);
$title_date = strip_tags($title_date);
// get title
$date_present = date('d-m-Y');
$m_lichxoso = new Default_Model_Lichxoso();
$arr_lichxoso = $m_lichxoso->getBangDo($date)->toArray();
$temp_madai = $arr_lichxoso['madai'];
$arr_madai = explode("|", $temp_madai);
$soluong_dai = sizeof($arr_madai);
$db = Zend_Db_Table::getDefaultAdapter();
if ($date == $date_present) {
if ($this->checkTimeDai("mn")) {
$arr_bangdo_mn = array();
for ($i = 0; $i < $soluong_dai - 1; $i++) {
$sl = 2;
$giai = 8;
while ($sl <= 10) {
$v_temp = (string) $bangdo_mn->find("td table", 1)->find(".rightcl", $i)->find("tr", $sl);
$arr_bangdo_mn[$arr_madai[$i]]["giai" . $giai] = (string) $bangdo_mn->find("td table", 1)->find(".rightcl", $i)->find("tr ", $sl);
$sl++;
$giai--;
}
}
if (sizeof($arr_bangdo_mn) > 0) {
foreach ($arr_bangdo_mn as $key_tenbang => $arr_bang) {
if (!$this->checkExistDataVeDo($db, $key_tenbang, $date_insert)) {
$sql = $this->addNewDataVeDo($db, $key_tenbang, $arr_bang, $date_insert);
$db->query($sql);
} else {
$sql = $this->updateDataVeDo($db, $key_tenbang, $arr_bang, $date_insert);
$db->query($sql);
}
}
}
}
// mien bac
if ($this->checkTimeDai("mb")) {
$key_tenbang = $arr_madai[$soluong_dai - 1];
$sl = 1;
$giai = 0;
$arr_bangdo_mb = array();
while ($sl <= 8) {
$arr_bangdo_mb["giai" . $giai] = (string) $bangdo_mb->find('tr', $sl)->find("td", 1);
$sl++;
$giai++;
}
if ($arr_bangdo_mb > 0) {
if (!$this->checkExistDataVeDo($db, $key_tenbang, $date_insert)) {
$sql = $this->addNewDataVeDo($db, $key_tenbang, $arr_bangdo_mb, $date_insert);
$db->query($sql);
} else {
$sql = $this->updateDataVeDo($db, $key_tenbang, $arr_bangdo_mb, $date_insert);
$db->query($sql);
}
}
}
} else {
$arr_bangdo_mn = array();
for ($i = 0; $i < $soluong_dai - 1; $i++) {
$sl = 2;
$giai = 8;
while ($sl <= 10) {
$v_temp = (string) $bangdo_mn->find("td table", 1)->find(".rightcl", $i)->find("tr", $sl);
$arr_bangdo_mn[$arr_madai[$i]]["giai" . $giai] = (string) $bangdo_mn->find("td table", 1)->find(".rightcl", $i)->find("tr ", $sl);
$sl++;
$giai--;
}
}
if (sizeof($arr_bangdo_mn) > 0) {
foreach ($arr_bangdo_mn as $key_tenbang => $arr_bang) {
if (!$this->checkExistDataVeDo($db, $key_tenbang, $date_insert)) {
$sql = $this->addNewDataVeDo($db, $key_tenbang, $arr_bang, $date_insert);
$db->query($sql);
} else {
$sql = $this->updateDataVeDo($db, $key_tenbang, $arr_bang, $date_insert);
$db->query($sql);
}
}
}
// mien bac
$key_tenbang = $arr_madai[$soluong_dai - 1];
$sl = 1;
$giai = 0;
$arr_bangdo_mb = array();
while ($sl <= 8) {
$arr_bangdo_mb["giai" . $giai] = (string) $bangdo_mb->find('tr', $sl)->find("td", 1);
$sl++;
$giai++;
}
if (sizeof($arr_bangdo_mb) > 0) {
if (!$this->checkExistDataVeDo($db, $key_tenbang, $date_insert)) {
$sql = $this->addNewDataVeDo($db, $key_tenbang, $arr_bangdo_mb, $date_insert);
$db->query($sql);
} else {
$sql = $this->updateDataVeDo($db, $key_tenbang, $arr_bangdo_mb, $date_insert);
$db->query($sql);
}
}
}
}
}
}
}
public function getKelas($ps, $kode, $kelas)
{
$nom = null;
// Create a DOM object
$html = new simple_html_dom();
// Load HTML from a URL
$html->load_file('https://six.akademik.itb.ac.id/publik/daftarkelas.php?ps=' . $ps . '&semester=1&tahun=2015&th_kur=2013');
foreach ($html->find('ol') as $ul) {
foreach ($ul->find('li') as $li) {
// Mencari mata kuliah berdasarkan kode kuliah
if (preg_match('/^' . $kode . '/', $li->plaintext)) {
$i = 0;
foreach ($li->find('li') as $child) {
if (!strcmp($child->children(0)->plaintext, $kelas)) {
//return $child->children(0)->href;
$nom = $child->children(0)->plaintext;
$link = $child->children(0)->href;
break;
}
$i++;
}
}
}
}
// mengecek apakah terdapat kelas atau tidak
if ($nom) {
return $link;
} else {
return "not found";
}
}
<?php
require 'simple_html_dom.php';
$cat_rem = fopen("cat_list.txt", "w");
fwrite($cat_rem, "");
fclose($cat_rem);
$cat_handle = fopen("cat_list.txt", "a");
$cat_counter = 0;
$cat_url = new simple_html_dom();
$cat_url->load_file('http://www.toy.ru/catalog/');
echo "<h4>Загрузили hmtl каталога товаров</h4>";
flush();
ob_flush();
if (count($cat_url->find('.category_list'))) {
foreach ($cat_url->find('.category_list') as $catalog) {
foreach ($catalog->find('div.item a') as $link) {
$category = file_get_html("http://www.toy.ru" . $link->href);
echo "<p>Загрузили hmtl категории http://www.toy.ru" . $link->href . " </p>";
flush();
ob_flush();
if (count($category->find('div.item a'))) {
foreach ($category->find('div.item a') as $link) {
$link_title = "";
if (count($link->find('img'))) {
$link_title = $link->find('img', 0)->title;
echo "<p>Название категории <strong>" . $link_title . "</strong></p>";
}
fwrite($cat_handle, $link->href . ";" . $link_title . "\r\n");
$cat_counter++;
echo "<p>Записали url категории http://www.toy.ru" . $link->href . " в файл </p>";
$subcat1 = file_get_html("http://www.toy.ru" . $link->href);
public function fetchDataFromPriceGrabberApi($upc)
{
ini_set('max_execution_time', 999999);
ini_set('memory_limit', '400M');
require_once dirname(BASEPATH) . '/system/application/libraries/simple_html_dom.php';
$debug = false;
$url = 'http://www.pricegrabber.com/search_request.php?form_keyword=' . $upc . '&some_id=&id_type=&requestParams=Tjs%3D&vendorIds=YTowOnt9&st=query&sv=findit_top&kw_suggest=0&topcat_menu=6&zip_code=54001';
if ($debug) {
echo '<br />' . $url . '<br />';
}
$html = new simple_html_dom();
$html->load_file($url);
if ($html->find('div[class=product_description]', 0)) {
$name = $html->find('div[class=product_description]', 0)->find('h1', 0)->plaintext;
} else {
$html->clear();
return array();
}
$desc = '';
if ($html->find('p[id=product_details_description]', 0)) {
$desc = $html->find('p[id=product_details_description]', 0)->plaintext;
}
$product_image = '';
if ($html->find('div[class=product_img]', 0)) {
$product_image = $html->find('div[class=product_img]', 0)->find('img', 0)->getAttribute('src');
}
$items = array();
if ($html->find('table[class=pricing_tbl]', 0)) {
$price_table = $html->find('table[class=pricing_tbl]', 0);
} else {
$html->clear();
return array();
}
if ($debug) {
echo $price_table;
}
foreach ($price_table->find('tr') as $tr) {
$mystring = $tr->getAttribute('class');
$findme = 'section';
$pos = strpos($mystring, $findme);
if ($pos !== false) {
continue;
}
if ('noseller' == $tr->find('td', 0)->getAttribute('class')) {
break;
}
$bottom_price = $this->getPriceForPriceGrabber($tr->find('td', 1)->find('div[class=deftip]', 0)->plaintext);
$price = $this->getPriceForPriceGrabber($tr->find('td', 2)->plaintext);
$shopping_price = $bottom_price - $price;
$seller_link = $tr->find('td', 4)->find('a', 0);
$href = $seller_link->getAttribute('href');
$img = $seller_link->find('img', 0);
if ($img) {
$menu = $img->getAttribute('alt');
$logo = $img->getAttribute('src');
} else {
$menu = $seller_link->plaintext;
$logo = '';
}
$data = array('name' => $name, 'desc' => $desc, 'manu' => $menu, 'url' => $href, 'productImage' => $product_image, 'basePrice' => trim($price), 'shippingPrice' => trim($shopping_price), 'price' => trim($price), 'logo' => $logo);
$items[] = $data;
if ($debug) {
echo '<br />';
echo '--------------------------';
echo '<br />';
echo '<pre>';
print_r($data);
echo '</pre>';
echo '<br />';
echo 'Name: ' . $name;
echo '<br />';
echo 'Desc: ' . $desc;
echo '<br />';
echo 'Bottom Price: ' . $bottom_price;
echo '<br />';
echo 'Price: ' . $price;
echo '<br />';
echo 'Shipping Price: ' . $shopping_price;
echo '<br />';
echo 'Seller Name: ' . $menu;
echo '<br />';
echo 'Seller Image: ' . $logo;
echo '<br />';
echo 'Store Link: ' . $href;
echo '<br />';
echo '--------------------------';
echo '<br />';
}
}
$html->clear();
return $items;
}
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('http://mydorpie.com/m/?page=tv_sabc2_today');
# get an element representing the second paragraph
$element = $html->find('div[id=blp]');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - SABC 2</title>\n<item>\n<title>SABC 2</title>\n<description>";
$full_value = "";
foreach ($element as $value) {
if (substr($value->innertext, 3, 2) >= 17) {
$value1 = str_replace("<b>", "", $value->innertext);
$value2 = str_replace("</b> ", " - ", $value1);
$full_value = $full_value . $value2;
$full_value = $full_value . ", ";
}
}
echo substr($full_value, 0, -2);
echo "</description>\n</item>\n</channel>\n<head/>\n</rss>";
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('http://love.horoscope.com/astrology/tomorrow-love-horoscope-taurus.html');
# get an element representing the second paragraph
$element = $html->find('div[class=fontdef1]');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - Love Horoscopes Taurus</title>\n<item>\n<title>Love Horoscopes Taurus</title>\n<description>";
echo $element[0]->innertext;
echo "</description>\n</item>\n</channel>\n<head/>\n</rss>";
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('http://mg.co.za/section/news-africa/');
# get an element representing the second paragraph
$element = $html->find('a');
$element2 = $html->find('p');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - International News</title>\n<item>\n<title>International News</title>\n<description>";
echo $element[39]->innertext;
echo " - ";
echo $element2[1]->innertext;
echo " MTN Play and mg.co.za ";
echo "</description>\n</item>\n</channel>\n<head/>\n</rss>";
function save()
{
if ($this->indexed == false) {
$xml = simplexml_load_file("../data/uq/degrees/" . $this->code . ".xml");
$html = new simple_html_dom();
$html->load_file($this->coursesite);
$courses = $xml->addChild("courses");
foreach ($html->find("tr") as $row) {
if (!is_null($row->find("td", 0)->find("a", 0))) {
$courselink = $row->find("td", 0)->find("a", 0);
$coursecode = trim(preg_replace('/\\t+/', '', $courselink->innertext));
$course = $courses->addChild("course");
$course->addAttribute("code", $coursecode);
$course->addAttribute("length", $row->find("td", 1)->innertext);
$coursetitle = $row->find("td", 2)->innertext;
//Remove tooltips from title
if (stripos($coursetitle, "<sup>") !== false) {
$course->addAttribute("title", removeSup($coursetitle));
} else {
$course->addAttribute("title", $coursetitle);
}
}
}
$xml->saveXML("../data/uq/degrees/" . $this->code . ".xml");
echo "Information for {$this->title} has been collected and added to the data file.</br>";
echo "<a href='../data/uq/degrees/" . $this->code . ".xml'>{$this->title} data file</a><br/><br/>";
}
}
if (!$status) {
die("Failed to select database!");
}
include 'simple_html_dom.php';
$html = new simple_html_dom();
$page = $_GET['url'];
$pageArr = explode("/", $page);
$pageTot = count($pageArr);
$pageName = $pageArr[$pageTot - 1];
$pageNameRec = str_replace("-", " ", $pageName);
$pageNameRec1 = str_replace("s.html", "", $pageNameRec);
$pageNameArr = explode(".", $pageName);
$pageNameArr1 = explode("-", $pageNameArr[0]);
$tot = count($pageNameArr1);
$catName = $pageNameArr1[$tot - 1];
$html->load_file($page);
$i = 0;
foreach ($html->find('table tr td[class=stone-main]') as $element) {
if ($i == 0) {
$name = strip_tags(trim($element->innertext));
}
$i++;
}
$name = explode("::", $name);
//$name = $pageNameRec1;
$imageArr = array();
$fullArr = array();
foreach ($html->find('table tr') as $row) {
$cells1 = $row->find('td img[width=170]');
if (count($cells1) >= 3) {
$imageArr[0] = $cells1[0]->src;
#$J++;
#continue;
#}
ob_start();
// ---------------------------------------------------------------------------------------
#echo $link . "<br>";
// ----------------- we
#echo $test_link;
$html = new simple_html_dom();
$this_to_parse = "https://connect.data.com" . $link;
#echo $this_to_parse . "\n";
// DO NOT DDOS THESE PPL. Have been blacklisted from my home IP. As if there's no way around that, but still a P.I.T.A
$rand_seconds = rand(2, 13);
// 2 to 13 second delay between requests. 1-10 is just as arbitrary
sleep($rand_seconds);
$dom = $html->load_file($this_to_parse);
if (!empty($dom)) {
#echo "Loaded file!<br>";
}
// Find the exact thing -- industries array --------------------------------------------
$i = 0;
$industries = '';
$location = '';
$name = '';
$website = '';
$size = '';
foreach ($html->find('.seo-company-info > table > tbody tr:nth-child(\'5\') > .seo-company-label') as $ele) {
global $industries;
$str = $ele->innertext;
if ($str == "Industries") {
$industries = $html->find('.seo-company-info > table > tbody tr:nth-child(5) > .seo-company-data', $i)->innertext;
for ($i = 0; $i < 3; ++$i) {
$dom = file_get_dom($filename);
//stat_dom($dom);
$dom->clear();
unset($dom);
dump_memory();
flush();
}
echo 'final: ' . number_format(memory_get_usage(), 0, '.', ',') . '<br>';
flush();
echo '<br><br>[one object]<br>init memory: ' . number_format(memory_get_usage(), 0, '.', ',') . '<br>';
echo '------------------------------------------<br>';
flush();
$dom = new simple_html_dom();
for ($i = 0; $i < 3; ++$i) {
$dom->load_file($filename);
$dom->clear();
dump_memory();
}
unset($dom);
echo 'final: ' . number_format(memory_get_usage(), 0, '.', ',') . '<br>';
flush();
echo '<br><br>[multi objects without clear memory]<br>init memory: ' . number_format(memory_get_usage(), 0, '.', ',') . '<br>';
echo '------------------------------------------<br>';
flush();
for ($i = 0; $i < 3; ++$i) {
$dom = file_get_dom($filename);
dump_memory();
}
echo 'final: ' . number_format(memory_get_usage(), 0, '.', ',') . '<br>';
flush();
public function getFileName()
{
$file_path = $this->work_folder . $this->file_data["current_file_name"];
$tmp_file = new simple_html_dom($str = null, $lowercase = true, $forceTagsClosed = true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN = false);
$tmp_file->load_file($file_path);
$sub_category = $tmp_file->find("[id=sub-category-sub-title]");
return $this->convertToTranslit($sub_category[0]->innertext);
}
<?php
# create and load the HTML
include 'simple_html_dom.php';
$html = new simple_html_dom();
$html->load_file('https://www.nationallottery.co.za/lotto_home/results.asp?type=2');
# get an element representing the second paragraph
$element = $html->find('span[class=onGreenBackground]');
$element2 = $html->find('img');
$element3 = $html->find('td');
# output it!
echo "<rss>\n<channel>\n<title>Bluefin Mobile - Lotto Plus Results</title>\n<item>\n<title>Lotto Plus Results</title>\n<description>";
echo "The winning Lotto Plus numbers for ";
echo $element[0]->innertext;
echo " are ";
$number1 = str_replace("<img src=\"../images/balls/ball_", "", $element2[21]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number1);
echo ", ";
$number2 = str_replace("<img src=\"../images/balls/ball_", "", $element2[22]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number2);
echo ", ";
$number3 = str_replace("<img src=\"../images/balls/ball_", "", $element2[23]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number3);
echo ", ";
$number4 = str_replace("<img src=\"../images/balls/ball_", "", $element2[24]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number4);
echo ", ";
$number5 = str_replace("<img src=\"../images/balls/ball_", "", $element2[25]);
echo str_replace(".gif\" width=\"34\" height=\"40\" />", "", $number5);
echo ", ";
$number6 = str_replace("<img src=\"../images/balls/ball_", "", $element2[26]);
<PUCE colorpuce="orange" level="1" type="square"/>
<PUCE colorpuce="green" level="2" type="disc"/>
<PUCE colorpuce="orange" level="3" type="circle"/>
<PUCE colorpuce="green" level="4" type="square"/>
<PAGE backcolor="#0033FF" font="Comic sans MS" linkcolor="yellow" textcolor="white"/>
<TITLES textcolor="white"/>
</PREFERENCES>';
$filename = "east.xml";
//supprimer fichier existant
if (file_exists($filename)) {
unlink($filename);
}
// 1 : on ouvre le fichier
$fichier = fopen($filename, "a+");
$html1 = new simple_html_dom();
$html1->load_file('test.html');
//$titre = $html1->find('h2',0)->innertext;
/*
$title = $html1->find('.pagetitre');
$contenu .='
<PAGE_TITRE>
<TITRE>'.$title->plaintext.'</TITRE><AUTEUR></AUTEUR>
</PAGE_TITRE>';
*/
/****************************************/
//H
for ($i = 1; $i < 7; $i++) {
$titres = 'h' . $i;
$titre = $html1->find("" . $titres . "");
foreach ($titre as $t) {
echo $t->plaintext;
