public function __construct($strUrl, $strJqClass = null, $strJqSetupFunc = null, $strQcClass = null, $strQcBaseClass = 'QPanel')
{
$this->hasDisabledProperty = false;
$html = file_get_html($strUrl);
if ($strJqClass === null) {
$nodes = $html->find('h1.entry-title');
$strJqClass = preg_replace('/ .*/', '', $nodes[0]->plaintext);
}
parent::__construct($strJqClass, $strJqSetupFunc, $strQcClass, $strQcBaseClass);
$htmlOptions = $html->find('section[id=options] div.api-item');
foreach ($htmlOptions as $htmlOption) {
$type = $this->add_option($htmlOption);
if ($this->is_event_option($type)) {
$this->add_event($htmlOption, $type);
}
}
$htmlEvents = $html->find('section[id=events] div.api-item');
foreach ($htmlEvents as $htmlEvent) {
$this->add_event($htmlEvent);
}
$htmlMethods = $html->find('section[id=methods] div.api-item');
$this->reset_names();
foreach ($htmlMethods as $htmlMethod) {
$this->add_method($htmlMethod);
}
}
public function getDpdOrderTracking()
{
$consignment = $this->getRequest()->getParam('consignment', 15502405041348.0);
$link = 'http://www.dpd.co.uk/tracking/quicktrack.do?search.consignmentNumber=' . $consignment . '&search.searchType=16&search.javascriptValidated=0&appmode=guest';
try {
$html = file_get_html($link);
} catch (Exception $e) {
var_dump($e);
}
$Status = "Vide";
$target_script = "Vide";
foreach ($html->find('script') as $html_script) {
if (strstr($html_script->outertext, "var trackCode =")) {
$target_script = $html_script->outertext;
}
}
$pattern = "/var trackCode = \\'(.*?)\\';*/";
preg_match($pattern, $target_script, $matches);
$data = array();
$data['Status'] = $html->find('td[class=app-light-row-one app-table-indent] div[id=' . $matches[1] . '_text]', 0)->plaintext;
$data['Parcel_No'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 0)->plaintext;
$data['Reference'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 1)->plaintext;
$data['consignment'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 2)->plaintext;
$data['Post_Code'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 3)->plaintext;
$data['Collected_Date'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 4)->plaintext;
$data['Service'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 5)->plaintext;
$data['Delivery_Status'] = $html->find('td[class=app-light-row-one app-border-top app-data-row]', 6)->plaintext;
$trackingtable = $html->find('table[id=parceldetail]', 0)->outertext;
$data['trackingtable'] = str_replace("SPICERS LTD", "WAREHOUSE", $trackingtable);
return $data;
}
public function collectData(array $param)
{
$page = 0;
$tags = '';
if (isset($param['p'])) {
$page = (int) preg_replace("/[^0-9]/", '', $param['p']);
$page = $page - 1;
$page = $page * 50;
}
if (isset($param['t'])) {
$tags = urlencode($param['t']);
}
$html = file_get_html("http://mspabooru.com/index.php?page=post&s=list&tags={$tags}&pid={$page}") or $this->returnError('Could not request Mspabooru.', 404);
foreach ($html->find('div[class=content] span') as $element) {
$item = new \Item();
$item->uri = 'http://mspabooru.com/' . $element->find('a', 0)->href;
$item->postid = (int) preg_replace("/[^0-9]/", '', $element->getAttribute('id'));
$item->timestamp = time();
$item->thumbnailUri = $element->find('img', 0)->src;
$item->tags = $element->find('img', 0)->getAttribute('alt');
$item->title = 'Mspabooru | ' . $item->postid;
$item->content = '<a href="' . $item->uri . '"><img src="' . $item->thumbnailUri . '" /></a><br>Tags: ' . $item->tags;
$this->items[] = $item;
}
}
function ExtractContent($url)
{
$html2 = file_get_html($url);
$text = $html2->find('div.column', 0)->innertext;
$text = preg_replace('@<script[^>]*?>.*?</script>@si', '', $text);
return $text;
}
public function collectData(array $param)
{
$html = '';
$link = 'http://www.leboncoin.fr/annonces/offres/' . $param[r] . '/?f=a&th=1&q=' . $param[k];
$html = file_get_html($link) or $this->returnError('Could not request LeBonCoin.', 404);
$list = $html->find('.list-lbc', 0);
if ($list === NULL) {
return;
}
$tags = $list->find('a');
foreach ($tags as $element) {
$item = new \Item();
$item->uri = $element->href;
$title = $element->getAttribute('title');
$content_image = $element->find('div.image', 0)->find('img', 0);
if ($content_image !== NULL) {
$content = '<img src="' . $element->find('div.image', 0)->find('img', 0)->getAttribute('src') . '" alt="thumbnail">';
}
$date = $element->find('div.date', 0)->find('div', 0) . $element->find('div.date', 0)->find('div', 1) . '<br/>';
$detailsList = $element->find('div.detail', 0);
for ($i = 1; $i < 4; $i++) {
$line = $detailsList->find('div', $i);
$content .= $line;
}
$item->title = $title . ' - ' . $detailsList->find('div', 3);
$item->content = $content . $date;
$this->items[] = $item;
}
}
public function parseRss()
{
$channel = Xml::toArray(Xml::build($this->args[0])->channel);
$items = $channel['channel']['item'];
$list = $this->PinterestPin->find('list', array('fields' => array('id', 'guid')));
$data = array();
foreach ($items as $item) {
if (!in_array($item['guid'], $list)) {
$html = file_get_html($item['guid']);
$image = $html->find('img.pinImage', 0);
if (is_object($image)) {
$data[] = array('guid' => $item['guid'], 'title' => $item['title'], 'image' => $image->attr['src'], 'description' => strip_tags($item['description']), 'created' => date('Y-m-d H:i:s', strtotime($item['pubDate'])));
}
}
}
if (!empty($data)) {
if ($this->PinterestPin->saveAll($data)) {
$this->out(__d('pinterest', '<success>All records saved sucesfully.</success>'));
return true;
} else {
$this->err(__d('pinterest', 'Cannot save records.'));
return false;
}
}
$this->out(__d('pinterest', '<warning>No records saved.</warning>'));
}
function CADExtractContent($url)
{
$html3 = file_get_html($url);
preg_match_all("/http:\\/\\/cdn2\\.cad-comic\\.com\\/comics\\/cad-\\S*png/", $html3, $url2);
$img = implode($url2[0]);
return $img;
}
function CoinDeskExtractContent($url)
{
$html2 = file_get_html($url);
$text = $html2->find('div.single-content', 0)->innertext;
$text = strip_tags($text, '<p><a><img>');
return $text;
}
public function collectData(array $param)
{
$html = '';
if (isset($param['q'])) {
/* keyword search mode */
$this->request = $param['q'];
$html = file_get_html('https://www.google.com/search?q=' . urlencode($this->request) . '&num=100&complete=0&tbs=qdr:y,sbd:1') or $this->returnError('No results for this query.', 404);
} else {
$this->returnError('You must specify a keyword (?q=...).', 400);
}
$emIsRes = $html->find('div[id=ires]', 0);
if (!is_null($emIsRes)) {
foreach ($emIsRes->find('li[class=g]') as $element) {
$item = new Item();
// Extract direct URL from google href (eg. /url?q=...)
$t = $element->find('a[href]', 0)->href;
$item->uri = '' . $t;
parse_str(parse_url($t, PHP_URL_QUERY), $parameters);
if (isset($parameters['q'])) {
$item->uri = $parameters['q'];
}
$item->title = $element->find('h3', 0)->plaintext;
$item->content = $element->find('span[class=st]', 0)->plaintext;
$this->items[] = $item;
}
}
}
public function collectData(array $param)
{
$html = file_get_html('http://lesjoiesducode.fr/') or $this->returnError('Could not request LesJoiesDuCode.', 404);
foreach ($html->find('div.blog-post') as $element) {
$item = new Item();
$temp = $element->find('h1 a', 0);
$titre = html_entity_decode($temp->innertext);
$url = $temp->href;
$temp = $element->find('div.blog-post-content', 0);
// retrieve .gif instead of static .jpg
$images = $temp->find('p img');
foreach ($images as $image) {
$img_src = str_replace(".jpg", ".gif", $image->src);
$image->src = $img_src;
}
$content = $temp->innertext;
$auteur = $temp->find('i', 0);
$pos = strpos($auteur->innertext, "by");
if ($pos > 0) {
$auteur = trim(str_replace("*/", "", substr($auteur->innertext, $pos + 2)));
$item->name = $auteur;
}
$item->content .= trim($content);
$item->uri = $url;
$item->title = trim($titre);
$this->items[] = $item;
}
}
public function getContentSsc($link)
{
$data = file_get_html($link);
$table1 = $data->find('table', 0);
$content = '<table>';
$content .= '<tbody>';
foreach ($table1->find('tr') as $tr) {
if ($tr->find('th', 0)) {
$content .= '<tr>';
$content .= '<th>';
$content .= $tr->find('th', 0)->plaintext;
$content .= '</th>';
$content .= '<td>';
if ($tr->find('td', 0)->find('a', 0)) {
$content .= '<a target="_blank" href="' . $tr->find('td', 0)->find('a', 0)->href . '">' . $tr->find('td', 0)->plaintext . '</a>';
} else {
$content .= $tr->find('td', 0)->plaintext;
}
$content .= '</td>';
$content .= '</tr>';
}
}
$content .= '</tbody>';
$content .= '</table>';
return $content;
}
public function collectData(array $param)
{
$html = '';
$baseUri = 'http://www.superbwallpapers.com';
$this->category = $param['c'] ?: '';
// All default
$this->resolution = $param['r'] ?: '1920x1200';
// Wide wallpaper default
$num = 0;
$max = $param['m'] ?: 36;
$lastpage = 1;
// Get last page number
$link = $baseUri . '/' . $this->category . '/9999.html';
$html = file_get_html($link);
$lastpage = min($html->find('.paging .cpage', 0)->innertext(), ceil($max / 36));
for ($page = 1; $page <= $lastpage; $page++) {
$link = $baseUri . '/' . $this->category . '/' . $page . '.html';
$html = file_get_html($link) or $this->returnError('No results for this query.', 404);
foreach ($html->find('.wpl .i a') as $element) {
$thumbnail = $element->find('img', 0);
$item = new \Item();
$item->uri = str_replace('200x125', $this->resolution, $thumbnail->src);
$item->timestamp = time();
$item->title = $element->title;
$item->thumbnailUri = $thumbnail->src;
$item->content = $item->title . '<br><a href="' . $item->uri . '">' . $thumbnail . '</a>';
$this->items[] = $item;
$num++;
if ($num >= $max) {
break 2;
}
}
}
}
public static function getPlayStoreVersion($packageName)
{
$url = "https://play.google.com/store/apps/details?id=" . $packageName;
$html = file_get_html($url);
$ret = $html->find('div[itemprop=softwareVersion]');
return $ret[0]->plaintext;
}
public function collectData(array $param)
{
$link = 'http://www.monde-diplomatique.fr';
$html = file_get_html($link) or $this->returnError('Could not request MondeDiplo. for : ' . $link, 404);
foreach ($html->find('div.laune') as $element) {
$item = new Item();
$item->uri = 'http://www.monde-diplomatique.fr' . $element->find('a', 0)->href;
$item->title = $element->find('h3', 0)->plaintext;
$item->content = $element->find('div.dates_auteurs', 0)->plaintext . '<br>' . strstr($element->find('div', 0)->plaintext, $element->find('div.dates_auteurs', 0)->plaintext, true);
$this->items[] = $item;
}
$liste = $html->find('div.listes', 0);
// First list
foreach ($liste->find('li') as $e) {
$item = new Item();
$item->uri = 'http://www.monde-diplomatique.fr' . $e->find('a', 0)->href;
$item->title = $e->find('a', 0)->plaintext;
$item->content = $e->find('div.dates_auteurs', 0)->plaintext;
$this->items[] = $item;
}
foreach ($html->find('div.liste ul li') as $element) {
if ($element->getAttribute('class') != 'intrapub') {
$item = new Item();
$item->uri = 'http://www.monde-diplomatique.fr' . $element->find('a', 0)->href;
$item->title = $element->find('h3', 0)->plaintext;
$item->content = $element->find('div.dates_auteurs', 0)->plaintext . ' <br> ' . $element->find('div.intro', 0)->plaintext;
$this->items[] = $item;
}
}
}
function bible_gateway_available_versions()
{
include_once 'simple_html_dom.php';
$html = file_get_html("http://www.biblegateway.com");
if (empty($html)) {
return false;
}
$select = $html->find('select[name=qs_version]', -1);
if (empty($select)) {
return false;
}
$versionnames = array();
$currentlang = '';
$options = $select->children;
foreach ($options as $option) {
if ($option->class == 'lang') {
$currentlang = $option->value;
continue;
}
// for some reason the english language section is deliniated by NIV not EN
if ($currentlang != 'NIV') {
continue;
}
$versionname = str_replace(' ', '', $option->innertext);
$versionnames[$option->value] = $versionname;
}
return $versionnames;
}
function updateJSON()
{
$list = array();
foreach (range('a', 'z') as $alphabet) {
array_push($list, $alphabet);
}
array_push($list, "numeric");
$space = '';
for ($x = 0; $x <= 3; $x++) {
$space = $space . " ";
}
$movieMapping = array();
foreach ($list as $alphabet) {
$html = file_get_html('http://www.songspk.link/' . $alphabet . '_list.html');
foreach ($html->find('div[class="catalog-album-holder"]') as $divElement) {
foreach ($divElement->find('a') as $hrefElement) {
$innerValue = trim($hrefElement->innertext);
$hrefValue = $hrefElement->href;
if (strlen($innerValue) > 1) {
$innerValue = preg_replace("/\\t/", "", $innerValue);
$movieMapping[trim($innerValue)] = trim($hrefValue);
}
}
}
//break;
}
$json = json_encode($movieMapping, true);
$file = fopen("data.json", "w");
file_put_contents("data.json", $json);
fclose($file);
//echo $json;
echo "data.json Created!!";
}
function accept_terms_get_cookies($terms_url, $button = 'Next', $postfields = array())
{
$dom = file_get_html($terms_url);
foreach ($dom->find('input[type=hidden]') as $data) {
$postfields = array_merge($postfields, array($data->name => $data->value));
}
foreach ($dom->find("input[value={$button}]") as $data) {
$postfields = array_merge($postfields, array($data->name => $data->value));
}
$curl = curl_init($terms_url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($curl, CURLOPT_POST, 1);
curl_setopt($curl, CURLOPT_POSTFIELDS, $postfields);
curl_setopt($curl, CURLOPT_HEADER, TRUE);
$terms_response = curl_exec($curl);
curl_close($curl);
// get cookie
// Please imporve it, I am not regex expert, this code changed ASP.NET_SessionId cookie
// to ASP_NET_SessionId and Path, HttpOnly are missing etc
// Example Source - Cookie: ASP.NET_SessionId=bz3jprrptbflxgzwes3mtse4; path=/; HttpOnly
// Stored in array - ASP_NET_SessionId => bz3jprrptbflxgzwes3mtse4
preg_match_all('/^Set-Cookie:\\s*([^;]*)/mi', $terms_response, $matches);
$cookies = array();
foreach ($matches[1] as $item) {
parse_str($item, $cookie);
$cookies = array_merge($cookies, $cookie);
}
return $cookies;
}
public function collectData(array $param)
{
$html = '';
if (isset($param['u'])) {
$this->request = $param['u'];
if (strlen(preg_replace("/[^0-9a-f]/", '', $this->request)) == 24) {
// is input the userid ?
$html = file_get_html('http://www.whyd.com/u/' . preg_replace("/[^0-9a-f]/", '', $this->request)) or $this->returnError('No results for this query.', 404);
} else {
// input may be the username
$html = file_get_html('http://www.whyd.com/search?q=' . urlencode($this->request)) or $this->returnError('No results for this query.', 404);
for ($j = 0; $j < 5; $j++) {
if (strtolower($html->find('div.user', $j)->find('a', 0)->plaintext) == strtolower($this->request)) {
$html = file_get_html('http://www.whyd.com' . $html->find('div.user', $j)->find('a', 0)->getAttribute('href')) or $this->returnError('No results for this query', 404);
break;
}
}
}
$this->name = $html->find('div#profileTop', 0)->find('h1', 0)->plaintext;
} else {
$this->returnError('You must specify username', 400);
}
for ($i = 0; $i < 10; $i++) {
$track = $html->find('div.post', $i);
$item = new \Item();
$item->name = $track->find('h2', 0)->plaintext;
$item->title = $track->find('h2', 0)->plaintext;
$item->content = $track->find('a.thumb', 0) . '<br/>' . $track->find('h2', 0)->plaintext;
$item->id = 'http://www.whyd.com' . $track->find('a.no-ajaxy', 0)->getAttribute('href');
$item->uri = 'http://www.whyd.com' . $track->find('a.no-ajaxy', 0)->getAttribute('href');
$this->items[] = $item;
}
}
function NiceMatinExtractContent($url)
{
$html2 = file_get_html($url);
$text = $html2->find('figure[itemprop=associatedMedia]', 0)->innertext;
$text .= $html2->find('div[id=content-article]', 0)->innertext;
return $text;
}
function strip_link($inputFile, $inputFileLocation)
{
$infile_final = $inputFileLocation . $inputFile;
// get DOM from URL or file
$html = file_get_html($infile_final);
$header_reg = $html->find('h2', 0)->plaintext;
$header_post = $html->find('h2', 1)->plaintext;
$table = $html->find('table', 0);
$boxScoreGames = $table->find('a');
$links = array();
if ($header_reg == "Regular Season") {
foreach ($boxScoreGames as $rec) {
if (preg_match("/games/", $rec)) {
//strip everything but the link out of the string (pissed i did it this way)
$rec = preg_replace('/<a href="/', '', $rec) . " ";
$rec = preg_replace('/">(W|L)(.*)/', '', $rec) . "\n";
$links[] = $rec;
}
}
$table = $html->find('table', 1);
$boxScoreGames = $table->find('a');
}
if ($header_post == "Postseason") {
foreach ($boxScoreGames as $rec) {
if (preg_match("/games/", $rec)) {
//strip everything but the link out of the string (pissed i did it this way)
$rec = preg_replace('/<a href="/', '', $rec) . " ";
$rec = preg_replace('/">(W|L)(.*)/', '', $rec) . "\n";
$links[] = $rec;
}
}
}
return $links;
}
function DeveloppezDotComExtractContent($url)
{
$articleHTMLContent = file_get_html($url);
$text = convert_smart_quotes($articleHTMLContent->find('div.content', 0)->innertext);
$text = utf8_encode($text);
return trim($text);
}
function crawl_site($u)
{
$html = file_get_html("http://www.hd-area.org/?s=search&q=" . $u);
$content = $html->find('div[id=content]');
$rss_head = "<rss version=\"2.0\"><channel>";
$rss_title = "<title>HD-Area Suche</title>";
$rss_desc = "<description>HD-Area-RSS-Feed-Generator</description>";
$rss_link = "<link>http://www.hd-area.org/?s=search&q=" . $u . "/</link>";
$rss_item = "";
$rss_tail = "</channel></rss>";
foreach ($html->find('div[id=content]') as $element) {
$urls = $element->find('a');
foreach ($urls as $url) {
$title = $url->title;
$link = $url->href;
if (!empty($title)) {
$rss_item = $rss_item . "<item>";
$rss_item = $rss_item . "<title>" . $title . "</title>";
$rss_item = $rss_item . "<link>" . $link . "</link>";
$rss_item = $rss_item . "</item>";
}
}
}
echo $rss_head;
echo $rss_title;
echo $rss_desc;
echo $rss_link;
echo $rss_item;
echo $rss_tail;
echo "\n";
}
public function collectData(array $param)
{
$page = 1;
$tags = '';
if (isset($param['p'])) {
$page = (int) preg_replace("/[^0-9]/", '', $param['p']);
}
if (isset($param['t'])) {
$tags = urlencode($param['t']);
}
$html = file_get_html("http://sakuga.yshi.org/post?page={$page}&tags={$tags}") or $this->returnError('Could not request Sakugabooru.', 404);
$input_json = explode('Post.register(', $html);
foreach ($input_json as $element) {
$data[] = preg_replace('/}\\)(.*)/', '}', $element);
}
unset($data[0]);
foreach ($data as $datai) {
$json = json_decode($datai, TRUE);
$item = new \Item();
$item->uri = 'http://sakuga.yshi.org/post/show/' . $json['id'];
$item->postid = $json['id'];
$item->timestamp = $json['created_at'];
$item->imageUri = $json['file_url'];
$item->thumbnailUri = $json['preview_url'];
$item->title = 'Sakugabooru | ' . $json['id'];
$item->content = '<a href="' . $item->imageUri . '"><img src="' . $item->thumbnailUri . '" /></a><br>Tags: ' . $json['tags'];
$this->items[] = $item;
}
}
function getBGVerseText($book, $chapter, $verse, $url)
{
$errorMessage = "<div class='error'>This verse doesn't exist.</div><p>Click <a href='" . $url . "' target='_blank'>here</a> to check. If you're still sure it's a verse you can <a href='javascript:showBGVerse(0);'>type it yourself.</a></p>";
$html = file_get_html($url) or die($errorMessage);
if ($verse == 1) {
$data = $html->find('span[class=chapternum]');
} else {
$data = $html->find('sup[class=versenum]');
}
if (count($data) <= 0) {
die($errorMessage);
}
$verse_text = $data[0]->parent();
$verse_text = str_replace("<br />", "\n", $verse_text);
$verse_text = str_replace(" ", " ", $verse_text);
$verse_text = ltrim(html_entity_decode(strip_tags($verse_text)));
//Get rid of Footnotes
$length = strpos($verse_text, "Footnotes");
if ($length != 0) {
$verse_text = substr($verse_text, 0, $length);
}
$verse_text = substr($verse_text, strpos($verse_text, $book));
$verse_text = substr($verse_text, strpos($verse_text, $chapter));
$verse_text = substr($verse_text, strpos($verse_text, $verse));
//Get rid of the brackets that link to footnotes
$verse_text = trim(preg_replace('/\\[[^)]*\\]/', '', $verse_text));
return $verse_text;
}
function getHTML($url, &$arr)
{
$m_url = $url;
$m_html = file_get_html($m_url);
$property = "";
$no_bed = get_no_bed($m_html);
$no_bath = get_no_bath($m_html);
$no_car = get_no_car($m_html);
$address = get_address($m_html);
$agency = get_agency($m_html);
$agency_localDir = get_agency_localDir($m_html);
$first_agent_name = get_first_agent_name($m_html);
$first_agent_contact = get_first_agent_contact($m_html);
$listing_type = "";
$price = get_price($m_html);
$inspect_time = get_inspect_time($m_html);
// $inspect_date = get_inspect_date ($m_html);
// $inspect_hour = get_inspect_hour ($m_html);
$auction_time = get_auction_time($m_html);
$auction_date = get_auction_date($m_html);
$auction_day = get_day($auction_date);
$auction_hour = get_auction_hour($m_html);
$auction_inspect_hour = get_auction_inspect_hour($m_html);
$auction_string = get_auction_string($auction_date, $auction_hour, $auction_inspect_hour);
$justlisted_string = get_justlisted_string($inspect_time);
$arr = array('url' => $m_url, 'no_bed' => $no_bed, 'no_bath' => $no_bath, 'no_car' => $no_car, 'address' => $address, 'agency' => $agency, 'agency_localDir' => $agency_localDir, 'first_agent_name' => $first_agent_name, 'first_agent_contact' => $first_agent_contact, 'listing_type' => $listing_type, 'price' => $price, 'inspect_time' => $inspect_time, 'auction_time' => $auction_time, 'auction_date' => $auction_date, 'auction_day' => $auction_day, 'auction_hour' => $auction_hour, 'auction_inspect_hour' => $auction_inspect_hour, 'auction_string' => $auction_string, 'justlisted_string' => $justlisted_string);
//print_r ($arr);
}
public function collectData(array $param)
{
$html = '';
if (isset($param['q'])) {
/* keyword search mode */
$this->request = str_replace(" ", "-", trim($param['q']));
$html = file_get_html('http://www.cpasbien.pw/recherche/' . urlencode($this->request) . '.html') or $this->returnError('No results for this query.', 404);
} else {
$this->returnError('You must specify a keyword (?q=...).', 400);
}
foreach ($html->find('#gauche', 0)->find('div') as $episode) {
if ($episode->getAttribute('class') == 'ligne0' || $episode->getAttribute('class') == 'ligne1') {
$htmlepisode = content_get_html($this->get_cached($episode->find('a', 0)->getAttribute('href')));
$item = new \Item();
$item->name = $episode->find('a', 0)->text();
$item->title = $episode->find('a', 0)->text();
$item->timestamp = $this->get_cached_time($episode->find('a', 0)->getAttribute('href'));
$textefiche = $htmlepisode->find('#textefiche', 0)->find('p', 1);
if (isset($textefiche)) {
$item->content = $textefiche->text();
} else {
$item->content = $htmlepisode->find('#textefiche', 0)->find('p', 0)->text();
}
$item->id = $episode->find('a', 0)->getAttribute('href');
$item->uri = $this->getURI() . $htmlepisode->find('#telecharger', 0)->getAttribute('href');
$item->thumbnailUri = $htmlepisode->find('#bigcover', 0)->find('img', 0)->getAttribute('src');
$this->items[] = $item;
}
}
}
public function dom_request($semi_asin)
{
require_once "simple_html_dom.php";
$checkURL = "http://astore.amazon.com/k-astore-20/detail/" . $semi_asin;
$checkImgURL = "http://astore.amazon.com/k-astore-20/images/" . $semi_asin;
$html = file_get_html($checkURL);
$htmlImage = file_get_html($checkImgURL);
// -------- Get Big Image
$chkBigImage = 1;
// if have multi big image;
$get_bigimage = $htmlImage->getElementById("content");
$chkData = explode("text/javascript", $get_bigimage);
$chkData = explode("\"", $chkData[1]);
$chkArr = 0;
for ($i = 2; $i < count($chkData); $i = $i + 2) {
$getBigImage[$chkArr] = $chkData[$i];
$chkArr++;
}
if ($getBigImage[0] == "") {
// -------- Get Big Image
$chkBigImage = 0;
// if have one big image;
$get_imageViewerLink = $htmlImage->getElementById("bigImage");
$chkData = explode("<br>", $get_imageViewerLink);
$chkData = explode("src", $chkData[0]);
$chkData = explode("\"", $chkData[1]);
$getBigImage[0] = $chkData[1];
}
$getBigImage = $getBigImage[0];
return $getBigImage;
}
function getFortuneInfo($keyword)
{
if ($keyword == "") {
return "请发送算命+人名，例如“算命张三”";
}
if (strlen($keyword) < 6 || strlen($keyword) > 12) {
return "人名长度为2到4个汉字";
}
try {
include 'simple_html_dom.php';
$url = "http://m.1518.com/xingming_view.php?word=" . urlencode(mb_convert_encoding($keyword, 'gb2312', 'utf-8')) . "&submit1=%C8%B7%B6%A8&FrontType=1";
$html_fotune = file_get_html($url);
if (!isset($html_fotune)) {
$html_fotune->clear();
return "程序检索出错！\n如果经常这样，请联系方倍工作室。";
}
$infomation = "";
foreach ($html_fotune->find('div[id="detail"] dl') as $item) {
$curText = $item->plaintext;
$curText = preg_replace('/\\s{2,}/i', ' ', $curText);
$curText = preg_replace('/\\t{2,}/i', ' ', $curText);
$curText = preg_replace('/：\\s/i', '：', $curText);
$infomation .= trim($curText) . "\n";
if (strlen($infomation) > 2000) {
break;
}
}
$html_fotune->clear();
$infomation = str_replace("\r\n", "\n", $infomation);
$infomation = str_replace("天格", "\n天格", $infomation);
$infomation = str_replace(" ", "", $infomation);
return trim($infomation);
} catch (Exception $e) {
}
}
function scraping_IMDB($url)
{
// create HTML DOM
$html = file_get_html($url);
// get title
$ret['Title'] = $html->find('title', 0)->innertext;
// get rating
$ret['Rating'] = $html->find('div[class="titlePageSprite star-box-giga-star"]', 0)->innertext;
// get overview
foreach ($html->find('div[class="info"]') as $div) {
// skip user comments
if ($div->find('h5', 0)->innertext == 'User Comments:') {
return $ret;
}
$key = '';
$val = '';
foreach ($div->find('*') as $node) {
if ($node->tag == 'h5') {
$key = $node->plaintext;
}
if ($node->tag == 'a' && $node->plaintext != 'more') {
$val .= trim(str_replace("\n", '', $node->plaintext));
}
if ($node->tag == 'text') {
$val .= trim(str_replace("\n", '', $node->plaintext));
}
}
$ret[$key] = $val;
}
// clean up memory
$html->clear();
unset($html);
return $ret;
}
function getStockAnalysis($stockcode)
{
if (!preg_match("/^\\d{6}\$/", $stockcode)) {
return "发送分析加上6位数字代码，例如“分析000063”";
}
$resultArray = array();
include_once 'simple_html_dom.php';
try {
$url = "http://m.ghzq.cn/weixin/index.aspx?code=" . $stockcode;
$html_analysis = file_get_html($url);
if (!isset($html_analysis)) {
$html_analysis->clear();
} else {
$stock = $html_analysis->find('div[class="row first"] div', 0)->plaintext;
$resultArray[] = array("Title" => trim($stock), "Description" => "", "PicUrl" => "", "Url" => "");
//基本面
$fundamentals = $html_analysis->find('div[class="font"]', 0);
$resultArray[] = array("Title" => str_replace("%", "%%", "【基本面】\n" . $fundamentals->plaintext), "Description" => "", "PicUrl" => "", "Url" => "");
//趋势面
$technical = $html_analysis->find('div[class="font"]', 1);
$resultArray[] = array("Title" => str_replace("%", "%%", "【技术面】\n" . $technical->plaintext), "Description" => "", "PicUrl" => "", "Url" => "");
//评级面
$technical = $html_analysis->find('div[class="font"]', 2);
$resultArray[] = array("Title" => str_replace("%", "%%", "【机构认同】\n" . $technical->plaintext), "Description" => "", "PicUrl" => "", "Url" => "");
$html_analysis->clear();
}
} catch (Exception $e) {
}
return $resultArray;
}
