PHP getHTML函数代码示例

function parseGG($name)
{
    $url = "http://www.gamersgate.com/DD-" . $name . "/";
    $html = getHTML($url);
    preg_match("/price_price(.*)>([0-9]+)/", $html, $match);
    $price = $match[2];
    return $price;
}

function parseGMG($name)
{
    $url = "http://www.greenmangaming.com/s/ru/en/pc/games/" . $name . "/";
    $html = getHTML($url);
    preg_match("/\"product_price_readable\": \"[0-9]+?(\\.[0-9]+)\"/", $html, $match);
    $price = $match[0];
    return explode(":", $price)[1];
}

function parseSteam($gameid)
{
    $url = "http://store.steampowered.com/app/" . $gameid . "/";
    $html = getHTML($url);
    preg_match("/itemprop=\"price\".*\"([0-9]+?,?[0-9]+)\"/", $html, $match);
    $price = $match[1];
    return array($price, $url, "Steam");
}

function fileupload_process($file)
{
    $attachment = handle_file($file);
    if (is_array($attachment)) {
        $html = getHTML($attachment);
        $response = array('success' => true, 'html' => $html, 'attach' => $attachment['id']);
        echo json_encode($response);
        exit;
    }
    $response = array('success' => false);
    echo json_encode($response);
    exit;
}

 public static function displayCFRow($row_key, $keyspace_name, $columnfamily_name, $row, $scf_key = null, $is_counter_column = false)
 {
     $vw_vars['scf_key'] = $scf_key;
     $vw_vars['row'] = $row;
     $vw_vars['keyspace_name'] = $keyspace_name;
     $vw_vars['columnfamily_name'] = $columnfamily_name;
     $vw_vars['row_key'] = $row_key;
     // If it's a column family of counter
     if ($is_counter_column) {
         return getHTML('columnfamily_row_counter.php', $vw_vars);
     } else {
         return getHTML('columnfamily_row.php', $vw_vars);
     }
 }

function parseGOG($name)
{
    $gameName = prepareNameGOG($name);
    $url = "http://www.gog.com/game/" . $gameName;
    $html = getHTML($url);
    preg_match("/buy-price__new(.*)>([0-9]+)/", $html, $match_disc);
    preg_match("/class=\"buy-price(.*)>([0-9]+)/", $html, $match);
    if (count($match_disc[0]) != 0) {
        $price = $match[2] < $match_disc[2] ? $match[2] : $match_disc[2];
    } else {
        $price = $match[2];
    }
    return array($price, $url, "GOG");
}

 /**
  * @brief	Charge les fichiers Javascript selon le nom de la page et selon l'état de l'application (production ou développement)
  * @param	String		$controlName	Nom de la page qui demande à inclure le Javascript
  * @return 	String		Code HTML nécessaire à l'inclusion du/des codes Javascript
  * @see 		JSLoader::$production
  */
 public static function loader($controlName)
 {
     $result = "";
     if (self::$production == false) {
         $file = array();
         if (file_exists(self::$base . "common.js")) {
             $file[] = self::$base . 'common.js';
         }
         if (file_exists(self::$base . $controlName . ".js")) {
             $file[] = self::$base . $controlName . ".js";
         }
         foreach ($file as $f) {
             $result .= self::getHTML($f);
         }
     } else {
         $result = getHTML(self::$base . self::$prodJS);
     }
     return $result;
 }

function getCast($tt, &$title = '')
{
    $html = getHTML($tt);
    if (preg_match('#<h3 itemprop="name">[\\s\\S]+?</h3>#i', $html, $match)) {
        $title = _clean($match[0]);
        // var_dump($title);
    }
    if (preg_match('#<table class="cast_list">([\\s\\S]+?)</table>#i', $html, $match)) {
        $table = $match[1];
        // preg_match_all('#itemprop="actor"[^<]+([\s\S]+?)</td>#', $table, $matches);
        // $actors = array_map(
        preg_match_all('#itemprop="actor"[\\s\\S]+?href="/name/(nm\\d+)[^>]+>([\\s\\S]+?)</a>#i', $table, $matches);
        $ids = array_map('_clean', $matches[1]);
        $actors = array_map('_clean', $matches[2]);
        // print_r($ids);
        $actors = array_combine($ids, $actors);
        // print_r($actors);
        preg_match_all('#<td class="character">([\\s\\S]+?)(?:\\(|/ \\.|</td)#i', $table, $matches);
        $characters = array_map('_clean', $matches[1]);
        $characters = array_combine($ids, $characters);
        // print_r($characters);
        return (object) compact('actors', 'characters');
    }
}

        <?php 
$html = getHTML('http://themoneyballunion.com/game/StatsLab//widget.php?stat=pwar&topX=10', 10);
$html = utf8_encode($html);
echo $html;
?>
      </div>
      <div id='panel3' class="panel">
        <h3>HR leaders</h3>
        <?php 
$html = getHTML('http://themoneyballunion.com/game/StatsLab//widget.php?stat=hr&topX=10', 10);
$html = utf8_encode($html);
echo $html;
?>
        <h3>Hit leaders</h3>
        <?php 
$html = getHTML('http://themoneyballunion.com/game/StatsLab//widget.php?stat=h&topX=10', 10);
$html = utf8_encode($html);
echo $html;
?>
      
      </div>
      
      
    </aside>
    <div class="news">
      <h2>Breaking News</h2>
      <div class="articles">
      <?php 
include 'simple_html_dom.php';
//set up curl
$ch = curl_init("http://www.themoneyballunion.com/game/lgreports//leagues/league_100_home.html");

require 'helper/ClusterHelper.php';
require 'helper/ColumnFamilyHelper.php';
require 'helper/MX4J.php';
require 'conf.inc.php';
define('MINIMUM_THRIFT_API_VERSION_FOR_COUNTERS', '19.10.0');
$cluster_helper = new ClusterHelper($CASSANDRA_CLUSTERS);
session_start();
// Make sure the cluster index in the session still exists in the config array
if ($cluster_helper->getClusterIndex() > $cluster_helper->getClustersCount() - 1) {
    $_SESSION['cluster_index'] = 0;
}
try {
    $random_server = $cluster_helper->getRandomNodeForCurrentCluster();
    $sys_manager = new SystemManager($random_server, $cluster_helper->getCredentialsForCurrentCluster(), 1500, 1500);
} catch (TException $e) {
    die(getHTML('header.php') . getHTML('server_error.php', array('error_message' => displayErrorMessage('cassandra_server_error', array('error_message' => $e->getMessage())))) . getHTML('footer.php'));
}
/*
	Get the specified view and replace the php variables
*/
function getHTML($filename, $php_params = array())
{
    if (!file_exists('views/' . $filename)) {
        die('The view ' . $filename . ' doesn\'t exist');
    }
    // If we got some params to be treated in php
    extract($php_params);
    ob_start();
    include 'views/' . $filename;
    $content = ob_get_contents();
    ob_end_clean();

    return $res;
}
function scrape_between($data, $start, $end)
{
    $data = stristr($data, $start);
    // Stripping all data from before $start
    $data = substr($data, strlen($start));
    // Stripping $start
    $stop = stripos($data, $end);
    // Getting the position of the $end of the data to scrape
    $data = substr($data, 0, $stop);
    // Stripping all data from after and including the $end of the data to scrape
    return $data;
    // Returning the scraped data from the function
}
$result = getHTML("http://www.snapdeal.com/product/hp-stream-8-windows-tablet/672158959721?", 0);
function getTitle($result)
{
    preg_match('/(.*)<\\/h1>/i', $result, $title);
    $ret = scrape_between($title[0], '<h1 itemprop="name" class=\'font20\'>', "</h1>");
    return $ret;
}
function getImg($result, $title)
{
    preg_match_all('/<img title=(.*) itemprop="image" (.*)>/i', $result, $img);
    $img_url = scrape_between($img[0][0], 'src="', '"');
    return $img_url;
}
function getMRP($result)
{
    preg_match_all('/original-price-id">(.*)</i', $result, $MRP);

/**
 * entry point
 */
function init()
{
    try {
        //connect to database
        $db = new PDO("mysql:host=" . DB_HOST . ";dbname=" . DB_NAME, DB_USER, DB_PASSWORD);
        $preparedParams = array();
        $statuses = $_POST["statuses"];
        $html = "";
        $pagingStatus = null;
        $filter = "";
        $sort = "";
        $query = "";
        if (isset($statuses)) {
            //statuses => array
            $statuses = json_decode(urldecode($statuses));
            foreach ($statuses as $key => $value) {
                switch ($value->action) {
                    case "paging":
                        $pagingStatus = $value;
                        break;
                    case "filter":
                        $filter .= getFilterQuery($value, $filter, $preparedParams);
                        break;
                    case "sort":
                        $sort = getSortQuery($value, $preparedParams);
                        break;
                }
            }
        }
        //count database items for pagination
        $query = "SELECT count(*) FROM Item " . $filter . " " . $sort;
        if (count($preparedParams) > 0) {
            $stmt = $db->prepare($query);
            //error_log(print_r($preparedParams, true));
            $stmt->execute($preparedParams);
            $count = $stmt->fetchColumn();
        } else {
            $count = $db->query($query)->fetchColumn();
        }
        //init pagination query
        if ($pagingStatus) {
            $paging = getPagingQuery($pagingStatus, $count, $preparedParams);
        }
        //init query with sort and filter
        $query = "SELECT title, description, image, likes, keyword1, keyword2 FROM Item " . $filter . " " . $sort . " " . $paging;
        if (count($preparedParams) > 0) {
            $stmt = $db->prepare($query);
            $stmt->execute($preparedParams);
            $items = $stmt->fetchAll();
        } else {
            $items = $db->query($query);
        }
        foreach ($items as $item) {
            $html .= getHTML($item);
        }
        //print html
        echo getHTMLWrapper($html, $count);
        //close the database connection
        $db = NULL;
    } catch (PDOException $ex) {
        print 'Exception: ' . $ex->getMessage();
    }
}

<?php

/*
Stap3:
Het dowlaoden van alle posts en op te slaan
*/
//Open de csv waar de links in staan
if ($cvs = fopen("postList.csv", "r")) {
    //Voor elke relge gevodne in csv haal data op
    while ($data = fgetcsv($cvs, 1000, ",")) {
        //Haal de html op
        getHTML($data[1]);
        //Als er geen data gevodnen is geef een error
        if (!$html) {
            echo "There is no data found on this page\n";
        } else {
            //Open de locatie waar je het bestand wil opslaan en maar het bestand aan met als bestan naam de laaste gedeelte van de link
            $file = fopen('/var/www/test/bayw/allPost/' . str_replace($data[1], "", "site naam"), 'w');
            //Zet de html in het bestand
            fputs($file, $html);
            //sluit bestand
            fclose($file);
        }
        //Vertraag het script voor 2 sec om overload te voor komen
        sleep(2);
    }
    //sluit de csv
    fclose($cvs);
}

function create($entity)
{
    $html = getHTML($entity['source_url']);
    if (!$html) {
        return error_log('Could not import ' + $entity['source_url']);
    }
    // Clean title
    $entity['title'] = trim(html_entity_decode($entity['title'], ENT_COMPAT, 'UTF-8'));
    // Generate key
    $entity['key'] = 'ch/' . makeSlug($entity['title']);
    // Extract email
    $emailLink = $html->find('table.tabelleESK a[href^=mailto:]', 0);
    if ($emailLink) {
        $entity['email'] = str_replace('mailto:', '', trim($emailLink->href));
    }
    // Extract URL
    foreach ($html->find('table.tabelleESK tr') as $row) {
        $name = trim($row->children(0)->innertext);
        if (stripos('homepage', $name) !== false) {
            foreach ($row->children() as $i => $cell) {
                $link = $cell->find('a[href]', 0);
                if ($link) {
                    $entity['url'] = $link->href;
                    break;
                }
                // Ugly case: URL but no link
                if ($i && !$cell->children()) {
                    $entity['url'] = $cell->innertext;
                    break;
                }
            }
        }
    }
    // Find entity abbreviation
    $orgTitle = $html->find('h2.titleOrg', 0);
    if ($orgTitle) {
        $orgTitleParts = explode('-', $orgTitle->innertext);
        if (count($orgTitleParts) > 1) {
            $entity['abbr'] = trim(array_pop($orgTitleParts));
            $entity['abbr'] = html_entity_decode($entity['abbr'], ENT_COMPAT, 'UTF-8');
        }
    } else {
        error_log('No title on ' + $entity['source_url']);
    }
    // Find entity address
    $infoBlock = $html->find('div.infoblock', 0)->innertext;
    if (preg_match('/<\\/h2>(.+?)<div class="titleContent">/s', $infoBlock, $matches)) {
        $infoBlock = str_replace(array('<br>', '(neues Fenster)'), array(', ', ''), $matches[1]);
        $infoBlock = preg_replace('/\\s\\s+/', ' ', $infoBlock);
        $infoBlock = trim(html_entity_decode(strip_tags($infoBlock), ENT_COMPAT, 'UTF-8'));
        $entity['address'] = $infoBlock;
    }
    save($entity);
    getChildren($entity, $html);
}

function init()
{
    if (empty($_POST['letters']) || empty($_POST['wordlen'])) {
        $html = getHTML(1);
    } else {
        $letters = trim($_POST['letters']);
        //Remove spaces in between
        $letters = strtolower(str_replace(' ', '', $letters));
        $wordlen = intval($_POST['wordlen']);
        if ($wordlen <= strlen($letters)) {
            $success = getMatches($letters, $wordlen);
            $html = getHTML(0, $success);
        } else {
            $success = array();
            $html = getHTML(0, $success);
        }
    }
    echo $html;
}