preg_match pattern to scan these prices

Question

i'm trying to scan prices from THIS page, i want to use this preg_match to extract prices from this div: <span class="price"><b>519,00&nbsp;€</b></span>. What is the correct preg_match?

This is my extractor script:

<?php
echo  "funziona!";

    if(!$fp = fopen("https://www.google.it/webhp?sourceid=chrome-instant&ion=1&espv=2&es_th=1&ie=UTF-8#tbs=vw:l,mr:1&tbm=shop&q=samsung+galaxy+note+4&tbas=0" ,"r" )) {
        return false;
    } //our fopen is right, so let's go
    $content = "";

    while(!feof($fp)) { //while it is not the last line, we will add the current line to our $content
        $content .= fgets($fp, 1024);
    }
    fclose($fp); //we are done here, don't need the main source anymore
?>

<?php
//our fopen, fgets here

//our magic regex here
preg_match_all('/<span class=\"price">(.*?)<\/span>/s',$content, $prices); //THIS IS PREG_MATCH 
    echo $prices[0][0]."<br />";
?>

I have never used preg_match before, i'm trying to adapt this script.
Thank you.

Answer 1

You should use a parser, not a regex to accomplish this task. Here's a sample of how this could be done using the simple html dom parser.

include_once 'simple_html_dom.php';
$html = file_get_html('http://www.example.com');
foreach($html->find('span') as $element) {
    if(strpos($element->class, 'price')){
        echo $element->innertext . "\n";
    }
}

This also is a pretty loose check you may get back more results than you want. It only is checking that the span's class contains the word price.

http://simplehtmldom.sourceforge.net/manual.htm#section_quickstart

Other approaches, How do you parse and process HTML/XML in PHP?

Answer 2

Have a look at this:

<?php
function getUrl($Url,$Options = array(),&$optOut = array())
{

    $CURL_DEFAULT_SETTINGS  = array
    (
        CURLOPT_FOLLOWLOCATION => true,
        CURLOPT_AUTOREFERER => true,
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_CONNECTTIMEOUT => 10,
        CURLOPT_MAXREDIRS => 10,
        CURLOPT_TIMEOUT => 10,
        CURLOPT_USERAGENT => 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8'
    );

    if (!($ch = curl_init($Url)))
        throw new Exception("Couldn't initialize cURL library",100);

    if (is_array($CURL_DEFAULT_SETTINGS) && count($CURL_DEFAULT_SETTINGS) > 0)
        curl_setopt_array($ch,$CURL_DEFAULT_SETTINGS);

    if (is_array($Options) && count($Options) > 0)
    {
        foreach ($Options as $k => $v)
        {
            curl_setopt($ch,$k,$v);
        }
    }

    $Data = curl_exec($ch);
    $Error = curl_error($ch);

    $optOut['CURLINFO_HEADER_OUT'] = curl_getinfo($ch, CURLINFO_HEADER_OUT );

    curl_close($ch);

    if (!$Data)
    {
        if ($Error)
            throw new Exception($Error);

        return false;
    }

    return $Data;
}

function getPriceFor($query) {
    $data = getUrl('https://www.google.it/search?tbs=vw:l,mr:1&tbm=shop&q='.rawurlencode($query).'&tbas=0&bav=on.2,or.&cad=b&fp=6a24b60e09fe0b18&biw=1196&bih=703&dpr=2&ion=1&espv=2&tch=1&ech=1&psi=byWgVee9A4TNeIXRgLAK.1436558704099.3');
    $data = '['.preg_replace('/\/\*""\*\//msi',',',preg_replace('/\/\*""\*\/[\s]*$/msi','',$data)).']';
    $data = json_decode($data,true);
    preg_match_all('/<div[\s]+class="_OA"><div><b>([^<]+)[\s]*<\/b><\/div><div>([^<]+)<\/div><\/div>/msi',$data[3]['d'],$res);

    $re = array();

    foreach ($res[1] as $k=>$r)
        $re[] = array('price'=>$r,'from'=>$res[2][$k]);

    return $re;
}

print_r(getPriceFor('samsung galaxy note 4'));

That must display something like this:

Array
(
    [0] => Array
        (
            [price] => 515,00 €
            [from] => phoneshopping.it
        )

    [1] => Array
        (
            [price] => 519,00 €
            [from] => Smartyrama
        )

    [2] => Array
        (
            [price] => 519,00 €
            [from] => Smartyrama
        )

    [3] => Array
        (
            [price] => 519,00 €
            [from] => Smartyrama
        )

    [4] => Array
        (
            [price] => 690,45 €
            [from] => Amazon.it - Seller
        )

    [5] => Array
        (
            [price] => 673,99 €
            [from] => da 2 negozi
        )

    [6] => Array
        (
            [price] => 345,00 €
            [from] => da 2 negozi
        )

    [7] => Array
        (
            [price] => 342,00 €
            [from] => Amazon.it - Seller
        )

    [8] => Array
        (
            [price] => 699,99 €
            [from] => ePRICE.it
        )

    [9] => Array
        (
            [price] => 730,00 €
            [from] => in oltre 5 negozi
        )

    [10] => Array
        (
            [price] => 20,00 €
            [from] => Amazon.it - Seller
        )

    [11] => Array
        (
            [price] => 208,99 €
            [from] => eGlobal Central Italia
        )

    [12] => Array
        (
            [price] => 711,00 €
            [from] => in oltre 5 negozi
        )

    [13] => Array
        (
            [price] => 322,99 €
            [from] => eGlobal Central Italia
        )

    [14] => Array
        (
            [price] => 40,09 €
            [from] => da 4 negozi
        )

    [15] => Array
        (
            [price] => 15,99 €
            [from] => acadattatore.com
        )

    [16] => Array
        (
            [price] => 339,99 €
            [from] => ePRICE.it
        )

    [17] => Array
        (
            [price] => 412,90 €
            [from] => da 3 negozi
        )

    [18] => Array
        (
            [price] => 343,33 €
            [from] => Amazon.it - Seller
        )

    [19] => Array
        (
            [price] => 629,00 €
            [from] => BestPriceStore
        )

)