Untitled

<?php
    $html = file_get_contents('http://bbcsite.com/news/123');
?>

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html>
    <head>
        <title>!</title>
        <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
    </head>
<body dir="rtl">
<?php
include_once 'Readability.php';


// get latest Medialens alert
// (change this URL to whatever you'd like to test)
$url = 'http://';
$html = file_get_contents($url);

// Note: PHP Readability expects UTF-8 encoded content.
// If your content is not UTF-8 encoded, convert it
// first before passing it to PHP Readability.
// Both iconv() and mb_convert_encoding() can do this.

// If we've got Tidy, let's clean up input.
// This step is highly recommended - PHP's default HTML parser
// often doesn't do a great job and results in strange output.
if (function_exists('tidy_parse_string')) {
    $tidy = tidy_parse_string($html, array(), 'UTF8');
    $tidy->cleanRepair();
    $html = $tidy->value;
}

// give it to Readability
$readability = new Readability($html, $url);
// print debug output?
// useful to compare against Arc90's original JS version -
// simply click the bookmarklet with FireBug's console window open
$readability->debug = false;
// convert links to footnotes?
$readability->convertLinksToFootnotes = true;
// process it
$result = $readability->init();
// does it look like we found what we wanted?
if ($result) {
    echo "== Title =====================================n";
    echo $readability->getTitle()->textContent, "nn";
    echo "== Body ======================================n";
    $content = $readability->getContent()->innerHTML;
    // if we've got Tidy, let's clean it up for output
    if (function_exists('tidy_parse_string')) {
        $tidy = tidy_parse_string($content, array('indent'=>true, 'show-body-only' => true), 'UTF8');
        $tidy->cleanRepair();
        $content = $tidy->value;
    }
    echo $content;
} else {
    echo 'Looks like we couldn't find the content. :(';
}
?>
</body>
</html>

function getData($url) {
    $url = str_replace('&', '&', urldecode(trim($url)) );
    $timeout = 5;
    $cookie = tempnam('/tmp', 'CURLCOOKIE');
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1');
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($ch, CURLOPT_ENCODING, '');
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($ch, CURLOPT_AUTOREFERER, true);
    curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
    curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);
    curl_setopt($ch, CURLOPT_MAXREDIRS, 10);
    $content = curl_exec($ch);
    curl_close ($ch);
    return $content;
}

$url = 'http://';
//$html = file_get_contents($url);
$html = getData($url);

if (function_exists('tidy_parse_string')) {
    $tidy = tidy_parse_string($html, array(), 'UTF8');
    $tidy->cleanRepair();
    $html = $tidy->value;
}

$readability = new Readability($html, $url);

//...

$html = file_get_contents('http://coder-dz.com');
preg_match_all('/<li>(.*?)</li>/s', $html, $matches);
foreach($matches[1] as $mytitle)
{
echo $mytitle."<br/>";
}

use GooseClient as GooseClient;

$goose = new GooseClient();
$article = $goose->extractContent('http://url.to/article');

$title = $article->getTitle();
$metaDescription = $article->getMetaDescription();
$metaKeywords = $article->getMetaKeywords();
$canonicalLink = $article->getCanonicalLink();
$domain = $article->getDomain();
$tags = $article->getTags();
$links = $article->getLinks();
$movies = $article->getMovies();
$articleText = $article->getCleanedArticleText();
$entities = $article->getPopularWords();
$image = $article->getTopImage();
$allImages = $article->getAllImages();