atticus Posted November 11, 2009 Share Posted November 11, 2009 Hi all. I am trying to parse HTML and grab a title from the text. Right now, I am getting just a blank page (error reporting is turned on) Here is the problem code: $regex = '~<span class="main-title">(?)</span>~'; preg_match_all($regex,$html,$match); foreach ($match[1] as $digit) { echo $digit; } Here is the complete function: function site($URL) { $target_url = "$URL"; $userAgent = 'User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080201 Firefox/2.0.0.12\r\n'; // make the cURL request to $target_url $ch = curl_init(); curl_setopt($ch, CURLOPT_USERAGENT, $userAgent); curl_setopt($ch, CURLOPT_URL,$target_url); curl_setopt($ch, CURLOPT_FAILONERROR, true); curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); curl_setopt($ch, CURLOPT_AUTOREFERER, true); curl_setopt($ch, CURLOPT_RETURNTRANSFER,true); curl_setopt($ch, CURLOPT_TIMEOUT, 10); $html= curl_exec($ch); if (!$html) { echo " cURL error number:" .curl_errno($ch); echo " cURL error:" . curl_error($ch); exit; } // parse the html into a DOMDocument // $dom = new DOMDocument(); // @$dom->loadHTML($html); //echo $html; $regex = '~<span class="main-title">(?)</span>~'; preg_match_all($regex,$html,$match); foreach ($match[1] as $digit) { echo $digit; } } Quote Link to comment Share on other sites More sharing options...
atticus Posted November 11, 2009 Author Share Posted November 11, 2009 Hi all. I am trying to parse HTML and grab a title from the text. Right now, I am getting just a blank page (error reporting is turned on) Here is the problem code: $regex = '~<span class="main-title">(?)</span>~'; preg_match_all($regex,$html,$match); foreach ($match[1] as $digit) { echo $digit; } Should be: <span class="main-title">(.+)</span> Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.