I created a web scraper using PHP for a similar purpose. This is actually quite simple. You can clear the data and write it to the database. Here is a brief excerpt:
function get_web_page( $url )
{
$options = array(
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HEADER => false,
CURLOPT_FOLLOWLOCATION => true,
CURLOPT_ENCODING => "",
CURLOPT_USERAGENT => "spider",
CURLOPT_AUTOREFERER => true,
CURLOPT_CONNECTTIMEOUT => 120,
CURLOPT_TIMEOUT => 120,
CURLOPT_MAXREDIRS => 10,
);
$ch = curl_init( $url );
curl_setopt_array( $ch, $options );
$content = curl_exec( $ch );
$err = curl_errno( $ch );
$errmsg = curl_error( $ch );
$header = curl_getinfo( $ch );
curl_close( $ch );
return $content;
}
$content = get_web_page($baseUrl);
$dom = new DOMDocument();
@$dom->loadHTML($content);
$xpath = new DOMXPath($dom);
$hrefs = $xpath->evaluate("/html/body//a");
for ($i = 0; $i < $hrefs->length; $i++) {
$href = $hrefs->item($i);
$url = $href->getAttribute('href');
}
source
share