I'm would like to extract all the team name and link from this page:
https://www.transfermarkt.fr/ligue-1/startseite/wettbewerb/FR1
I'm using DOMXpath to match element but with the following code it do not return me anything.
function get_data($url) {
$ch = curl_init();
$timeout = 5;
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST,false);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER,false);
curl_setopt($ch, CURLOPT_MAXREDIRS, 10);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
$data = curl_exec($ch);
curl_close($ch);
return $data;
}
$url = 'https://www.transfermarkt.fr/ligue-1/startseite/wettbewerb/FR1';
$html = get_data($url);
$dom = new DOMDocument();
$dom->loadHTML($html);
$xpath = new DOMXpath($dom);
foreach($xpath->query('//*[contains(concat( " ", @class, " " ), concat( " ", "hide-for-pad", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "tooltipstered", " " ))]') as $v) {
echo $v->getAttribute("href") . PHP_EOL;
}
Do you know why please ?
Thanks a any help.
Sometimes the HTML is altered by Javascript once the page is loaded. I've had a look at the page and I think you should be able to get the details from the following (please check the correct URL is displayed)...
$teams = $xpath->query('//td[@class="zentriert no-border-rechts"]/a[contains(concat( " ", @class, " " ), concat( " ", "vereinprofil_tooltip", " " ))]');
foreach($teams as $v) {
echo $v->getAttribute("href") . " - ";
echo $v->firstChild->getAttribute("alt").PHP_EOL;
}
This may give duplicates, so a possibility is to create a list of the teams and URL's like this...
$teams = [];
foreach($teams as $v) {
$teams[$v->firstChild->getAttribute("alt")] = $v->getAttribute("href");
}
Which will give you a list of team names (as the key) and the URL as the value.