php - Avoid the header of box xpath and curl -
iam writting code web data xpath , curl.
these code ul li contain , worked.
but dont want header..
i write following code avoid header can't
if($row->item(0)->tagname != '<ul class="graybg"><li>مدل خودرو</li> <li>مشخصات</li><li>قیمت نمایندگی</li><li>قیمت بازار آزاد</li></ul>') full code.
$ch = curl_init ("http://www.pedal.ir/price/"); curl_setopt($ch, curlopt_returntransfer, true); curl_setopt($ch,curlopt_useragent,'mozilla/5.0 (windows; u; windows nt 5.1; en-us; rv:1.8.1.13) gecko/20080311 firefox/2.0.0.13'); curl_setopt($ch, curlopt_header, 0); curl_setopt($ch, curlopt_encoding, 'utf-8'); $page = curl_exec($ch); $dom = new domdocument('1.0', 'utf-8'); libxml_use_internal_errors(true); $dom->loadhtml($page); libxml_clear_errors(); $xpath = new domxpath($dom); $data = array(); $table_rows = $xpath- >query('/html/body/div/div[1]/div/div/div/div/div/div/div[2]/ul '); // target row (the browser rendered <tbody>, doesnt have one) if($table_rows->length <= 0) { // exit if not found echo 'no table rows found'; exit; } foreach($table_rows $tr) { // foreach row $row = $tr->childnodes; if($row->item(0)->tagname != '<ul class="graybg"><li>مدل خودرو</li> <li>مشخصات</li><li>قیمت نمایندگی</li><li>قیمت بازار آزاد</li></ul>') { // avoid headers $data[] = array( 'moled' =>trim($row->item(0)->nodevalue), 'detail' => trim($row->item(2)->nodevalue), 'pricenama' => trim($row->item(4)->nodevalue), 'pricebaza' => trim($row->item(6)->nodevalue), ); } } echo '<pre>'; print_r($data);;
as alternative, since header has distinct class identifies it, include inside checking:
foreach($table_rows $tr) { // foreach row $row = $tr->childnodes; if($row->item(0)->parentnode->getattribute('class') !== 'graybg') { // avoid headers $data[] = array( 'moled' =>trim($row->item(0)->nodevalue), 'detail' => trim($row->item(2)->nodevalue), 'pricenama' => trim($row->item(4)->nodevalue), 'pricebaza' => trim($row->item(6)->nodevalue), ); } }