一、思路

最近做了一個網站用到了從網址爬取天貓和淘寶的商品資訊，首先看了下手機端的網頁發現用的react，不太瞭解沒法搞，所以就考慮從PC入口爬取資料，但是當爬取URL獲取資料時並沒有獲取價格，庫存等的資訊，仔細研究了下發現是非同步請求了另一個介面，但是介面要使用refer才能獲取資料，於是就通過以下方式寫了一個簡單的爬蟲，用於爬取商品預覽圖和商品的第一個分類的價格、庫存等。

二、實現

程式碼如下：

function crawlUrl($url){
import('PhpQuery.Curl');
    $curl=new \Curl();
    $result = $curl
 
->read($url);
    $content = mb_convert_encoding( $result['content'], 'UTF-8', 'UTF-8,GBK,GB2312,BIG5' );
    $myres=array();
    if(strrpos($url,'taobao.com')!=false) {
        //匹配是否下架
        if(strpos($content,'此寶貝已下架')!==false){
            return false;
        }
        preg_match("|itemId           : '(.*)'|isU"
 
, $content, $match);
        $item_id=$match[1];
        preg_match("|sellerId         : '(.*)'|isU", $content, $match);
        $sellet_id=$match[1];
        preg_match("|<title>(.*)</title>|isU",$content,$match);
        $title=$match[1];
        //價格庫存資訊
        $ch = curl_init();
        curl_setopt ($ch
 
, CURLOPT_URL, 'https://detailskip.taobao.com/service/getData/1/p1/item/detail/sib.htm?itemId='.$item_id.'&sellerId='.$sellet_id.'&modules=dynStock,qrcode,viewer,price,duty,xmpPromotion,delivery,upp,activity,fqg,zjys,amountRestriction,couponActivity,soldQuantity,originalPrice,tradeContract&callback=onSibRequestSuccess');
        $opt[CURLOPT_HEADER]=false;
        $opt[CURLOPT_CONNECTTIMEOUT]=15;
        $opt[CURLOPT_TIMEOUT]=300;
        $opt[CURLOPT_AUTOREFERER]=true;
        $opt[CURLOPT_USERAGENT]='Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11';
        curl_setopt_array($ch,$opt);
        curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt ($ch,CURLOPT_REFERER,$url);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
        $out_put=curl_exec ($ch);
        curl_close ($ch);
        $res=str_replace('onSibRequestSuccess(',"",$out_put);
        $res=rtrim($res,');1');
        $result=json_decode($res,true);
        //查詢出圖片資訊
        preg_match('|<ul id="J_UlThumb" class="tb-thumb tb-clearfix">(.*)</ul>|isU', $content, $match);
        preg_match_all('/<img data-src="(.*?)" \//', $match[1], $images);

        $myres['title']=str_replace('-淘寶網','',$title);

        $myres['price']=current($result['data']['originalPrice']);

        $myres['act_price']=current($result['data']['promotion']['promoData']);

        $myres['stock']=$result['data']['dynStock']['stock'];

        $myres['banners']=$images[1];
    }else{
        //匹配是否下架
        if(strpos($content,'此寶貝已下架')!==false){
            return false;
        }
        $start=strpos($url,'&id=');
        $item_id=substr($url,$start+4,12);
        if(!is_numeric($item_id)){
            $start=strpos($url,'?id=');
            $end=strpos($url,'&spm');
            $item_id=substr($url,$start+4,$end-$start-4);
        }
        preg_match("|<title>(.*)</title>|isU",$content,$match);
        $title=$match[1];
        $myurl='https://mdskip.taobao.com/core/initItemDetail.htm?cachedTimestamp=1500562177777&queryMemberRight=true&cartEnable=true&offlineShop=false&addressLevel=2&itemId='.$item_id.'&tryBeforeBuy=false&isAreaSell=false&tmallBuySupport=true&isPurchaseMallPage=false&household=false&isForbidBuyItem=false&service3C=false&isRegionLevel=false&showShopProm=false&isSecKill=false&sellerPreview=false&isUseInventoryCenter=false&isApparel=true&callback=setMdskip&timestamp=1500562172109&isg=AiUlDZFWmP/sMgVurQSILU3Ytet/Zdis&isg2=Ajk51JIhRFqKzxmiNPP6dkYxSKXT7iySkzSTeVtu9WDf4ll0o5Y9yKdyEtHu';
        //價格庫存資訊
        $ch = curl_init();
        curl_setopt ($ch, CURLOPT_URL, $myurl);
        $opt[CURLOPT_HEADER]=false;
        $opt[CURLOPT_CONNECTTIMEOUT]=15;
        $opt[CURLOPT_TIMEOUT]=300;
        $opt[CURLOPT_AUTOREFERER]=true;
        $opt[CURLOPT_USERAGENT]='Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11';
        curl_setopt_array($ch,$opt);
        curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt ($ch,CURLOPT_REFERER,$url);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
        $out_put=curl_exec ($ch);
        curl_close ($ch);
        $res = mb_convert_encoding( $out_put, 'UTF-8', 'UTF-8,GBK,GB2312,BIG5' );
        $res=str_replace('setMdskip',"",$res);
        $res=str_replace('(',"",$res);
        $res=str_replace(')',"",$res);
        $result=json_decode($res,true);
        $nowk="";
        $nowstore="";
        foreach($result['defaultModel']['inventoryDO']['skuQuantity'] as $k=>$val){
            $nowk=$k;
            $nowstore=$val;
            break;
        }

        $myres['title']=str_replace('-tmall.com天貓','',$title);

        $myres['price']=$result['defaultModel']['itemPriceResultDO']['priceInfo'][$nowk]['price'];

        $myres['act_price']=isset($result['defaultModel']['itemPriceResultDO']['priceInfo'][$nowk]['suggestivePromotionList'])?$result['defaultModel']['itemPriceResultDO']['priceInfo'][$nowk]['suggestivePromotionList']:$result['defaultModel']['itemPriceResultDO']['priceInfo'][$nowk];

        $myres['stock']=$result['defaultModel']['inventoryDO']['totalQuantity']?$result['defaultModel']['inventoryDO']['totalQuantity']:$nowstore['quantity'];
        //查詢出圖片資訊
        preg_match('|<ul id="J_UlThumb" class="tb-thumb tm-clear">(.*)</ul>|isU',$content, $match);
        preg_match_all('/<img src="(.*?)" \//',$match[1],$images);
        $myres['banners']=$images[1];
    }
    return $myres;
    }

上述程式碼用到phpquery的庫，但是其實沒啥用，直接用Curl就行，具體爬取的資料可以穿參檢視結果，方法不區分淘寶和天貓連結，但是前提是必須是PC端連結，另外正則寫的不規範，所以可以自己重寫正則來匹配資料。

以上