php如何爬取天猫和淘宝商品数据-php教程-PHP中文网

php如何爬取天猫和淘宝商品数据

小云云

发布： 2018-02-24 09:17:21

原创

2654人浏览过

一、思路

最近做了一个网站用到了从网址爬取天猫和淘宝的商品信息，首先看了下手机端的网页发现用的react，不太了解没法搞，所以就考虑从PC入口爬取数据，但是当爬取URL获取数据时并没有获取价格，库存等的信息，仔细研究了下发现是异步请求了另一个接口，但是接口要使用refer才能获取数据，于是就通过以下方式写了一个简单的爬虫，用于爬取商品预览图和商品的第一个分类的价格、库存等。

二、实现

代码如下：

function crawlUrl($url){
import(&#39;PhpQuery.Curl&#39;);
  $curl=new \Curl();
  $result = $curl->read($url);
  $content = mb_convert_encoding( $result[&#39;content&#39;], &#39;UTF-8&#39;, &#39;UTF-8,GBK,GB2312,BIG5&#39; );
  $myres=array();
  if(strrpos($url,&#39;taobao.com&#39;)!=false) {
    //匹配是否下架
    if(strpos($content,&#39;此宝贝已下架&#39;)!==false){
      return false;
    }
    preg_match("|itemId      : &#39;(.*)&#39;|isU", $content, $match);
    $item_id=$match[1];
    preg_match("|sellerId     : &#39;(.*)&#39;|isU", $content, $match);
    $sellet_id=$match[1];
    preg_match("|<title>(.*)</title>|isU",$content,$match);
    $title=$match[1];
    //价格库存信息
    $ch = curl_init();
    curl_setopt ($ch, CURLOPT_URL, &#39;https://detailskip.taobao.com/service/getData/1/p1/item/detail/sib.htm?itemId=&#39;.$item_id.&#39;&sellerId=&#39;.$sellet_id.&#39;&modules=dynStock,qrcode,viewer,price,duty,xmpPromotion,delivery,upp,activity,fqg,zjys,amountRestriction,couponActivity,soldQuantity,originalPrice,tradeContract&callback=onSibRequestSuccess&#39;);
    $opt[CURLOPT_HEADER]=false;
    $opt[CURLOPT_CONNECTTIMEOUT]=15;
    $opt[CURLOPT_TIMEOUT]=300;
    $opt[CURLOPT_AUTOREFERER]=true;
    $opt[CURLOPT_USERAGENT]=&#39;Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11&#39;;
    curl_setopt_array($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);
    $res=str_replace(&#39;onSibRequestSuccess(&#39;,"",$out_put);
    $res=rtrim($res,&#39;);1&#39;);
    $result=json_decode($res,true);
    //查询出图片信息
    preg_match(&#39;|<ul id="J_UlThumb" class="tb-thumb tb-clearfix">(.*)</ul>|isU&#39;, $content, $match);
    preg_match_all(&#39;/<img src="(.*?)" \//&#39;, $match[1], $images);

    $myres[&#39;title&#39;]=str_replace(&#39;-淘宝网&#39;,&#39;&#39;,$title);

    $myres[&#39;price&#39;]=current($result[&#39;data&#39;][&#39;originalPrice&#39;]);

    $myres[&#39;act_price&#39;]=current($result[&#39;data&#39;][&#39;promotion&#39;][&#39;promoData&#39;]);

    $myres[&#39;stock&#39;]=$result[&#39;data&#39;][&#39;dynStock&#39;][&#39;stock&#39;];

    $myres[&#39;banners&#39;]=$images[1];
  }else{
    //匹配是否下架
    if(strpos($content,&#39;此宝贝已下架&#39;)!==false){
      return false;
    }
    $start=strpos($url,&#39;&id=&#39;);
    $item_id=substr($url,$start+4,12);
    if(!is_numeric($item_id)){
      $start=strpos($url,&#39;?id=&#39;);
      $end=strpos($url,&#39;&spm&#39;);
      $item_id=substr($url,$start+4,$end-$start-4);
    }
    preg_match("|<title>(.*)</title>|isU",$content,$match);
    $title=$match[1];
    $myurl=&#39;https://mdskip.taobao.com/core/initItemDetail.htm?cachedTimestamp=1500562177777&queryMemberRight=true&cartEnable=true&offlineShop=false&addressLevel=2&itemId=&#39;.$item_id.&#39;&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&#39;;
    //价格库存信息
    $ch = curl_init();
    curl_setopt ($ch, CURLOPT_URL, $myurl);
    $opt[CURLOPT_HEADER]=false;
    $opt[CURLOPT_CONNECTTIMEOUT]=15;
    $opt[CURLOPT_TIMEOUT]=300;
    $opt[CURLOPT_AUTOREFERER]=true;
    $opt[CURLOPT_USERAGENT]=&#39;Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11&#39;;
    curl_setopt_array($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, &#39;UTF-8&#39;, &#39;UTF-8,GBK,GB2312,BIG5&#39; );
    $res=str_replace(&#39;setMdskip&#39;,"",$res);
    $res=str_replace(&#39;(&#39;,"",$res);
    $res=str_replace(&#39;)&#39;,"",$res);
    $result=json_decode($res,true);
    $nowk="";
    $nowstore="";
    foreach($result[&#39;defaultModel&#39;][&#39;inventoryDO&#39;][&#39;skuQuantity&#39;] as $k=>$val){
      $nowk=$k;
      $nowstore=$val;
      break;
    }

    $myres[&#39;title&#39;]=str_replace(&#39;-tmall.com天猫&#39;,&#39;&#39;,$title);

    $myres[&#39;price&#39;]=$result[&#39;defaultModel&#39;][&#39;itemPriceResultDO&#39;][&#39;priceInfo&#39;][$nowk][&#39;price&#39;];

    $myres[&#39;act_price&#39;]=isset($result[&#39;defaultModel&#39;][&#39;itemPriceResultDO&#39;][&#39;priceInfo&#39;][$nowk][&#39;suggestivePromotionList&#39;])?$result[&#39;defaultModel&#39;][&#39;itemPriceResultDO&#39;][&#39;priceInfo&#39;][$nowk][&#39;suggestivePromotionList&#39;]:$result[&#39;defaultModel&#39;][&#39;itemPriceResultDO&#39;][&#39;priceInfo&#39;][$nowk];

    $myres[&#39;stock&#39;]=$result[&#39;defaultModel&#39;][&#39;inventoryDO&#39;][&#39;totalQuantity&#39;]?$result[&#39;defaultModel&#39;][&#39;inventoryDO&#39;][&#39;totalQuantity&#39;]:$nowstore[&#39;quantity&#39;];
    //查询出图片信息
    preg_match(&#39;|<ul id="J_UlThumb" class="tb-thumb tm-clear">(.*)</ul>|isU&#39;,$content, $match);
    preg_match_all(&#39;/<img src="(.*?)" \//&#39;,$match[1],$images);
    $myres[&#39;banners&#39;]=$images[1];
  }
  return $myres;
}

登录后复制

上述代码用到phpquery的库，但是其实没啥用，直接用Curl就行，具体爬取的数据可以穿参查看结果，方法不区分淘宝和天猫链接，但是前提是必须是PC端链接，另外正则写的不规范，所以可以自己重写正则来匹配数据。