一、思路

最近做了一个网站,用来从网站上抓取天猫和淘宝的商品信息。 首先,我在手机上查看了网页,发现使用了react。 我对它了解不多。 爬取URL获取数据时,并没有获取到价格、库存等信息,仔细研究后发现是另外一个接口异步请求的,但是该接口必须使用reference来获取数据,所以我 写了一个简单的爬虫,方法如下: 用来爬取商品预览图和商品第一品类的价格、库存等。

二、实现

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,’此宝贝已下架’)!==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];
//价格库存信息
$ch = curl_init();
curl_setopt ($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);
//查询出图片信息
preg_match(‘|<ul id=”J_UlThumb” class=”tb-thumb tb-clearfix”>(.*)</ul>|isU’, $content, $match);
preg_match_all(‘/<img data-src=”(.*?)” \//’, $match[1], $images);

$myres[‘title’]=str_replace(‘-淘宝网’,”,$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,’此宝贝已下架’)!==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’;
//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;
$opt[CURLOPT_USERAGENT]=’Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11′;
curl_setopt_array($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;
}

$myres[‘title’]=str_replace(‘-tmall.com天猫’,”,$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’];
//查询出图片信息
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。

发表回复

您的电子邮箱地址不会被公开。