苏宁、京东物流支持

最新推荐文章于 2022-06-30 16:34:11 发布

clmforever

最新推荐文章于 2022-06-30 16:34:11 发布

阅读量544

点赞数 2

分类专栏：快递文章标签：快递京东物流苏宁物流

本文链接：https://blog.csdn.net/clmforever/article/details/93341417

版权

快递专栏收录该内容

0 篇文章 0 订阅

订阅专栏

最近项目中有需要用到京东和苏宁的物流信息，但市场上的第三方接口都是收费的，还就是有些不太稳定，于是一鼓作气写了个“爬虫”，这里做简要说明

语言：php，请求先安装curl扩展
一、苏宁物流
RequestUrl:https://wuliu.suning.com/home/toLogisticsDetail.htm
RequestType:post
RequestData:[‘expressNos’=>$this->expressNo]

$Reqdata = ['expressNos'=>$this->expressNo];
$url = 'https://wuliu.suning.com/home/toLogisticsDetail.htm';
$content = $this->Curl_post($url,$Reqdata);

private function Curl_post($url,$post_data){
	$ch = curl_init();
	curl_setopt($ch, CURLOPT_POST, 1);
	curl_setopt($ch, CURLOPT_HEADER, 0);
	curl_setopt($ch, CURLOPT_URL,$url);
	curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
	$result = curl_exec($ch);
	$data = str_replace("\"",'"',$result );
	$data = json_decode($data,true);
	return $data;
}

拿到请求的内容，做如下处理

去掉最外层部分

$content = explode('<ul class="s-waybill-content">',$content)[1];
$content2 = explode('</ul>',$content)[0];

去掉中心标签的空格，换行，注释等

 $content2 = $this->compress_html($content2);
 private function compress_html($string) {
	$string = str_replace("\r", "", $string);
    $string = str_replace("\r\n", '', $string); //清除换行符
    $string = str_replace("\n", '', $string); //清除换行符
    $string = str_replace("\t", '', $string); //清除制表符
    $pattern = array("/> *([^ ]*) *</","/[\s]+/","/<!--[^!]*-->/","/\" /","/ \"/","'/\*[^*]*\*/'");
    $replace = array(">\\1<"," ","","\"","\"","");
    return preg_replace($pattern, $replace, $string);
}

继续做处理…，主要是字符截取和替换，正则等

$pattern = '|<span[^>]*>(.*)</span>|isU';
$s = preg_match_all($pattern, $content2, $matches);
$list = array_chunk($matches[1],2);
foreach ($list as $k=>$v) {
	$list[$k]['time'] = $list[$k][0];
	$list[$k]['text'] = $list[$k][1];
	unset($list[$k][0]);
	unset($list[$k][1]);
}

完成，$list 就是拿到的数据 .

二、京东物流

RequestUrl:https://www.jdwl.com/order/search?waybillCodes=
RequestType:get

$url = 'https://www.jdwl.com/order/search?waybillCodes='.$this->expressNo;
$content = $this->Curl_get($url);

private function Curl_get($url){
	$curl = curl_init();
	curl_setopt($curl, CURLOPT_URL, $url);
	curl_setopt($curl, CURLOPT_HEADER, 1);
	curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
	$data = curl_exec($curl);
	curl_close($curl);
	return $data;
}

拿到请求的内容，做如下处理

同样去掉最外层部分

$content = explode('<ul class="b-new-search-list">',$content)[1];
$content2 = explode('</ul>',$content)[0];

去掉干扰项

$content2 = preg_replace("#<i[^>]*>(.*)</i>#isU", "$1", $content2);
$content2 = $this->compress_html($content2);//这个函数在上面有写

截取所有li标签里的内容

$_li = '|<li[^>]*>(.*)</li>|isU';
$s = preg_match_all($_li, $content2, $li_);

循环 $li_[1]的内容，时间和内容的处理

$list = [];//数组，存放物流信息
foreach ($li_[1] as &$v) {
	//s1截取所有日期时间点
	$_time = '|<span[^>]*>(.*)</span>|isU';
	preg_match_all($_time, $v, $time_);
	$date = $time_[1][0];//日期
	unset($time_[1][0]);//去掉日期
	$times = $time_[1];//得到当前日期的所有时间点
	//加上日期
	foreach($times as &$vv){
		$vv = $date.' '.$vv;
	}

	//s2截取所有内容
	$_pcon = '|<p[^>]*>(.*)</p>|isU';
	preg_match_all($_pcon, $v, $pcon_);
	$pcons = $pcon_[1];

	//s3时间与内容匹配
	$reslist = ['time'=>$times,'text'=>$pcons];
	$arrs = array();
	foreach ($reslist as $key => $value) {
        array_push($arrs,$reslist[$key]);
      }
	$r = $this->array_merge_more(['time','text'],$arrs);
	foreach ($r as $v1) {
		array_push($list,$v1);
	}
}

//主要是相同长度，相同顺序的2组数组按照key值拼接组合
private function array_merge_more($keys,$arrs){
    // 检查参数是否正确
    if(!$keys || !is_array($keys) || !$arrs || !is_array($arrs) || count($keys)!=count($arrs)){
      return array();
    }
    // 一维数组中最大长度
    $max_len = 0;
    // 整理数据，把所有一维数组转重新索引
    for($i=0,$len=count($arrs); $i<$len; $i++){
      $arrs[$i] = array_values($arrs[$i]);
      if(count($arrs[$i])>$max_len){
        $max_len = count($arrs[$i]);
      }
    }

    // 合拼数据
    $result = array();
    for($i=0; $i<$max_len; $i++){
      $tmp = array();
      foreach($keys as $k=>$v){
        if(isset($arrs[$k][$i])){
          $tmp[$v] = $arrs[$k][$i];
        }
      }
      $result[] = $tmp;
    }
    return $result;
  }