Heim  >  Artikel  >  php教程  >  抓取“IC 交易网”供应商程序

抓取“IC 交易网”供应商程序

WBOY
WBOYOriginal
2016-06-13 10:47:231557Durchsuche

/** 
* 抓取“IC 交易网”供应商主程序 
* author Lee.
* Last modify $Date: 2012-2-6 10:44:32$ 
* 注:本程序按照编码 GB2312 执行,因为“IC 交易网”网站是GB2312编码,数据库也得保持一致
*/ 
class ic { 
    private $key; // 型号  
    private $pageNum; // 页码  
 
    /**
     * 入口程序
     */ 
    public function go($key) { 
        $this->key = $key; 
        $this->pageNum = $this->getPageNum(); 
        $this->getInfo(); 
    } 
 
    /**
     * 获取供应商 url 链接数组
     * @return ArrayObject
     */ 
    private function getInfo() { 
        if ($this->pageNum==1) { # 处理只有一页的情况 
            $arr = $this->shopUrlMatchReArr($this->getContent()); 
            $this->isAddSuccess($arr); 
        } elseif ($this->pageNum>1) { # 多页 
            for ($i=1; $ipageNum; $i++) { 
                $arr = $this->shopUrlMatchReArr($this->getContent($i)); 
                $this->isAddSuccess($arr); 
            } 
        }    
    } 
     
    /**
     * 打印是否添加成功
     * @param ArrayObject $arr
     * @return string
     */ 
    private function isAddSuccess($arr) { 
        foreach ($arr as $k=>$v) { 
            if ($this->execAdd($this->getInfoByShopUrl($v))) { 
                echo 'Add Success!!'; 
            } else { 
                echo 'Add Faild!!'; 
            } 
        } 
    } 
 
    /**
     * 执行添加到数据库
     * @param ArrayObject $infoArr
     * @return Number 受影响的行数
     */ 
    private function execAdd($infoArr) { 
        $mysqli = $this->getDb(); 
        if (!emptyempty($infoArr['company'])) { 
            if (!$this->isExists($mysqli, $infoArr)) { 
                $num = $mysqli->query("INSERT INTO ic(company,address,phone,mobile,fax,zip,person,qq,msn,email,website,regDate,shopUrl) VALUES ('{$infoArr['company']}','{$infoArr['address']}','{$infoArr['phone']}','{$infoArr['mobile']}','{$infoArr['fax']}','{$infoArr['zip']}','{$infoArr['person']}','{$infoArr['qq']}','{$infoArr['msn']}','{$infoArr['email']}','{$infoArr['website']}','{$infoArr['regDate']}','{$infoArr['shopUrl']}')"); 
                return $num; 
            } else { 
                return false; # 表示数据已经存在 
            } 
        } else { 
            return false; 
        } 
    } 
 
    /**
     * 连接数据库
     */ 
    private function getDb() { 
        $mysqli = new mysqli('localhost', 'root', '1715544', 'weiku'); 
        $mysqli->query('SET NAMES GB2312'); 
        return $mysqli; 
    } 
 
    /**
     * 检查公司是否已经存在
     * @param Resource $mysqli
     * @param ArrayObject $infoArr
     * @return bool
     */ 
    private function isExists($mysqli, $infoArr) { 
        $mysqli->query("SELECT company FROM ic WHERE company = '{$infoArr['company']}'"); 
        if ($mysqli->affected_rows) { 
            return true; 
        } else { 
            return false; 
        } 
    } 
 
    /**
     * 格式化字符串
     * @param string $str 
     * @return string
     */ 
    private function formatString($str) { 
        return trim($str); 
    } 
 
    /**
     * 抓取信息
     * @param $url 
     * @return ArrayObject
     */ 
    private function getInfoByShopUrl($url) { 
        $re = $this->getUrlInfo($url); 
        if (stristr($re, '')) $re = preg_replace('/.*/Usi', '', $re); 
        preg_match_all('/(.+)/Usi', $re, $companyArr); <br>         preg_match_all('/地址:(.*)/Usi', $re, $addressArr); <br>         preg_match_all('/电话:(.*)/Usi', $re, $phoneArr); <br>         preg_match_all('/手机:(.*)/Usi', $re, $mobileArr); <br>         preg_match_all('/传真:(.*)/Usi', $re, $faxArr); <br>         preg_match_all('/邮编:(.*)/Usi', $re, $zipArr); <br>         preg_match_all('/联系人:(.*)/Usi', $re, $personArr); <br>         preg_match_all('/QQ:(.*)/Usi', $re, $qqArr); <br>         preg_match_all('/MSN:(.*)/Usi', $re, $msnArr); <br>         preg_match_all('/Email:(.*)/Usi', $re, $emailArr); <br>         preg_match_all('/网址:(.*)/Usi', $re, $websiteArr); <br>         preg_match_all('/注册日期:(.*)/Usi', $re, $regDateArr); <br>         $infoArr = array( <br>             'company'=>$this->formatString($companyArr[1][0]), <br>             'address'=>$this->formatString($addressArr[1][0]), <br>             'phone'=>$this->formatString($phoneArr[1][0]), <br>             'mobile'=>$this->formatString($mobileArr[1][0]), <br>             'fax'=>$this->formatString($faxArr[1][0]), <br>             'zip'=>$this->formatString($zipArr[1][0]), <br>             'person'=>$this->formatString($personArr[1][0]), <br>             'qq'=>$this->formatString($qqArr[1][0]), <br>             'msn'=>$this->formatString($msnArr[1][0]), <br>             'email'=>$this->formatString($emailArr[1][0]), <br>             'website'=>$this->stripATags($this->formatString($websiteArr[1][0])), <br>             'regDate'=>$this->formatString($regDateArr[1][0]), <br>             'shopUrl'=>$url <br>         ); <br>         return $infoArr; <br>     } <br>  <br>     /**<br>      * 根据页面获取供应商 url 数组<br>      * @param string $re<br>      * @return ArrayObject<br>      */ <br>     private function shopUrlMatchReArr($re) { <br>         preg_match_all('/<a onmousemove='\".+\"' onmouseout="hidetip\(\)" href="(.+)" target="\_blank">.+/Usi', $re, $arr); <br>         $arr = $this->formatUrlArr(array_unique($arr[1])); <br>         return $arr; <br>     } <br>      <br>     /**<br>      * 格式化数组<br>      * @param Array $arr<br>      * @return ArrayObject<br>      */ <br>     private function formatUrlArr($arr) { <br>         $newArr = array(); <br>         foreach ($arr as $key=>$value) { <br>             if ($this->isExistsHttp($value)) { <br>                 $newArr[$key] = $value; <br>             } <br>         } <br>         return $newArr; <br>     } <br>      <br>     /**<br>      * 格式化 QQ<br>      * @param string $str<br>      * @return string<br>      */ <br>     private function formatQqMsn($str, $e='QQ') { <br>         if (emptyempty($str)) return ''; <br>         preg_match_all('/alt="'.$e.'\:(.+)"/Usi', $str, $arr); <br>         if (count($arr[1])==1) return $arr[1][0]; <br>         $newStr = null; <br>         foreach ($arr[1] as $value) { <br>             $newStr .= $value . ' '; <br>         } <br>         return rtrim($newStr, ' '); <br>     } <br>  <br>     /**<br>      * 去掉网址的 A 标签<br>      * @param string $site<br>      * @return string<br>      */ <br>     private function stripATags($site) { <br>         $site = preg_replace('/</a><a.>(.+)/', '\1', $site); <br>         return $site; <br>     } <br>  <br>     /**<br>      * 检查 url 是否有 http<br>      * @param string $url<br>      * @return bool<br>      */ <br>     private function isExistsHttp($url) { <br>         if (stristr($url, 'http://')) { <br>             return true; <br>         } else { <br>             return false; <br>         } <br>     } <br>      <br>     /**<br>      * 获取页面内容<br>      * @param Number $page<br>      * @return string<br>      */ <br>     private function getContent($page=1) { <br>         $re = file_get_contents($this->getUrl($this->key, $page)); <br>         return $re; <br>     } <br>      <br>     /**<br>      * 获取页码<br>      * @return Number<br>      */ <br>     private function getPageNum() { <br>         $i = null; <br>         $re = $this->getContent(); <br>         preg_match_all('/共(.+)页/Usi', $re, $arr); <br>         $i = $arr[1][0]; <br>         return $i; <br>     } <br>  <br>     /**<br>      * 获取 URL 链接<br>      * @param string $str<br>      * @param int $page 页码<br>      * @return string<br>      */ <br>     private function getUrl($str, $page=1) { <br>         return "http://www.ic.net.cn/partsearch/searchinstock.asp?newtype=1&area=&Page={$page}&partnumber={$str}&mfg=&DateCode=&QTY=&PRICE=&Exact=&orderby=inputdate&qty_filter=50&usertype2=1&pack="; <br>     } <br>  <br>     /**<br>      * 获取页面内容<br>      * @param string $url<br>      * @return string<br>      */ <br>     private function getUrlInfo($url) { <br>         $re = file_get_contents($url); <br>         return $re; <br>     } <br> } <br>  <br> /*<br> 程序运行思路:根据“IC 交易网”的IC搜索功能,输入型号进行搜索,然后抓取供应商信息<br>  <br> 数据库结构<br> CREATE TABLE `ic` (<br>     `id` mediumint(8) unsigned NOT NULL auto_increment,<br>     `company` varchar(500) NOT NULL,<br>     `address` varchar(500) default NULL,<br>     `phone` varchar(500) default NULL,<br>     `mobile` varchar(500) default NULL,<br>     `fax` varchar(300) default NULL,<br>     `zip` varchar(300) default NULL,<br>     `person` varchar(500) default NULL,<br>     `qq` varchar(300) default NULL,<br>     `msn` varchar(300) default NULL,<br>     `email` varchar(500) default NULL,<br>     `website` varchar(300) default NULL,<br>     `regDate` varchar(500) default NULL,<br>     PRIMARY KEY  (`id`)<br> ) ENGINE=InnoDB DEFAULT CHARSET=gb2312<br> */ <br>  <br> $i = new ic(); <br> $arr = array_unique(array('MAX3232', 'AML8613', 'MT6225A', 'OM8373PS/N3/A', 'PT7313', 'MAX8212ESA', 'TL431', 'S3C2440', 'TMS320F2812PGFA', 'PCM1704', 'AN6717', 'CA3162E', 'CA3161E', 'LM393N', 'DS18B20', 'SHT10', 'AML8613', 'AN6717', 'LM393N', 'CA3161E', 'CA3162E', 'PCM1704', 'STK392-040', 'K1667', 'MAX232', 'STM32F103', 'LM358')); <br> foreach ($arr as $v) { <br>     $i->go($v); <br> } <br> ?> <br> <?php <br /> /**<br> * 抓取“IC 交易网”供应商主程序<br> * author Lee.<br> * Last modify $Date: 2012-2-6 10:44:32$<br> * 注:本程序按照编码 GB2312 执行,因为“IC 交易网”网站是GB2312编码,数据库也得保持一致<br> */<br> class ic {<br>  private $key; // 型号<br>  private $pageNum; // 页码</a.>

 /**
  * 入口程序
  */
 public function go($key) {
  $this->key = $key;
  $this->pageNum = $this->getPageNum();
  $this->getInfo();
 }

 /**
  * 获取供应商 url 链接数组
  * @return ArrayObject
  */
 private function getInfo() {
  if ($this->pageNum==1) { # 处理只有一页的情况
   $arr = $this->shopUrlMatchReArr($this->getContent());
   $this->isAddSuccess($arr);
  } elseif ($this->pageNum>1) { # 多页
   for ($i=1; $ipageNum; $i++) {
    $arr = $this->shopUrlMatchReArr($this->getContent($i));
    $this->isAddSuccess($arr);
   }
  } 
 }
 
 /**
  * 打印是否添加成功
  * @param ArrayObject $arr
  * @return string
  */
 private function isAddSuccess($arr) {
  foreach ($arr as $k=>$v) {
   if ($this->execAdd($this->getInfoByShopUrl($v))) {
    echo 'Add Success!!';
   } else {
    echo 'Add Faild!!';
   }
  }
 }

 /**
  * 执行添加到数据库
  * @param ArrayObject $infoArr
  * @return Number 受影响的行数
  */
 private function execAdd($infoArr) {
  $mysqli = $this->getDb();
  if (!empty($infoArr['company'])) {
   if (!$this->isExists($mysqli, $infoArr)) {
    $num = $mysqli->query("INSERT INTO ic(company,address,phone,mobile,fax,zip,person,qq,msn,email,website,regDate,shopUrl) VALUES ('{$infoArr['company']}','{$infoArr['address']}','{$infoArr['phone']}','{$infoArr['mobile']}','{$infoArr['fax']}','{$infoArr['zip']}','{$infoArr['person']}','{$infoArr['qq']}','{$infoArr['msn']}','{$infoArr['email']}','{$infoArr['website']}','{$infoArr['regDate']}','{$infoArr['shopUrl']}')");
    return $num;
   } else {
    return false; # 表示数据已经存在
   }
  } else {
   return false;
  }
 }

 /**
  * 连接数据库
  */
 private function getDb() {
  $mysqli = new mysqli('localhost', 'root', '1715544', 'weiku');
  $mysqli->query('SET NAMES GB2312');
  return $mysqli;
 }

 /**
  * 检查公司是否已经存在
  * @param Resource $mysqli
  * @param ArrayObject $infoArr
  * @return bool
  */
 private function isExists($mysqli, $infoArr) {
  $mysqli->query("SELECT company FROM ic WHERE company = '{$infoArr['company']}'");
  if ($mysqli->affected_rows) {
   return true;
  } else {
   return false;
  }
 }

 /**
  * 格式化字符串
  * @param string $str
  * @return string
  */
 private function formatString($str) {
  return trim($str);
 }

 /**
  * 抓取信息
  * @param $url
  * @return ArrayObject
  */
 private function getInfoByShopUrl($url) {
  $re = $this->getUrlInfo($url);
  if (stristr($re, '')) $re = preg_replace('/.*/Usi', '', $re);
  preg_match_all('/(.+)/Usi', $re, $companyArr);<br>   preg_match_all('/地址:(.*)/Usi', $re, $addressArr);<br>   preg_match_all('/电话:(.*)/Usi', $re, $phoneArr);<br>   preg_match_all('/手机:(.*)/Usi', $re, $mobileArr);<br>   preg_match_all('/传真:(.*)/Usi', $re, $faxArr);<br>   preg_match_all('/邮编:(.*)/Usi', $re, $zipArr);<br>   preg_match_all('/联系人:(.*)/Usi', $re, $personArr);<br>   preg_match_all('/QQ:(.*)/Usi', $re, $qqArr);<br>   preg_match_all('/MSN:(.*)/Usi', $re, $msnArr);<br>   preg_match_all('/Email:(.*)/Usi', $re, $emailArr);<br>   preg_match_all('/网址:(.*)/Usi', $re, $websiteArr);<br>   preg_match_all('/注册日期:(.*)/Usi', $re, $regDateArr);<br>   $infoArr = array(<br>    'company'=>$this->formatString($companyArr[1][0]),<br>    'address'=>$this->formatString($addressArr[1][0]),<br>    'phone'=>$this->formatString($phoneArr[1][0]),<br>    'mobile'=>$this->formatString($mobileArr[1][0]),<br>    'fax'=>$this->formatString($faxArr[1][0]),<br>    'zip'=>$this->formatString($zipArr[1][0]),<br>    'person'=>$this->formatString($personArr[1][0]),<br>    'qq'=>$this->formatString($qqArr[1][0]),<br>    'msn'=>$this->formatString($msnArr[1][0]),<br>    'email'=>$this->formatString($emailArr[1][0]),<br>    'website'=>$this->stripATags($this->formatString($websiteArr[1][0])),<br>    'regDate'=>$this->formatString($regDateArr[1][0]),<br>    'shopUrl'=>$url<br>   );<br>   return $infoArr;<br>  }

 /**
  * 根据页面获取供应商 url 数组
  * @param string $re
  * @return ArrayObject
  */
 private function shopUrlMatchReArr($re) {
  preg_match_all('/.+/Usi', $re, $arr);
  $arr = $this->formatUrlArr(array_unique($arr[1]));
  return $arr;
 }
 
 /**
  * 格式化数组
  * @param Array $arr
  * @return ArrayObject
  */
 private function formatUrlArr($arr) {
  $newArr = array();
  foreach ($arr as $key=>$value) {
   if ($this->isExistsHttp($value)) {
    $newArr[$key] = $value;
   }
  }
  return $newArr;
 }
 
 /**
  * 格式化 QQ
  * @param string $str
  * @return string
  */
 private function formatQqMsn($str, $e='QQ') {
  if (empty($str)) return '';
  preg_match_all('/alt="'.$e.'\:(.+)"/Usi', $str, $arr);
  if (count($arr[1])==1) return $arr[1][0];
  $newStr = null;
  foreach ($arr[1] as $value) {
   $newStr .= $value . ' ';
  }
  return rtrim($newStr, ' ');
 }

 /**
  * 去掉网址的 A 标签
  * @param string $site
  * @return string
  */
 private function stripATags($site) {
  $site = preg_replace('/(.+)/', '\1', $site);
  return $site;
 }

 /**
  * 检查 url 是否有 http
  * @param string $url
  * @return bool
  */
 private function isExistsHttp($url) {
  if (stristr($url, 'http://')) {
   return true;
  } else {
   return false;
  }
 }
 
 /**
  * 获取页面内容
  * @param Number $page
  * @return string
  */
 private function getContent($page=1) {
  $re = file_get_contents($this->getUrl($this->key, $page));
  return $re;
 }
 
 /**
  * 获取页码
  * @return Number
  */
 private function getPageNum() {
  $i = null;
  $re = $this->getContent();
  preg_match_all('/共(.+)页/Usi', $re, $arr);
  $i = $arr[1][0];
  return $i;
 }

 /**
  * 获取 URL 链接
  * @param string $str
  * @param int $page 页码
  * @return string
  */
 private function getUrl($str, $page=1) {
  return "http://www.ic.net.cn/partsearch/searchinstock.asp?newtype=1&area=&Page={$page}&partnumber={$str}&mfg=&DateCode=&QTY=&PRICE=&Exact=&orderby=inputdate&qty_filter=50&usertype2=1&pack=";
 }

 /**
  * 获取页面内容
  * @param string $url
  * @return string
  */
 private function getUrlInfo($url) {
  $re = file_get_contents($url);
  return $re;
 }
}

/*
程序运行思路:根据“IC 交易网”的IC搜索功能,输入型号进行搜索,然后抓取供应商信息

数据库结构
CREATE TABLE `ic` (
 `id` mediumint(8) unsigned NOT NULL auto_increment,
 `company` varchar(500) NOT NULL,
 `address` varchar(500) default NULL,
 `phone` varchar(500) default NULL,
 `mobile` varchar(500) default NULL,
 `fax` varchar(300) default NULL,
 `zip` varchar(300) default NULL,
 `person` varchar(500) default NULL,
 `qq` varchar(300) default NULL,
 `msn` varchar(300) default NULL,
 `email` varchar(500) default NULL,
 `website` varchar(300) default NULL,
 `regDate` varchar(500) default NULL,
 PRIMARY KEY  (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=gb2312
*/

$i = new ic();
$arr = array_unique(array('MAX3232', 'AML8613', 'MT6225A', 'OM8373PS/N3/A', 'PT7313', 'MAX8212ESA', 'TL431', 'S3C2440', 'TMS320F2812PGFA', 'PCM1704', 'AN6717', 'CA3162E', 'CA3161E', 'LM393N', 'DS18B20', 'SHT10', 'AML8613', 'AN6717', 'LM393N', 'CA3161E', 'CA3162E', 'PCM1704', 'STK392-040', 'K1667', 'MAX232', 'STM32F103', 'LM358'));
foreach ($arr as $v) {
 $i->go($v);
}
?>


摘自 Lee.的专栏
Stellungnahme:
Der Inhalt dieses Artikels wird freiwillig von Internetnutzern beigesteuert und das Urheberrecht liegt beim ursprünglichen Autor. Diese Website übernimmt keine entsprechende rechtliche Verantwortung. Wenn Sie Inhalte finden, bei denen der Verdacht eines Plagiats oder einer Rechtsverletzung besteht, wenden Sie sich bitte an admin@php.cn
Vorheriger Artikel:php 验证码类Nächster Artikel:ExpressionEngine 开发框架图