php查词采集器

/**  * dict.class.php 采集百度词典翻译内容  *  * @copyright      (C) 2014 widuu  * @license       http://www.widuu.com  * @lastmodify     2014-2-15  */      header("content-type:text/html;charset=utf8"); class Dict{       private $word;           //显示的条数     private static $num = 10;       public function __construct(){}                 /**    * 公用返回百度采集数据的方法    * @param string 英文单词    * retun array(      *              symbol" => 音标      *              "pro"    => 发音      *              "example"=> 例句      *              "explain"=> 简明释义      *              "synonym"=> 同反义词      *              "phrase" => 短语数组      *          )    *      */    public function content($word){          $this -> word = $word;          $symbol = $this -> Pronounced();          $pro    = $this->getSay();          $example = $this -> getExample();          $explain = $this -> getExplain();          $synonym = $this -> getSynonym();          $phrase = $this -> getPhrase();          $result = array(                 "symbol" => $symbol,     //音标                 "pro"    => $pro,            //发音                 "example"=> $example,        //例句                 "explain"=> $explain,        //简明释义                 "synonym"=> $synonym,        //同反义词                 "phrase" => $phrase      //短语数组             );         return $result;     }         /**    * 远程获取百度翻译内容    * get function curl    * retun string    *      */      private function getContent(){         $useragent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0";         $ch = curl_init();         $url = "http://dict.baidu.com/s?wd=".$this->word;         curl_setopt($ch, CURLOPT_URL, $url);         curl_setopt($ch, CURLOPT_USERAGENT,$useragent);         curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);          curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);          curl_setopt($ch, CURLOPT_HTTPGET, 1);         curl_setopt($ch, CURLOPT_AUTOREFERER,1);         curl_setopt($ch, CURLOPT_HEADER, 0);          curl_setopt($ch, CURLOPT_TIMEOUT, 30);         $result = curl_exec($ch);         if (curl_errno($curl)) {             echo 'Errno'.curl_error($curl);         }         curl_close($ch);         return $result;     }         /**    * 获取百度翻译发音    * retun array(英,美)    *      */      private function Pronounced(){         $data = $this -> getContent();         preg_match_all("/\"EN\-US\"\>(.*)\<\/b\>/Ui",$data,$pronounced);         return array(             'en' => $pronounced[1][0],             'us' => $pronounced[1][1]         );     }       /**      * 获取百度翻译发音      * return array(英,美)      *      */      private function getSay(){         $data = $this -> getContent();         preg_match_all("/url=\"(.*)\"/Ui",$data,$pronounced);         return array(             'en' => $pronounced[1][0],             'us' => $pronounced[1][1]         );       }       /**    * 获取百度翻译例句    * return array() 多维数组 例句    *       */      private function getExample(){         $str = "";         $data = $this -> getContent();         preg_match_all("/var example_data = (.*)\]\;/Us",$data,$example);       $data1 = "[[[".ltrim($example[1][0],"[");       $data2 = explode("[[[",$data1);       $num = count(array_filter($data2));         foreach($data2 as $key => $value){             $data3 = explode("[[","[[".$value);             foreach ($data3 as $k => $v) {                 preg_match_all("/\[\"(.*)\",/Us","[".$v, $match);                 if(!empty($match[1])){                     $str .= implode($match[1]," ")."@";                 }             }         }         $data4 = trim($str,"@");         $data5 = explode("@", $data4);         $result = array_chunk($data5, 2);         return $result;     }       /**    * 获取简明释义    * return array (x => "词性",b => "附属")    *       **/      private function getExplain(){         $data = $this -> getContent();         preg_match_all("/id\=\"en\-simple\-means\"\>(.*)\/Us",$data,$explain);         $r_data = $explain[1][0];         preg_match_all("/\\(?P.*)\<\/strong\>\(?P.*)\<\/span\>\<\/p\>/Us", $r_data, $a_data);         preg_match_all("/\(?P[^\>]+)\:\(?P.*)\<\/a\>\<\/span\>/Us", $r_data, $b_data);                   $result = array();         foreach ($a_data["adj"] as $key => $value) {             $result[$value] = $a_data["name"][$key];         }                   $word_b = array();         foreach ($b_data["tag"] as $key => $value) {             $word_b[$value] = strip_tags($b_data["word"][$key]);         }                   $result_data = array("x" => $result,"b" => $word_b);           return $result_data;     }         /**    * 获取同义词    * return array(0 => "同义词", 1 => "反义词") 一般为多维数组    *       */      private function getSynonym(){         $data = $this -> getContent();         preg_match_all("/id=\"en\-syn\-ant\"\>(.*)/Us",$data,$synonym);         $content = $synonym[1][0];         $data1 = explode("", $content);         $result = array();         $data2 = array();         foreach ($data1 as $key => $value) {             preg_match_all("/\(?P.*)\ \;\<\/strong\>\<\/div\>\\(?.*)\<\/ul\>/Us", $value, $r_data);             $data2[$key]["adj"] = $r_data["adj"];             $data2[$key]["content"] = $r_data["content"];         }           foreach ($data2 as $key => $value) {             foreach ($value["content"] as $k => $v) {                 if(!empty($v)){                     preg_match_all("/\\(?P.*)\<\/p\>(?P<value>.*)\<\/li>/Us", $v, $v_data);                     foreach ($v_data['title'] as $m => $d) {                         $data = strip_tags(preg_replace("<</a>>"," ", $v_data["value"][$m]));                         $result[$key][$value["adj"][$k]][$d] = $data;                     }                 }             }         }         return $result;     }       /**    * 获取短语词组    * return array (key => value) 一维或者多维数组    *       */      private function getPhrase(){         $num = self::$num;         $data = $this -> getContent();         preg_match_all("/id=\"en\-phrase\"\>(.*)\<div class\=\"source\"\>/Us",$data,$phrase);         $data = explode("</dd>",$phrase[1][0]);         $data1 = array_slice($data,0,$num);         $result = array();         foreach ($data1 as $key => $value) {             $data2 = explode("</p>", $value);             $n = count($data2);             if($n<=3){                 $result[str_replace(" ","",strip_tags($data2[0]))] = strip_tags($data2[1]);             }else{                 $data3 = array_slice($data2,0,$n-1);                 $data4 = array_slice($data2,0,2);                 $res = array_diff($data3,$data4);                 $data5 = array_chunk($res,2);                 $key_value = trim(str_replace(" ","",strip_tags($data4[0])));                 $result[$key_value] = strip_tags($data4[1]);                 foreach ($data5 as $key => $value) {                     foreach ($value as $k => $v) {                         $value[$k] = strip_tags($v);                     }                     $array = array($result[$key_value],$value);                     if (array_key_exists($key_value, $result)){                         $result[$key_value] = $array;                     }                 }                               }         }         return $result;     }       /**      * 将数组转换为字符串      *      * @param  array  $data    数组      * @param  bool  $isformdata 如果为0,则不使用new_stripslashes处理,可选参数,默认为1      * @return  string 返回字符串,如果,data为空,则返回空      */    private function array2string($data, $isformdata = 1) {       if($data == '') return '';       if($isformdata) $data = $this->new_stripslashes($data);       return addslashes(var_export($data, TRUE));     }       /**      * 返回经stripslashes处理过的字符串或数组      * @param $string 需要处理的字符串或数组codego.net/25/1/1/      * @return mixed      */    private function new_stripslashes($string) {       if(!is_array($string)) return stripslashes($string);       foreach($string as $key => $val) $string[$key] = $this->new_stripslashes($val);       return $string;     }   }   // $word = new dict("express"); // $word ->content();</p><p><img src="/upload/ad_content/xuanchuantu-10.jpg"></p><p><a href="https://www.cdcxhl.com/" target="_blank">创新互联建站</a>专注于嘉鱼网站建设服务及定制,我们拥有丰富的企业做网站经验。 热诚为您提供嘉鱼营销型网站建设,嘉鱼网站制作、嘉鱼网页设计、嘉鱼网站官网定制、<a href="https://www.cdcxhl.com/xiaochengx.html" target="_blank">小程序设计</a>服务,打造嘉鱼网络公司原创品牌,更为您提供<a href="https://www.cdcxhl.com/paiming/jiayu.html" target="_blank">嘉鱼网站排名</a>全网营销落地服务。</p> <br> 网站名称:php查词采集器 <br> 标题链接:<a href="http://www.xwwzsj.com/article/pihpjo.html">http://www.xwwzsj.com/article/pihpjo.html</a> </div> </div> <div class="other"> <h3>其他资讯</h3> <ul> <li> <a href="/article/dppoihc.html">服务器托管的费用一般多少?北京个人服务器托管</a> </li><li> <a href="/article/dppoged.html">jpaoracle</a> </li><li> <a href="/article/dppogss.html">大数据工程师报考费用?(阿里云速成美站价格)</a> </li><li> <a href="/article/dppogeg.html">MySQL多表更新和多表删除的实现</a> </li><li> <a href="/article/dppogih.html">远程优先的时代如何缓解勒索软件攻击?</a> </li> </ul> </div> </div> <div class="f_service_con"> <div class="h_fumin"> <div class="h_fumin_lei"> <div class="h_fumin_lei_tu"><img src="/Public/Home/images/f_service01.png"></div> <p>售后响应及时</p><span>7×24小时客服热线</span> </div> <div class="h_fumin_lei"> <div class="h_fumin_lei_tu"><img src="/Public/Home/images/f_service02.png"></div> <p>数据备份</p><span>更安全、更高效、更稳定</span> </div> <div class="h_fumin_lei"> <div class="h_fumin_lei_tu"><img src="/Public/Home/images/f_service03.png"></div> <p>价格公道精准</p><span>项目经理精准报价不弄虚作假</span> </div> <div class="h_fumin_lei"> <div class="h_fumin_lei_tu"><img src="/Public/Home/images/f_service04.png"></div> <p>合作无风险</p><span>重合同讲信誉,无效全额退款</span> </div> </div> </div> <div class="footerbar"> <div class="footer-t"> <div class="f-box"> <div class="f-1"> <div class="f-t"> <h2>联系我们</h2> <span>TEL</span> </div> <div class="f-b"> <h1><a href="tel:13518219792" rel="nofollow">135-1821-9792</a></h1> <h1><a href="tel:028-86922220" rel="nofollow">028-86922220</a></h1> <p>地址:成都市太升南路288号锦天国际</p> </div> </div> <div class="f-2"> <div class="f-t"> <h2>快捷导航</h2> <span>Shortcut</span> </div> <div class="f-b"> <ul > </ul> <ul > <li><a href="/jianshe" title="宣威网站建设">宣威网站建设</a></li> <li><a href="/jianshe#ym_websiteBox2" title="品牌网站建设">品牌网站建设</a></li> <li><a href="/jianshe#ym_websiteBox1" title="企业网站建设">企业网站建设</a></li> <li><a href="/jianshe#ym_websiteBox4" title="集团网站建设">集团网站建设</a></li> <li><a href="/jianshe#ym_websiteBox4_2" title="外贸网站建设">外贸网站建设</a></li> <li><a href="/jianshe#ym_websiteBox4_5" title="企业宣传视频">企业宣传视频</a></li> </ul> <ul > <li><a href="/weixin" title="微信开发">微信开发</a></li> <li><a href="/weixin#item1" title="公众号开发">公众号开发</a></li> <li><a href="/weixin#item2" title="微商城建设">微商城建设</a></li> <li><a href="/weixin#item3" title="微官网建设">微官网建设</a></li> <li><a href="/weixin#item4" title="小程序开发">小程序开发</a></li> </ul> <ul> <li><a href="/case/" title="网站作品案例">网站作品案例</a></li> <li><a href="/case/" title="品牌网站案例">品牌网站案例</a></li> <li><a href="/case/" title="集团网站案例">集团网站案例</a></li> <li><a href="/case/" title="企业网站案例">企业网站案例</a></li> <li><a href="/case/" title="外贸网站案例">外贸网站案例</a></li> <li><a href="/case/" title="营销网站案例">营销网站案例</a></li> </ul> <ul style="margin:0;"> <li><a href="/about/">瑞达杰昌建站</a></li> <li><a href="/about/">公司简介</a></li> <li><a href="/about#ab_item3">企业文化</a></li> <li><a href="/contact">联系我们</a></li> <li><a href="/Pay.html">付款方式</a></li> <li><a href="/jianshe#ym_websiteBox8">售后服务</a></li> </ul> <div style="clear:both;"></div> </div> </div> <div class="f-3"> <div class="f-t"> <h2>二维码</h2> <span>QR CODE</span> </div> <div class="f-b"> <ul> <li><img src="/Public/Home/images/fewm.png"> <p>微信公众号</p> </li> <li style="margin: 0"><img src="/Public/Home/images/fewm2.png"> <p>手机端网站</p> </li> <div style="clear:both;"></div> </ul> </div> </div> <div style="clear:both;"></div> </div> </div> <div class="footer-about"> <div class="w1200">瑞达杰昌建站工作室是一家专注从事于高品质视觉体验及互联网设计开发,<a href="/" target="_blank">宣威网站建设</a>,<a href="/jianshe" target="_blank">宣威网站设计</a>,<a href="/jianshe" target="_blank">宣威网页设计</a>,<a href="/jianshe" target="_blank">宣威网站制作</a>,<a href="/jianshe#ym_websiteBox2" target="_blank">品牌网站建设</a>,<a href="/jianshe#ym_websiteBox3" target="_blank">营销网站建设</a>,<a href="/jianshe#ym_websiteBox4" target="_blank">集团网站建设</a>,<a href="/jianshe#ym_websiteBox1" target="_blank">企业网站建设</a>,<a href="/jianshe#ym_websiteBox4_2" target="_blank">外贸网站建设</a>,<a href="/jianshe#ym_websiteBox4_3" target="_blank">响应式网站建设</a>,<a href="/weixin#item4" target="_blank">小程序开发</a>,<a href="/weixin" target="_blank">微信开发</a>,<a href="/jianshe#ym_websiteBox4_4" target="_blank">企业形象设计</a>,<a href="/jianshe#ym_websiteBox4_5" target="_blank">企业宣传视频</a>等服务,瑞达杰昌建站位于宣威市龙岗区大运软件小镇,瑞达杰昌建站拥有经验丰富的高级网站建设工程师和一流的网页高端设计人员,具备各种规模与类型网站建设的雄厚实力,在网站建设领域树立了自己独特的设计风格。 </div> <div class="friend-links"> <h6 class="clearfix"> <span class="tilte">友情链接</span> <a class="exchagne" href="http://wpa.qq.com/msgrd?v=3&uin=631063699&site=qq&menu=yes">交换友情链接</a> </h6> <div class="link-list clearfix"> <div class="link-slider"> <a href="https://www.cdcxhl.com/ruanwen/yingxiao" title="软文营销" target="_blank">软文营销</a>   <a href="http://www.ybfdjzy.com/" title="宜宾柴油发电机维修" target="_blank">宜宾柴油发电机维修</a>   <a href="http://www.gyjierui.cn/" title="南充建网站" target="_blank">南充建网站</a>   <a href="http://www.qiaobapo.com/" title="成都工商注册公司" target="_blank">成都工商注册公司</a>   <a href="http://www.digifinexcn.com/" title="固迪佳新材料" target="_blank">固迪佳新材料</a>   <a href="http://www.gtftapa.com/" title="成都网站建设公司" target="_blank">成都网站建设公司</a>   <a href="http://www.zycyfdj.com/" title="资阳发电机组租用" target="_blank">资阳发电机组租用</a>   <a href="http://www.yaancyfdj.com/" title="雅安发电机" target="_blank">雅安发电机</a>   <a href="http://www.bjruijie.cn/" title="产品质量认证" target="_blank">产品质量认证</a>   <a href="http://www.scwlttbz.com/" title="成都展厅设计" target="_blank">成都展厅设计</a>    </div> </div> </div> </div> <div class="footer-b"> <div class="f-box"> <ul> <li><a href="/jianshe#ym_websiteBox6" target="_blank">服务流程</a></li> <li><a href="/jianshe#ym_websiteBox8" target="_blank">售后服务</a></li> <li><a href="/about/" target="_blank">联系我们</a></li> <li><a href="https://www.cdxwcx.com/pay/" target="_blank">付款方式</a></li> <li><a href="https://www.cdcxhl.com/menu.html" target="_blank">网站地图</a></li> <li><a href="#" target="_blank">sitemap</a></li> <li> <p> <script data-cfasync="false" src="/Public/Home/js/email-decode.min.js"></script> </p> </li> <div style="clear:both;"></div> </ul> <p class="copy">Copyright © 2025 青羊区瑞达杰昌互联网信息服务工作室(个体工商户) 宣威建站 All Rights Reserved   <a href="https://beian.miit.gov.cn/" target="_blank" rel="nofollow">蜀ICP备2025133229号-6</a> <a style="display:none" target="_blank" href="###"><img style="vertical-align:middle" border="0" src="" width="65" height="25" /></a> </p> <div style="clear:both;"></div> </div> </div> <div class="sj_footer"> <div class="f-box"> <ul> <li><a href="/jianshe" target="_blank">网站建设</a></li> <li><a href="/jianshe#ym_websiteBox6" target="_blank">服务流程</a></li> <li><a href="/jianshe#ym_websiteBox8" target="_blank">售后服务</a></li> <li><a href="https://www.cdxwcx.com/pay/" target="_blank">付款方式</a></li> <li><a href="/about/" target="_blank">关于我们</a></li> <li><a href="https://www.cdcxhl.com/menu.html" target="_blank">网站地图</a></li> <div style="clear:both;"></div> </ul> <p class="copy">Copyright © 2025 青羊区瑞达杰昌互联网信息服务工作室(个体工商户) 宣威建站</p> <p class="copy"> <a href="https://beian.miit.gov.cn/" target="_blank" rel="nofollow">蜀ICP备2025133229号-6</a>  <a href="###" target="_blank"><img src="/Public/Home/images/govicon.gif" width="20" height="28" border="0" style="border-width:0px;border:hidden; border:none;"></a></p> <div style="clear:both;"></div> </div> </div> </div> <script type='text/javascript' src='/Public/Home/js/qqkefu.js'></script> <div class="qqkefu"> <ul> <li class="qq_czaa" id="130"><b class="a"></b>135-1821-9792</li> <li class="qq_czaa" id="130"><a href="tencent://message/?uin=1683211881"><b class="b"></b>业务咨询QQ</a></li> <li class="qq_czaa" id="130"><a href="javascript:showDiv()"><b class="f"></b>提交合作意向表</a></li> <li class="qq_czb"> <b class="c"></b> <div class="erweima"> <p><img src="/Public/Home/images/right_erweima.png"></p> </div> </li> <li class="top"><span></span></li> </ul> </div> <div id="popDiv" class="mydiv" style="display:none;"> <a class="mydiv_clk" href="javascript:closeDiv()">X</a> <div class="mydiv_list"> <div class="c_f_title"><span class="c_f_t">合作意向表</span></div> <div class="c_f_con"> <form id="form1" name="form1" class="mess_form" method="post" action="/post_order"> <input name='enews' type='hidden' value='AddFeedback'> <input name="bid" value="1" type="hidden"> <input type="hidden" name="ecmsfrom" value="9"> <input type="hidden" name='title' value="客户提交需求"> <li class="c_n"><span>公司名称</span> <dl><input name='gsname' id='gsname' type="text"></dl> </li> <li class="c_n"><span>邮箱</span> <dl><input name='gemail' id='gemail' type="text"></dl> </li> <li class="c_n xmm"> <div class="xmm_01"><span>姓名</span> <dl class="c_n_i"><input name='name' id='name' type="text"></dl> </div> <div class="xmm_01"><span style="text-align:center">电话</span> <dl class="c_n_i"><input name="tel" type="text"></dl> </div> </li> <li class="c_tser">您需要的服务</li> <li class="clearfix"> <dd><label><input type="radio" name='hobby' id='hobby' value="高端网站建设"><span>高端网站建设</span></label></dd> <dd><label><input type="radio" name='hobby' id='hobby' value="我需要做微信营销"><span>我需要做微信营销</span></label></dd> <dd><label><input type="radio" name='hobby' id='hobby' value="要找长期合作,需要年度服务"><span>要找长期合作,需要年度服务</span></label></dd> <dd><label><input type="radio" name='hobby' id='hobby' value="我需要做购物商城"><span>我需要做购物商城</span></label></dd> <dd><label><input type="radio" name='hobby' id='hobby' value="我需要网站改版"><span>我需要网站改版</span></label></dd> <dd><label><input type="radio" name='hobby' id='hobby' value="其他"><span>其他</span></label></dd> </li> <li class="c_tser">您关注的地方</li> <li class="clearfix"> <dd><label><input type="radio" name='hobby2' id='hobby2' value="对功能要求比较高"><span>对功能要求比较高</span></label></dd> <dd><label><input type="radio" name='hobby2' id='hobby2' value="对设计创意要求比较高"><span>对设计创意要求比较高</span></label></dd> <dd><label><input type="radio" name='hobby2' id='hobby2' value="需要可以购物支付"><span>需要可以购物支付</span></label></dd> <dd><label><input type="radio" name='hobby2' id='hobby2' value="搜索引擎排名"><span>搜索引擎排名</span></label></dd> </li> <li class="c_tser">预算</li> <li class="clearfix clearfix2"> <dd><label><input type="radio" name='hobby3' id='hobby3' value="一万以内"><span>一万以内</span></label> </dd> <dd><label><input type="radio" name='hobby3' id='hobby3' value="1-3万"><span>1-3万</span></label> </dd> <dd><label><input type="radio" name='hobby3' id='hobby3' value="3-5万"><span>3-5万</span></label> </dd> <dd><label><input type="radio" name='hobby3' id='hobby3' value="5万以上"><span>5万以上</span></label> </dd> <dd><label><input type="radio" name='hobby3' id='hobby3' value="需招投标"><span>需招投标</span></label> </dd> </li> <li class="c_n" style="border-top:1px solid #eee; padding-top:10px"><span>验证码</span> <dl class="c_n_i yzmm"><input type="text" name='code' id='code' value=""></dl><span style="text-align:center"><img src="/Public/Home/images/1661eb19783442c38063791555cd0d80.gif" onclick="this.src=this.src + '?'" width="100" height="40"></span> </li> <li class="clearfix"> <dd class="submit"><input name='submit' type="submit" value="提交需求"></dd> </li> </form> </div> </div> </div> <div id="bg" class="bg" style="display:none;"></div> <div id='popIframe' class='popIframe' frameborder='0'></div> <script> //提交需求选项 $(document).ready(function (e) { $(".mess_form").submit(function () { if ($("#gsname").val() == "") { alert("请填写您的公司名称!"); $("#gsname").focus(); return false; } if ($("#gemail").val() == "") { alert("请填写您的邮箱"); $("#gemail").focus(); return false; } if ($("#name").val() == "") { alert("请填写您的姓名!"); $("#name").focus(); return false; } if ($("#tel").val() == "") { alert("请填写您的电话!"); $("#tel").focus(); return false; } if ($("#hobby").val() == "") { alert("请选择您需要的服务!"); $("#hobby").focus(); return false; } if ($("#hobby2").val() == "") { alert("请选择您关注的地方!"); $("#hobby2").focus(); return false; } if ($("#hobby3").val() == "") { alert("请选择您的预算!"); $("#hobby3").focus(); return false; } if ($("#code").val() == "") { alert("请填写正确的验证码!"); $("#code").focus(); return false; } }); }); </script> <script language="javascript" type="text/javascript"> //提交需求窗口 function showDiv() { document.getElementById('popDiv').style.display = 'block'; document.getElementById('popIframe').style.display = 'block'; document.getElementById('bg').style.display = 'block'; } function closeDiv() { document.getElementById('popDiv').style.display = 'none'; document.getElementById('bg').style.display = 'none'; document.getElementById('popIframe').style.display = 'none'; } </script> <script type="text/javascript" src="/Public/Home/js/scrolltopcontrol.js"></script> <script type="text/javascript" src="/Public/Home/js/su_new.js"></script> </body> </html> <script> $(".con img").each(function(){ var src = $(this).attr("src"); //获取图片地址 var str=new RegExp("http"); var result=str.test(src); if(result==false){ var url = "https://www.cdcxhl.com"+src; //绝对路径 $(this).attr("src",url); } }); window.onload=function(){ document.oncontextmenu=function(){ return false; } } </script>