/** * dict.class.php 采集百度詞典翻譯內(nèi)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; //顯示的條數(shù) private static $num = 10; public function __construct(){} /** * 公用返回百度采集數(shù)據(jù)的方法 * @param string 英文單詞 * retun array( * symbol" => 音標(biāo) * "pro" => 發(fā)音 * "example"=> 例句 * "explain"=> 簡(jiǎn)明釋義 * "synonym"=> 同反義詞 * "phrase" => 短語(yǔ)數(shù)組 * ) * */ public function content($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, //音標(biāo) "pro" => $pro, //發(fā)音 "example"=> $example, //例句 "explain"=> $explain, //簡(jiǎn)明釋義 "synonym"=> $synonym, //同反義詞 "phrase" => $phrase //短語(yǔ)數(shù)組 ); return $result; } /** * 遠(yuǎn)程獲取百度翻譯內(nèi)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; } /** * 獲取百度翻譯發(fā)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] ); } /** * 獲取百度翻譯發(fā)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] ); } /** * 獲取百度翻譯例句 * return array() 多維數(shù)組 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; } /** * 獲取簡(jiǎn)明釋義 * return array (x => "詞性",b => "附屬") * **/ private function getExplain(){ $data = $this -> getContent(); preg_match_all("/id\=\"en\-simple\-means\"\>(.*)\<div(\s+)class\=\"source\"\>/Us",$data,$explain); $r_data = $explain[1][0]; preg_match_all("/\<p\>\<strong\>(?P<adj>.*)\<\/strong\>\<span\>(?P<name>.*)\<\/span\>\<\/p\>/Us", $r_data, $a_data); preg_match_all("/\<span\>(?P<tag>[^\>]+)\:\<a(\s+)href\=\"(.*)\"\>(?P<word>.*)\<\/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; } /** * 獲取同義詞 * return array(0 => "同義詞", 1 => "反義詞") 一般為多維數(shù)組 * */ private function getSynonym(){ $data = $this -> getContent(); preg_match_all("/id=\"en\-syn\-ant\"\>(.*)<div(\s+)class\=\"source\">/Us",$data,$synonym); $content = $synonym[1][0]; $data1 = explode("</dl>", $content); $result = array(); $data2 = array(); foreach ($data1 as $key => $value) { preg_match_all("/\<strong\>(?P<adj>.*)\ \;\<\/strong\>\<\/div\>\<div(\s+)class\=\"syn\-ant\-list\"\>\<ul\>(?<content>.*)\<\/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("/\<li\>\<p\>(?P<title>.*)\<\/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; } /** * 獲取短語(yǔ)詞組 * return array (key => value) 一維或者多維數(shù)組 * */ 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; } /** * 將數(shù)組轉(zhuǎn)換為字符串 * * @param array $data 數(shù)組 * @param bool $isformdata 如果為0,則不使用new_stripslashes處理,可選參數(shù),默認(rèn)為1 * @return string 返回字符串,如果,data為空,則返回空 */ private function array2string($data, $isformdata = 1) { if($data == '') return ''; if($isformdata) $data = $this->new_stripslashes($data); return addslashes(var_export($data, TRUE)); } /** * 返回經(jīng)stripslashes處理過(guò)的字符串或數(shù)組 * @param $string 需要處理的字符串或數(shù)組codego.net/25/1/1/ * @return mixed */ private function new_stripslashes($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();
創(chuàng)新互聯(lián)建站專注于嘉魚網(wǎng)站建設(shè)服務(wù)及定制,我們擁有豐富的企業(yè)做網(wǎng)站經(jīng)驗(yàn)。 熱誠(chéng)為您提供嘉魚營(yíng)銷型網(wǎng)站建設(shè),嘉魚網(wǎng)站制作、嘉魚網(wǎng)頁(yè)設(shè)計(jì)、嘉魚網(wǎng)站官網(wǎng)定制、小程序設(shè)計(jì)服務(wù),打造嘉魚網(wǎng)絡(luò)公司原創(chuàng)品牌,更為您提供嘉魚網(wǎng)站排名全網(wǎng)營(yíng)銷落地服務(wù)。
網(wǎng)站名稱:php查詞采集器
當(dāng)前鏈接:http://muchs.cn/article20/pihpjo.html
成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián),為您提供App設(shè)計(jì)、關(guān)鍵詞優(yōu)化、用戶體驗(yàn)、自適應(yīng)網(wǎng)站、網(wǎng)站維護(hù)、網(wǎng)頁(yè)設(shè)計(jì)公司
聲明:本網(wǎng)站發(fā)布的內(nèi)容(圖片、視頻和文字)以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主,如果涉及侵權(quán)請(qǐng)盡快告知,我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如需處理請(qǐng)聯(lián)系客服。電話:028-86922220;郵箱:631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載,或轉(zhuǎn)載時(shí)需注明來(lái)源: 創(chuàng)新互聯(lián)