├── 2.png
├── README.md
├── dictdemo.php
└── dict.class.php
/2.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/widuu/baidu_dict/HEAD/2.png
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 |
2 | ##百度词典查词采集器（PHP版本）
3 |
4 | 
5 |
6 | 自己写的百度词典dict.baidu.com 采集翻译用的，你自己也可以自己定制，其中包含几个文件：
7 |
8 | 1. word_data.php 13.5W单词库
9 |
10 | 2. dict.class.php 采集类
11 |
12 | 3. dictdemo.php 简单的采集案例
13 |
14 | ###使用方法
15 |
16 | 只要把文件放到你的指定的目录下即可，然后运行dictdemo.php可以查看效果，入库的流程请自己编写
17 |
18 | `dict.class.php`中有`array2string()`的方法，来把数组转化成字符串方便入库。
19 |
20 |
21 |
22 |
23 |
--------------------------------------------------------------------------------
/dictdemo.php:
--------------------------------------------------------------------------------
1 | $val) $string[$key] = new_stripslashes($val);
31 | return $string;
32 | }
33 |
34 | $dbname = "dict_word";
35 | $hostname = "localhost";
36 | $username = "root";
37 | $password = "dgj99349";
38 | $conn = mysql_connect($hostname,$username,$password);
39 | mysql_select_db($dbname,$conn);
40 | mysql_query("set names utf8");
41 | $url = "http://www.test.com/"; //你放dictdemo.php的网站地址
42 | ignore_user_abort();
43 | set_time_limit(0);
44 | $filename = "./dict_num.txt";
45 | include("dict.class.php");
46 | $data = include("word_data.php");
47 | $dict = new dict();
48 | if (isset($_GET["num"])){
49 | $key = intval($_GET["num"]);
50 | $word = $data[$key];
51 | $result = $dict -> content($word);
52 | if(empty($result["symbol"]["en"])){
53 | $result = file_put_contents("noword.txt", $word."\n", FILE_APPEND); //有的个性的单词啥都没有 写入文件中
54 | }else{
55 | $symbol = array2string(array_filter($result['symbol']));
56 | $pro = array2string(array_filter($result['pro']));
57 | $example = array2string(array_filter($result['example']));
58 | $explain = array2string(array_filter($result['explain']));
59 | $synonym = array2string(array_filter($result['synonym']));
60 | $phrase = array2string(array_filter($result['phrase']));
61 | echo "";
62 | print_r($symbol);
63 | print_r($pro);
64 | print_r($example);
65 | print_r($explain);
66 | print_r($synonym);
67 | print_r($phrase);
68 | echo "
";
69 | //mysql_query("insert into dict_word (`word`,`symbol`,`pro`,`example`,`explain`,`synonym`,`phrase`) values ('{$word}')")
70 |
71 | //your 逻辑采集入库
72 | }
73 | $num = $key+1;
74 | file_put_contents($filename,$num);
75 | }
76 |
77 | if(file_exists($filename)){
78 | $key = file_get_contents($filename);
79 | }else{
80 | $fp =fopen("$filename", "w+");
81 | }
82 |
83 | $key = empty($key) ? 0 : intval($key);
84 |
85 | echo "";
88 |
89 |
90 |
91 |
--------------------------------------------------------------------------------
/dict.class.php:
--------------------------------------------------------------------------------
1 | 音标
28 | * "pro" => 发音
29 | * "example"=> 例句
30 | * "explain"=> 简明释义
31 | * "synonym"=> 同反义词
32 | * "phrase" => 短语数组
33 | * )
34 | *
35 | */
36 |
37 | public function content($word){
38 | $this -> word = $word;
39 | $symbol = $this -> Pronounced();
40 | $pro = $this->getSay();
41 | $example = $this -> getExample();
42 | $explain = $this -> getExplain();
43 | $synonym = $this -> getSynonym();
44 | $phrase = $this -> getPhrase();
45 | $result = array(
46 | "symbol" => $symbol, //音标
47 | "pro" => $pro, //发音
48 | "example"=> $example, //例句
49 | "explain"=> $explain, //简明释义
50 | "synonym"=> $synonym, //同反义词
51 | "phrase" => $phrase //短语数组
52 | );
53 | return $result;
54 | }
55 |
56 |
57 | /**
58 | * 远程获取百度翻译内容
59 | * get function curl
60 | * retun string
61 | *
62 | */
63 |
64 | private function getContent(){
65 | $useragent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0";
66 | $ch = curl_init();
67 | $url = "http://dict.baidu.com/s?wd=".$this->word;
68 | curl_setopt($ch, CURLOPT_URL, $url);
69 | curl_setopt($ch, CURLOPT_USERAGENT,$useragent);
70 | curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);
71 | curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
72 | curl_setopt($ch, CURLOPT_HTTPGET, 1);
73 | curl_setopt($ch, CURLOPT_AUTOREFERER,1);
74 | curl_setopt($ch, CURLOPT_HEADER, 0);
75 | curl_setopt($ch, CURLOPT_TIMEOUT, 30);
76 | $result = curl_exec($ch);
77 | if (curl_errno($curl)) {
78 | echo 'Errno'.curl_error($curl);
79 | }
80 | curl_close($ch);
81 | return $result;
82 | }
83 |
84 |
85 | /**
86 | * 获取百度翻译发音
87 | * retun array(英，美)
88 | *
89 | */
90 |
91 | private function Pronounced(){
92 | $data = $this -> getContent();
93 | preg_match_all("/\"EN\-US\"\>(.*)\<\/b\>/Ui",$data,$pronounced);
94 | return array(
95 | 'en' => $pronounced[1][0],
96 | 'us' => $pronounced[1][1]
97 | );
98 | }
99 |
100 | /**
101 | * 获取百度翻译发音
102 | * return array(英，美)
103 | *
104 | */
105 |
106 | private function getSay(){
107 | $data = $this -> getContent();
108 | preg_match_all("/url=\"(.*)\"/Ui",$data,$pronounced);
109 | return array(
110 | 'en' => $pronounced[1][0],
111 | 'us' => $pronounced[1][1]
112 | );
113 | }
114 |
115 | /**
116 | * 获取百度翻译例句
117 | * return array() 多维数组 例句
118 | *
119 | */
120 |
121 | private function getExample(){
122 | $str = "";
123 | $data = $this -> getContent();
124 | preg_match_all("/var example_data = (.*)\]\;/Us",$data,$example);
125 | $data1 = "[[[".ltrim($example[1][0],"[");
126 | $data2 = explode("[[[",$data1);
127 | $num = count(array_filter($data2));
128 | foreach($data2 as $key => $value){
129 | $data3 = explode("[[","[[".$value);
130 | foreach ($data3 as $k => $v) {
131 | preg_match_all("/\[\"(.*)\",/Us","[".$v, $match);
132 | if(!empty($match[1])){
133 | $str .= implode($match[1]," ")."@";
134 | }
135 | }
136 | }
137 | $data4 = trim($str,"@");
138 | $data5 = explode("@", $data4);
139 | $result = array_chunk($data5, 2);
140 | return $result;
141 | }
142 |
143 | /**
144 | * 获取简明释义
145 | * return array (x => "词性"，b => "附属")
146 | *
147 | **/
148 |
149 | private function getExplain(){
150 | $data = $this -> getContent();
151 | preg_match_all("/id\=\"en\-simple\-means\"\>(.*)\/Us",$data,$explain);
152 | $r_data = $explain[1][0];
153 | preg_match_all("/\\(?P.*)\<\/strong\>\(?P.*)\<\/span\>\<\/p\>/Us", $r_data, $a_data);
154 | preg_match_all("/\(?P[^\>]+)\：\(?P.*)\<\/a\>\<\/span\>/Us", $r_data, $b_data);
155 |
156 | $result = array();
157 | foreach ($a_data["adj"] as $key => $value) {
158 | $result[$value] = $a_data["name"][$key];
159 | }
160 |
161 | $word_b = array();
162 | foreach ($b_data["tag"] as $key => $value) {
163 | $word_b[$value] = strip_tags($b_data["word"][$key]);
164 | }
165 |
166 | $result_data = array("x" => $result,"b" => $word_b);
167 |
168 | return $result_data;
169 | }
170 |
171 |
172 |
173 |
174 | /**
175 | * 获取百科释义
176 | * return string
177 | *
178 | */
179 |
180 | // private function getBaike(){
181 | // $data = $this -> getContent();
182 | // preg_match_all("/id\=\"en\-baike\-mean\"\>(.*)<\/div>/Us",$data,$baike);
183 | // return strip_tags($baike[1][0]);
184 | // }
185 |
186 | /**
187 | * 获取同义词
188 | * return array(0 => "同义词", 1 => "反义词") 一般为多维数组
189 | *
190 | */
191 |
192 | private function getSynonym(){
193 | $data = $this -> getContent();
194 | preg_match_all("/id=\"en\-syn\-ant\"\>(.*)/Us",$data,$synonym);
195 | $content = $synonym[1][0];
196 | $data1 = explode("", $content);
197 | $result = array();
198 | $data2 = array();
199 | foreach ($data1 as $key => $value) {
200 | preg_match_all("/\(?P.*)\ \;\<\/strong\>\<\/div\>\\(?.*)\<\/ul\>/Us", $value, $r_data);
201 | $data2[$key]["adj"] = $r_data["adj"];
202 | $data2[$key]["content"] = $r_data["content"];
203 | }
204 |
205 | foreach ($data2 as $key => $value) {
206 | foreach ($value["content"] as $k => $v) {
207 | if(!empty($v)){
208 | preg_match_all("/\\(?P.*)\<\/p\>(?P<value>.*)\<\/li>/Us", $v, $v_data);
209 | foreach ($v_data['title'] as $m => $d) {
210 | $data = strip_tags(preg_replace("<</a>>"," ", $v_data["value"][$m]));
211 | $result[$key][$value["adj"][$k]][$d] = $data;
212 | }
213 | }
214 | }
215 | }
216 | return $result;
217 | }
218 |
219 | /**
220 | * 获取柯林斯高阶英汉词典
221 | * return string
222 | *
223 | */
224 |
225 | // private function getCollins(){
226 | // $data = $this -> getContent();
227 | // preg_match_all("/id\=\"en\-collins\"\>(.*)\<div class\=\"source\"\>/Us",$data,$collins);
228 | // return strip_tags($collins[1][0]);
229 | // }
230 |
231 | /**
232 | * 获取短语词组
233 | * return array (key => value) 一维或者多维数组
234 | *
235 | */
236 |
237 | private function getPhrase(){
238 | $num = self::$num;
239 | $data = $this -> getContent();
240 | preg_match_all("/id=\"en\-phrase\"\>(.*)\<div class\=\"source\"\>/Us",$data,$phrase);
241 | $data = explode("</dd>",$phrase[1][0]);
242 | $data1 = array_slice($data,0,$num);
243 | $result = array();
244 | foreach ($data1 as $key => $value) {
245 | $data2 = explode("</p>", $value);
246 | $n = count($data2);
247 | if($n<=3){
248 | $result[str_replace(" ","",strip_tags($data2[0]))] = strip_tags($data2[1]);
249 | }else{
250 | $data3 = array_slice($data2,0,$n-1);
251 | $data4 = array_slice($data2,0,2);
252 | $res = array_diff($data3,$data4);
253 | $data5 = array_chunk($res,2);
254 | $key_value = trim(str_replace(" ","",strip_tags($data4[0])));
255 | $result[$key_value] = strip_tags($data4[1]);
256 | foreach ($data5 as $key => $value) {
257 | foreach ($value as $k => $v) {
258 | $value[$k] = strip_tags($v);
259 | }
260 | $array = array($result[$key_value],$value);
261 | if (array_key_exists($key_value, $result)){
262 | $result[$key_value] = $array;
263 | }
264 | }
265 |
266 | }
267 | }
268 | return $result;
269 | }
270 |
271 | /**
272 | * 将数组转换为字符串
273 | *
274 | * @param array $data 数组
275 | * @param bool $isformdata 如果为0，则不使用new_stripslashes处理，可选参数，默认为1
276 | * @return string 返回字符串，如果，data为空，则返回空
277 | */
278 | private function array2string($data, $isformdata = 1) {
279 | if($data == '') return '';
280 | if($isformdata) $data = $this->new_stripslashes($data);
281 | return addslashes(var_export($data, TRUE));
282 | }
283 |
284 | /**
285 | * 返回经stripslashes处理过的字符串或数组
286 | * @param $string 需要处理的字符串或数组
287 | * @return mixed
288 | */
289 | private function new_stripslashes($string) {
290 | if(!is_array($string)) return stripslashes($string);
291 | foreach($string as $key => $val) $string[$key] = $this->new_stripslashes($val);
292 | return $string;
293 | }
294 |
295 | }
296 |
297 | // $word = new dict("express");
298 | // $word ->content();
--------------------------------------------------------------------------------