Heim  >  Artikel  >  Backend-Entwicklung  >  PHP制作百度词典查词采集器_PHP教程

PHP制作百度词典查词采集器_PHP教程

WBOY
WBOYOriginal
2016-07-13 10:08:311249Durchsuche

PHP制作百度词典查词采集器

 这篇文章主要介绍了PHP制作百度词典查词采集器的相关资料,需要的朋友可以参考下

 

 

百度dict 采集样本

写的采集百度dict词典翻译后的所有结果数据,当然附带了13.5w单词库和采集简单的案例,这里我把写出的主要类dict.class.php放出来,项目地址http://github.com/widuu/baidu_dict,有需要的直接fork就可以了~么么哒,这东西用的人很少,所以有用的兄弟拿走了哈~

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

/**

* 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\"\>(.*)\/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.*)\\(?P.*)\\/Us", $r_data, $a_data);

preg_match_all("/\(?P[^\>]+)\:\(?P.*)\\/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.*)\ \;\\\

\
    (?.*)\/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<value>.*)\/Us", $v, $v_data); <p>foreach ($v_data['title'] as $m => $d) {</p> <p>$data = strip_tags(preg_replace(">"," ", $v_data["value"][$m]));</p> <p>$result[$key][$value["adj"][$k]][$d] = $data;</p> <p>}</p> <p>}</p> <p>}</p> <p>}</p> <p>return $result;</p> <p>}</p> <p> </p> <p>/**</p> <p>* 获取短语词组</p> <p>* return array (key => value) 一维或者多维数组</p> <p>*</p> <p>*/</p> <p> </p> <p>private function getPhrase(){</p> <p>$num = self::$num;</p> <p>$data = $this -> getContent();</p> <p>preg_match_all("/id=\"en\-phrase\"\>(.*)\</p> <div class>/Us",$data,$phrase); <p>$data = explode("",$phrase[1][0]);</p> <p>$data1 = array_slice($data,0,$num);</p> <p>$result = array();</p> <p>foreach ($data1 as $key => $value) {</p> <p>$data2 = explode("</p>", $value); <p>$n = count($data2);</p> <p>if($n </p> <p>$result[str_replace(" ","",strip_tags($data2[0]))] = strip_tags($data2[1]);</p> <p>}else{</p> <p>$data3 = array_slice($data2,0,$n-1);</p> <p>$data4 = array_slice($data2,0,2);</p> <p>$res = array_diff($data3,$data4);</p> <p>$data5 = array_chunk($res,2);</p> <p>$key_value = trim(str_replace(" ","",strip_tags($data4[0])));</p> <p>$result[$key_value] = strip_tags($data4[1]);</p> <p>foreach ($data5 as $key => $value) {</p> <p>foreach ($value as $k => $v) {</p> <p>$value[$k] = strip_tags($v);</p> <p>}</p> <p>$array = array($result[$key_value],$value);</p> <p>if (array_key_exists($key_value, $result)){</p> <p>$result[$key_value] = $array;</p> <p>}</p> <p>}</p> <p> </p> <p>}</p> <p>}</p> <p>return $result;</p> <p>}</p> <p> </p> <p>/**</p> <p>* 将数组转换为字符串</p> <p>*</p> <p>* @param array $data 数组</p> <p>* @param bool $isformdata 如果为0,则不使用new_stripslashes处理,可选参数,默认为1</p> <p>* @return string 返回字符串,如果,data为空,则返回空</p> <p>*/</p> <p>private function array2string($data, $isformdata = 1) {</p> <p>if($data == '') return '';</p> <p>if($isformdata) $data = $this->new_stripslashes($data);</p> <p>return addslashes(var_export($data, TRUE));</p> <p>}</p> <p> </p> <p>/**</p> <p>* 返回经stripslashes处理过的字符串或数组</p> <p>* @param $string 需要处理的字符串或数组</p> <p>* @return mixed</p> <p>*/</p> <p>private function new_stripslashes($string) {</p> <p>if(!is_array($string)) return stripslashes($string);</p> <p>foreach($string as $key => $val) $string[$key] = $this->new_stripslashes($val);</p> <p>return $string;</p> <p>}</p> <p> </p> <p>}</p> <p> </p> <p>// $word = new dict("express");</p> <p>// $word ->content();</p> </div></value>

以上就是本文的全部内容了,非常实用的功能,希望小伙伴们能够喜欢。

www.bkjia.comtruehttp://www.bkjia.com/PHPjc/950763.htmlTechArticlePHP制作百度词典查词采集器 这篇文章主要介绍了PHP制作百度词典查词采集器的相关资料,需要的朋友可以参考下 百度dict 采集样本 写的采集...
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