PageRenderTime 51ms CodeModel.GetById 20ms RepoModel.GetById 0ms app.codeStats 1ms

/lib/VideoUrlParser.php

https://github.com/GavinFoo/AniHere
PHP | 571 lines | 437 code | 31 blank | 103 comment | 21 complexity | c9c4c1ee003713ff8f5865283645bd09 MD5 | raw file
    

  1. <?php
    2. 

  2. /**
    3. 

  3.  * Video 
    4. 

  4.  * 
    5. 

  5.  * @package 
    6. 

  6.  * @version 1.2
    7. 

  7.  * @copyright 2005-2011 HDJ.ME 
    8. 

  8.  * @author Dijia Huang <huangdijia@gmail.com> 
    9. 

  9.  * @license PHP Version 3.0 {@link http://www.php.net/license/3_0.txt}
    10. 

  10.  *
    11. 

  11.  * Usage
    12. 

  12.  * require_once "VideoUrlParser.class.php";
    13. 

  13.  * $urls[] = "http://v.youku.com/v_show/id_XMjI4MDM4NDc2.html";
    14. 

  14.  * $urls[] = "http://www.tudou.com/playlist/p/l13087099.html";
    15. 

  15.  * $urls[] = "http://www.tudou.com/programs/view/ufg-A3tlcxk/";
    16. 

  16.  * $urls[] = "http://v.ku6.com/special/show_4926690/Klze2mhMeSK6g05X.html";
    17. 

  17.  * $urls[] = "http://www.56.com/u68/v_NjI2NTkxMzc.html";
    18. 

  18.  * $urls[] = "http://www.letv.com/ptv/vplay/1168109.html";
    19. 

  19.  * $urls[] = "http://video.sina.com.cn/v/b/46909166-1290055681.html";
    20. 

  20.  *
    21. 

  21.  * foreach($urls as $url){
    22. 

  22.  *     $info = VideoUrlParser::parse($url);
    23. 

  23.  *     //var_dump($info);
    24. 

  24.  *     echo "<a href='{$info['url']}' target='_new'>{$info['title']}</a>";
    25. 

  25.  *     echo "<br />";
    26. 

  26.  *     echo $info['object'];
    27. 

  27.  *     echo "<br />";
    28. 

  28.  * }
    29. 

  29.  *
    30. 

  30.  *
    31. 

  31.  *
    32. 

  32.  * //优酷
    33. 

  33.  * http://v.youku.com/v_show/id_XMjU0NjY4OTEy.html
    34. 

  34.  * <embed src="http://player.youku.com/player.php/sid/XMjU0NjY4OTEy/v.swf" quality="high" width="480" height="400" align="middle" allowScriptAccess="sameDomain" type="application/x-shockwave-flash"></embed>
    35. 

  35.  * 
    36. 

  36.  * //酷六
    37. 

  37.  * http://v.ku6.com/special/show_3917484/x0BMXAbgZdQS6FqN.html
    38. 

  38.  * <embed src="http://player.ku6.com/refer/x0BMXAbgZdQS6FqN/v.swf" quality="high" width="480" height="400" align="middle" allowScriptAccess="always" allowfullscreen="true" type="application/x-shockwave-flash"></embed>
    39. 

  39.  * 
    40. 

  40.  * //土豆
    41. 

  41.  * http://www.tudou.com/playlist/p/a65929.html?iid=74905844
    42. 

  42.  * <embed src="http://www.tudou.com/l/A_0urj-Geec/&iid=74905844/v.swf" type="application/x-shockwave-flash" allowscriptaccess="always" allowfullscreen="true" wmode="opaque" width="480" height="400"></embed>
    43. 

  43.  * 
    44. 

  44.  * //56
    45. 

  45.  * http://www.56.com/u98/v_NTkyODY2NTU.html
    46. 

  46.  * <embed src="http://player.56.com/v_NTkyODY2NTU.swf"  type="application/x-shockwave-flash" width="480" height="405" allowNetworking="all" allowScriptAccess="always"></embed>
    47. 

  47.  * 
    48. 

  48.  * //新浪播客
    49. 

  49.  * http://video.sina.com.cn/v/b/46909166-1290055681.html
    50. 

  50.  * <embed src="http://you.video.sina.com.cn/api/sinawebApi/outplayrefer.php/vid=46909166_1290055681_b0K1GHEwDWbK+l1lHz2stqkP7KQNt6nki2O0u1ehIwZYQ0/XM5GdZNQH6SjQBtkEqDhAQJ42dfcn0Rs/s.swf" pluginspage="http://www.macromedia.com/go/getflashplayer" type="application/x-shockwave-flash" name="ssss" allowFullScreen="true" allowScriptAccess="always" width="480" height="370"></embed>
    51. 

  51.  * 
    52. 

  52.  * //乐视
    53. 

  53.  * http://www.letv.com/ptv/vplay/1168109.html
    54. 

  54.  * <embed src="http://i3.imgs.letv.com/player/swfPlayer.swf?id=1168109&host=app.letv.com&vstatus=1&AP=1&logoMask=0&isShowP2p=0&autoplay=true" quality="high" scale="NO_SCALE" wmode="opaque" bgcolor="#000000" width="480" height="388" name="FLV_player" align="middle" allowscriptaccess="always" allowfullscreen="true" type="application/x-shockwave-flash" pluginspage="http://www.macromedia.com/go/getflashplayer">
    55. 

  55.  */
    56. 

  56. 

  57. class VideoUrlParser
    58. 

  58. {
    59. 

  59.     const USER_AGENT = "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.10 (KHTML, like Gecko)
    60. 

  60.         Chrome/8.0.552.224 Safari/534.10";
    61. 

  61.     const CHECK_URL_VALID = "/(youku\.com|tudou\.com|ku6\.com|56\.com|letv\.com|video\.sina\.com\.cn|(my\.)?tv\.sohu\.com|v\.qq\.com)/";
    62. 

  62. 

  63.     /**
    64. 

  64.      * parse 
    65. 

  65.      * 
    66. 

  66.      * @param string $url 
    67. 

  67.      * @param mixed $createObject 
    68. 

  68.      * @static
    69. 

  69.      * @access public
    70. 

  70.      * @return void
    71. 

  71.      */
    72. 

  72.     static public function parse($url='', $createObject=true){
    73. 

  73.         $lowerurl = strtolower($url);
    74. 

  74.         preg_match(self::CHECK_URL_VALID, $lowerurl, $matches);
    75. 

  75.         if(!$matches) return false;
    76. 

  76. 

  77.         switch($matches[1]){
    78. 

  78.         case 'youku.com':
    79. 

  79.             $data = self::_parseYouku($url);
    80. 

  80.             break;
    81. 

  81.         case 'tudou.com':
    82. 

  82.             $data = self::_parseTudou($url);
    83. 

  83.             break;
    84. 

  84.         case 'ku6.com':
    85. 

  85.             $data = self::_parseKu6($url);
    86. 

  86.             break;
    87. 

  87.         case '56.com':
    88. 

  88.             $data = self::_parse56($url);
    89. 

  89.             break;
    90. 

  90.         case 'letv.com':
    91. 

  91.             $data = self::_parseLetv($url);
    92. 

  92.             break;
    93. 

  93.         case 'video.sina.com.cn':
    94. 

  94.             $data = self::_parseSina($url);
    95. 

  95.             break;
    96. 

  96.         case 'my.tv.sohu.com':
    97. 

  97.         case 'tv.sohu.com':
    98. 

  98.         case 'sohu.com':
    99. 

  99.             $data = self::_parseSohu($url);
    100. 

  100.             break;
    101. 

  101.         case 'v.qq.com':
    102. 

  102.             $data = self::_parseQq($url);
    103. 

  103.             break;
    104. 

  104.         default:
    105. 

  105.             $data = false;
    106. 

  106.         }
    107. 

  107. 

  108.         if($data && $createObject) $data['object'] = "<embed src=\"{$data['swf']}\" wmode=\"opaque\" quality=\"high\" width=\"750\" height=\"443\" align=\"middle\" allowNetworking=\"all\" allowScriptAccess=\"always\" type=\"application/x-shockwave-flash\"></embed>";
    109. 

  109.         return $data;
    110. 

  110.     }
    111. 

  111.     /**
    112. 

  112.      * 腾讯视频 
    113. 

  113.      * http://v.qq.com/cover/o/o9tab7nuu0q3esh.html?vid=97abu74o4w3_0
    114. 

  114.      * http://v.qq.com/play/97abu74o4w3.html
    115. 

  115.      * http://v.qq.com/cover/d/dtdqyd8g7xvoj0o.html
    116. 

  116.      * http://v.qq.com/cover/d/dtdqyd8g7xvoj0o/9SfqULsrtSb.html
    117. 

  117.      * http://imgcache.qq.com/tencentvideo_v1/player/TencentPlayer.swf?_v=20110829&vid=97abu74o4w3&autoplay=1&list=2&showcfg=1&tpid=23&title=%E7%AC%AC%E4%B8%80%E7%8E%B0%E5%9C%BA&adplay=1&cid=o9tab7nuu0q3esh
    118. 

  118.      */ 
    119. 

  119.     private function _parseQq($url){
    120. 

  120.         if(preg_match("/\/play\//", $url)){
    121. 

  121.             $html = self::_fget($url);
    122. 

  122.             preg_match("/url=[^\"]+/", $html, $matches);
    123. 

  123.             if(!$matches); return false;
    124. 

  124.             $url = $matches[0];
    125. 

  125.         }
    126. 

  126.         preg_match("/vid=([^\_]+)/", $url, $matches);
    127. 

  127.         $vid = $matches[1];
    128. 

  128.         $html = self::_fget($url);
    129. 

  129.         // query
    130. 

  130.         preg_match("/flashvars\s=\s\"([^;]+)/s", $html, $matches);
    131. 

  131.         $query = $matches[1];
    132. 

  132.         if(!$vid){
    133. 

  133.             preg_match("/vid\s?=\s?vid\s?\|\|\s?\"(\w+)\";/i", $html, $matches);
    134. 

  134.             $vid = $matches[1];
    135. 

  135.         }
    136. 

  136.         $query = str_replace('"+vid+"', $vid, $query);
    137. 

  137.         parse_str($query, $output);
    138. 

  138.         $data['img'] = "http://vpic.video.qq.com/{$$output['cid']}/{$vid}_1.jpg";
    139. 

  139.         $data['url'] = $url;
    140. 

  140.         $data['title'] = $output['title'];
    141. 

  141.         $data['swf'] = "http://imgcache.qq.com/tencentvideo_v1/player/TencentPlayer.swf?".$query;
    142. 

  142.         return $data;
    143. 

  143.     }
    144. 

  144.     
    145. 

  145. 

  146.     /**
    147. 

  147.      * 优酷网 
    148. 

  148.      * http://v.youku.com/v_show/id_XMjI4MDM4NDc2.html
    149. 

  149.      * http://player.youku.com/player.php/sid/XMjU0NjI2Njg4/v.swf
    150. 

  150.      */ 
    151. 

  151.     private function _parseYouku($url){
    152. 

  152.         preg_match("#id\_(\w+)#", $url, $matches);
    153. 

  153. 

  154.         if (empty($matches)){
    155. 

  155.             preg_match("#v_playlist\/#", $url, $mat);
    156. 

  156.             if(!$mat) return false;
    157. 

  157. 

  158.             $html = self::_fget($url);
    159. 

  159. 

  160.             preg_match("#videoId2\s*=\s*\'(\w+)\'#", $html, $matches);
    161. 

  161.             if(!$matches) return false;
    162. 

  162.         }
    163. 

  163. 

  164.         $link = "http://v.youku.com/player/getPlayList/VideoIDS/{$matches[1]}/timezone/+08/version/5/source/out?password=&ran=2513&n=3";
    165. 

  165.         $retval = self::_cget($link);
    166. 

  166.         if ($retval) {
    167. 

  167.             $json = json_decode($retval, true);
    168. 

  168. 

  169.             $data['img'] = $json['data'][0]['logo'];
    170. 

  170.             $data['title'] = $json['data'][0]['title'];
    171. 

  171.             $data['url'] = $url;
    172. 

  172.             $data['swf'] = "http://player.youku.com/player.php/sid/{$matches[1]}/v.swf";
    173. 

  173. 

  174.             return $data;
    175. 

  175.         } else {
    176. 

  176.             return false;
    177. 

  177.         }
    178. 

  178.     }
    179. 

  179. 

  180.     /**
    181. 

  181.      * 土豆网
    182. 

  182.      * http://www.tudou.com/programs/view/Wtt3FjiDxEE/
    183. 

  183.      * http://www.tudou.com/v/Wtt3FjiDxEE/v.swf
    184. 

  184.      * 
    185. 

  185.      * http://www.tudou.com/playlist/p/a65718.html?iid=74909603
    186. 

  186.      * http://www.tudou.com/l/G5BzgI4lAb8/&iid=74909603/v.swf
    187. 

  187.      */
    188. 

  188.     private function _parseTudou($url){
    189. 

  189.         preg_match("#view/([-\w]+)/#", $url, $matches);
    190. 

  190. 

  191.         if (empty($matches)) {
    192. 

  192.             if (strpos($url, "/playlist/") == false && strpos($url, "/listplay/") == false) return false;
    193. 

  193. 

  194.             if(strpos($url, 'iid=') !== false){
    195. 

  195.                 $quarr = explode("iid=", $lowerurl);
    196. 

  196.                 if (empty($quarr[1]))  return false;
    197. 

  197.             }elseif(preg_match("#p\/l(\d+).#", $lowerurl, $quarr)){
    198. 

  198.                 if (empty($quarr[1])) return false;
    199. 

  199.             }
    200. 

  200. 

  201.             $html = self::_fget($url);
    202. 

  202.             $html = iconv("GB2312", "UTF-8", $html);
    203. 

  203. 

  204.             preg_match("/lid_code\s=\slcode\s=\s[\'\"]([^\'\"]+)/s", $html, $matches);
    205. 

  205.             $icode = $matches[1];
    206. 

  206. 

  207.             preg_match("/iid\s=\s.*?\|\|\s(\d+)/sx", $html, $matches);
    208. 

  208.             $iid = $matches[1];
    209. 

  209. 

  210.             preg_match("/listData\s=\s(\[\{.*\}\])/sx", $html, $matches);
    211. 

  211.             
    212. 

  212.             $find = array("/\n/", '/\s/', "/:[^\d\"]\w+[^\,]*,/i", "/(\{|,)(\w+):/");
    213. 

  213.             $replace = array("", "", ':"",', '\\1"\\2":');
    214. 

  214.             $str = preg_replace($find, $replace, $matches[1]);
    215. 

  215.             //var_dump($str);
    216. 

  216.             $json = json_decode($str);
    217. 

  217.             //var_dump($json);exit;
    218. 

  218.             if(is_array($json) || is_object($json) && !empty($json)){
    219. 

  219.                 foreach ($json as $val) {
    220. 

  220.                     if ($val->iid == $iid) {
    221. 

  221.                         break;
    222. 

  222.                     }
    223. 

  223.                 }
    224. 

  224.             }
    225. 

  225. 

  226.             $data['img'] = $val->pic;
    227. 

  227.             $data['title'] = $val->title;
    228. 

  228.             $data['url'] = $url;
    229. 

  229.             $data['swf'] = "http://www.tudou.com/l/{$icode}/&iid={$iid}/v.swf";
    230. 

  230. 

  231.             return $data;
    232. 

  232.         }
    233. 

  233. 

  234.         $host = "www.tudou.com";
    235. 

  235.         $path = "/v/{$matches[1]}/v.swf";
    236. 

  236. 

  237.         $ret = self::_fsget($path, $host);
    238. 

  238. 

  239.         if (preg_match("#\nLocation: (.*)\n#", $ret, $mat)) {
    240. 

  240.             parse_str(parse_url(urldecode($mat[1]), PHP_URL_QUERY));
    241. 

  241. 

  242.             $data['img'] = $snap_pic;
    243. 

  243.             $data['title'] = $title;
    244. 

  244.             $data['url'] = $url;
    245. 

  245.             $data['swf'] = "http://www.tudou.com/v/{$matches[1]}/v.swf";
    246. 

  246. 

  247.             return $data;
    248. 

  248.         }
    249. 

  249.         return false;
    250. 

  250.     }
    251. 

  251. 

  252.     /**
    253. 

  253.      * 酷6网 
    254. 

  254.      * http://v.ku6.com/film/show_520/3X93vo4tIS7uotHg.html
    255. 

  255.      * http://v.ku6.com/special/show_4926690/Klze2mhMeSK6g05X.html
    256. 

  256.      * http://v.ku6.com/show/7US-kDXjyKyIInDevhpwHg...html
    257. 

  257.      * http://player.ku6.com/refer/3X93vo4tIS7uotHg/v.swf
    258. 

  258.      */
    259. 

  259.     private function _parseKu6($url){
    260. 

  260.         if(preg_match("/show\_/", $url)){
    261. 

  261.             preg_match("#/([\w\.]*?)\.html#", $url, $matches);
    262. 

  262. 			var_dump($matches);
    263. 

  263.             $url = "http://v.ku6.com/fetchVideo4Player/{$matches[1]}.html";
    264. 

  264.             $html = self::_fget($url);
    265. 

  265. 

  266.             if ($html) {
    267. 

  267.                 $json = json_decode($html, true);
    268. 

  268.                 if(!$json) return false;
    269. 

  269.                 
    270. 

  270.                 $data['img'] = $json['data']['picpath'];
    271. 

  271.                 $data['title'] = $json['data']['t'];
    272. 

  272.                 $data['url'] = $url;
    273. 

  273.                 $data['swf'] = "http://player.ku6.com/refer/{$matches[1]}/v.swf";
    274. 

  274. 

  275.                 return $data;
    276. 

  276.             } else {
    277. 

  277.                 return false;
    278. 

  278.             }
    279. 

  279.         }elseif(preg_match("/show\//", $url, $matches)){
    280. 

  280.             $html = self::_fget($url);
    281. 

  281.             preg_match("/ObjectInfo\s?=\s?([^\n]*)};/si", $html, $matches);
    282. 

  282.             $str = $matches[1];
    283. 

  283.             // img
    284. 

  284.             preg_match("/cover\s?:\s?\"([^\"]+)\"/", $str, $matches);
    285. 

  285.             $data['img'] = $matches[1];
    286. 

  286.             // title
    287. 

  287.             preg_match("/title\"?\s?:\s?\"([^\"]+)\"/", $str, $matches);
    288. 

  288.             $jsstr = "{\"title\":\"{$matches[1]}\"}";
    289. 

  289.             $json = json_decode($jsstr, true);
    290. 

  290.             $data['title'] = $json['title'];
    291. 

  291.             // url
    292. 

  292.             $data['url'] = $url;
    293. 

  293.             // query
    294. 

  294.             preg_match("/\"(vid=[^\"]+)\"\sname=\"flashVars\"/s", $html, $matches);
    295. 

  295.             $query = str_replace("&amp;", '&', $matches[1]);
    296. 

  296.             preg_match("/\/\/player\.ku6cdn\.com[^\"\']+/", $html, $matches);
    297. 

  297.             $data['swf'] = 'http:'.$matches[0].'?'.$query;
    298. 

  298.             
    299. 

  299.             return $data;
    300. 

  300.         }
    301. 

  301.     }
    302. 

  302. 

  303.     /**
    304. 

  304.      * 56网
    305. 

  305.      * http://www.56.com/u73/v_NTkzMDcwNDY.html
    306. 

  306.      * http://player.56.com/v_NTkzMDcwNDY.swf
    307. 

  307.      */
    308. 

  308.     private function _parse56($url){
    309. 

  309.         preg_match("#/v_(\w+)\.html#", $url, $matches);
    310. 

  310. 

  311.         if (empty($matches)) return false;
    312. 

  312. 

  313.         $link="http://vxml.56.com/json/{$matches[1]}/?src=out";
    314. 

  314.         $retval = self::_cget($link);
    315. 

  315. 

  316.         if ($retval) {
    317. 

  317.             $json = json_decode($retval, true);
    318. 

  318. 

  319.             $data['img'] = $json['info']['bimg'];
    320. 

  320.             $data['title'] = $json['info']['Subject'];
    321. 

  321.             $data['url'] = $url;
    322. 

  322.             $data['swf'] = "http://player.56.com/v_{$matches[1]}.swf";
    323. 

  323. 

  324.             return $data;
    325. 

  325.         } else {
    326. 

  326.             return false;
    327. 

  327.         } 
    328. 

  328.     }
    329. 

  329. 

  330.     /**
    331. 

  331.      * 乐视网 
    332. 

  332.      * http://www.letv.com/ptv/vplay/1168109.html
    333. 

  333.      * http://www.letv.com/player/x1168109.swf
    334. 

  334.      */
    335. 

  335.     private function _parseLetv($url){
    336. 

  336.         $html = self::_fget($url);
    337. 

  337.         preg_match("#http://v.t.sina.com.cn/([^'\"]*)#", $html, $matches);
    338. 

  338.         parse_str(parse_url(urldecode($matches[0]), PHP_URL_QUERY));
    339. 

  339.         preg_match("#vplay/(\d+)#", $url, $matches);
    340. 

  340.         $data['img'] = $pic;
    341. 

  341.         $data['title'] = $title;
    342. 

  342.         $data['url'] = $url;
    343. 

  343.         $data['swf'] = "http://www.letv.com/player/x{$matches[1]}.swf";
    344. 

  344. 

  345.         return $data;
    346. 

  346.     }
    347. 

  347. 

  348.     // 搜狐TV http://my.tv.sohu.com/u/vw/5101536
    349. 

  349.     private function _parseSohu($url){
    350. 

  350.         $html = self::_fget($url);
    351. 

  351.         $html = iconv("GB2312", "UTF-8", $html);
    352. 

  352.         preg_match_all("/og:(?:title|image|videosrc)\"\scontent=\"([^\"]+)\"/s", $html, $matches);
    353. 

  353.         $data['img'] = $matches[1][1];
    354. 

  354.         $data['title'] = $matches[1][0];
    355. 

  355.         $data['url'] = $url;
    356. 

  356.         $data['swf'] = $matches[1][2];
    357. 

  357.         return $data;
    358. 

  358.     }
    359. 

  359.         
    360. 

  360.     /*
    361. 

  361.      * 新浪播客
    362. 

  362.      * http://video.sina.com.cn/v/b/48717043-1290055681.html
    363. 

  363.      * http://you.video.sina.com.cn/api/sinawebApi/outplayrefer.php/vid=48717043_1290055681_PUzkSndrDzXK+l1lHz2stqkP7KQNt6nki2O0u1ehIwZYQ0/XM5GdatoG5ynSA9kEqDhAQJA4dPkm0x4/s.swf
    364. 

  364.      */
    365. 

  365.     private function _parseSina($url){
    366. 

  366.         preg_match("/(\d+)(?:\-|\_)(\d+)/", $url, $matches);
    367. 

  367.         $url = "http://video.sina.com.cn/v/b/{$matches[1]}-{$matches[2]}.html";
    368. 

  368.         $html = self::_fget($url);
    369. 

  369.         preg_match("/video\s?:\s?([^<]+)}/", $html, $matches);
    370. 

  370.         $find = array("/\n/", "/\s*/", "/\'/", "/\{([^:,]+):/", "/,([^:]+):/", "/:[^\d\"]\w+[^\,]*,/i");
    371. 

  371.         $replace = array('', '', '"', '{"\\1":', ',"\\1":', ':"",');
    372. 

  372.         $str = preg_replace($find, $replace, $matches[1]);
    373. 

  373.         $arr = json_decode($str, true);
    374. 

  374. 

  375.         $data['img'] = $arr['pic'];
    376. 

  376.         $data['title'] = $arr['title'];
    377. 

  377.         $data['url'] = $url;
    378. 

  378.         $data['swf'] = $arr['swfOutsideUrl'];
    379. 

  379.         
    380. 

  380.         return $data;
    381. 

  381.     }
    382. 

  382. 

  383.     /*
    384. 

  384.      * 通过 file_get_contents 获取内容
    385. 

  385.      */
    386. 

  386.     private function _fget($url=''){
    387. 

  387.         if(!$url) return false;
    388. 

  388.         $html = file_get_contents($url);
    389. 

  389.         // 判断是否gzip压缩
    390. 

  390.         if($dehtml = self::_gzdecode($html))
    391. 

  391.             return $dehtml;
    392. 

  392.         else
    393. 

  393.             return $html;
    394. 

  394.     }
    395. 

  395. 

  396.     /*
    397. 

  397.      * 通过 fsockopen 获取内容
    398. 

  398.      */
    399. 

  399.     private function _fsget($path='/', $host='', $user_agent=''){
    400. 

  400.         if(!$path || !$host) return false;
    401. 

  401.         $user_agent = $user_agent ? $user_agent : self::USER_AGENT;
    402. 

  402. 

  403.         $out = <<<HEADER
    404. 

  404. GET $path HTTP/1.1
    405. 

  405. Host: $host
    406. 

  406. User-Agent: $user_agent
    407. 

  407. Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
    408. 

  408. Accept-Language: zh-cn,zh;q=0.5
    409. 

  409. Accept-Charset: GB2312,utf-8;q=0.7,*;q=0.7\r\n\r\n
    410. 

  410. HEADER;
    411. 

  411.         $fp = @fsockopen($host, 80, $errno, $errstr, 10);
    412. 

  412.         if (!$fp)  return false;
    413. 

  413.         if(!fputs($fp, $out)) return false;
    414. 

  414.         while ( !feof($fp) ) {
    415. 

  415.             $html .= fgets($fp, 1024);
    416. 

  416.         }
    417. 

  417.         fclose($fp);
    418. 

  418.         // 判断是否gzip压缩
    419. 

  419.         if($dehtml = self::_gzdecode($html))
    420. 

  420.             return $dehtml;
    421. 

  421.         else
    422. 

  422.             return $html;
    423. 

  423.     }
    424. 

    425. 

  425.     /*
    426. 

  426.      * 通过 curl 获取内容
    427. 

  427.      */
    428. 

  428.     private function _cget($url='', $user_agent=''){
    429. 

  429.         if(!$url) return;
    430. 

  430. 

  431.         $user_agent = $user_agent ? $user_agent : self::USER_AGENT;
    432. 

  432. 

  433.         $ch = curl_init();
    434. 

  434.         curl_setopt($ch, CURLOPT_URL, $url);
    435. 

  435.         curl_setopt($ch, CURLOPT_HEADER, 0);
    436. 

  436.         if(strlen($user_agent)) curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
    437. 

  437. 

  438.         ob_start();
    439. 

  439.         curl_exec($ch);
    440. 

  440.         $html = ob_get_contents();        
    441. 

  441.         ob_end_clean();
    442. 

  442. 

  443.         if(curl_errno($ch)){
    444. 

  444.            curl_close($ch);
    445. 

  445.             return false;
    446. 

  446.         }
    447. 

  447.         curl_close($ch);
    448. 

  448.         if(!is_string($html) || !strlen($html)){
    449. 

  449.             return false;
    450. 

  450.         }
    451. 

  451.         return $html;
    452. 

  452.         // 判断是否gzip压缩
    453. 

  453.         if($dehtml = self::_gzdecode($html))
    454. 

  454.             return $dehtml;
    455. 

  455.         else
    456. 

  456.             return $html;
    457. 

  457.     }
    458. 

  458.     
    459. 

  459.     private function _gzdecode($data) {
    460. 

  460.         $len = strlen ( $data );
    461. 

  461.         if ($len < 18 || strcmp ( substr ( $data, 0, 2 ), "\x1f\x8b" )) {
    462. 

  462.             return null; // Not GZIP format (See RFC 1952) 
    463. 

  463.         }
    464. 

  464.         $method = ord ( substr ( $data, 2, 1 ) ); // Compression method 
    465. 

  465.         $flags = ord ( substr ( $data, 3, 1 ) ); // Flags 
    466. 

  466.         if ($flags & 31 != $flags) {
    467. 

  467.             // Reserved bits are set -- NOT ALLOWED by RFC 1952 
    468. 

  468.             return null;
    469. 

  469.         }
    470. 

  470.         // NOTE: $mtime may be negative (PHP integer limitations) 
    471. 

  471.         $mtime = unpack ( "V", substr ( $data, 4, 4 ) );
    472. 

  472.         $mtime = $mtime [1];
    473. 

  473.         $xfl = substr ( $data, 8, 1 );
    474. 

  474.         $os = substr ( $data, 8, 1 );
    475. 

  475.         $headerlen = 10;
    476. 

  476.         $extralen = 0;
    477. 

  477.         $extra = "";
    478. 

  478.         if ($flags & 4) {
    479. 

  479.             // 2-byte length prefixed EXTRA data in header 
    480. 

  480.             if ($len - $headerlen - 2 < 8) {
    481. 

  481.                 return false; // Invalid format 
    482. 

  482.             }
    483. 

  483.             $extralen = unpack ( "v", substr ( $data, 8, 2 ) );
    484. 

  484.             $extralen = $extralen [1];
    485. 

  485.             if ($len - $headerlen - 2 - $extralen < 8) {
    486. 

  486.                 return false; // Invalid format 
    487. 

  487.             }
    488. 

  488.             $extra = substr ( $data, 10, $extralen );
    489. 

  489.             $headerlen += 2 + $extralen;
    490. 

  490.         }
    491. 

  491.      
    492. 

  492.         $filenamelen = 0;
    493. 

  493.         $filename = "";
    494. 

  494.         if ($flags & 8) {
    495. 

  495.             // C-style string file NAME data in header 
    496. 

  496.             if ($len - $headerlen - 1 < 8) {
    497. 

  497.                 return false; // Invalid format 
    498. 

  498.             }
    499. 

  499.             $filenamelen = strpos ( substr ( $data, 8 + $extralen ), chr ( 0 ) );
    500. 

  500.             if ($filenamelen === false || $len - $headerlen - $filenamelen - 1 < 8) {
    501. 

  501.                 return false; // Invalid format 
    502. 

  502.             }
    503. 

  503.             $filename = substr ( $data, $headerlen, $filenamelen );
    504. 

  504.             $headerlen += $filenamelen + 1;
    505. 

  505.         }
    506. 

  506.      
    507. 

  507.         $commentlen = 0;
    508. 

  508.         $comment = "";
    509. 

  509.         if ($flags & 16) {
    510. 

  510.             // C-style string COMMENT data in header 
    511. 

  511.             if ($len - $headerlen - 1 < 8) {
    512. 

  512.                 return false; // Invalid format 
    513. 

  513.             }
    514. 

  514.             $commentlen = strpos ( substr ( $data, 8 + $extralen + $filenamelen ), chr ( 0 ) );
    515. 

  515.             if ($commentlen === false || $len - $headerlen - $commentlen - 1 < 8) {
    516. 

  516.                 return false; // Invalid header format 
    517. 

  517.             }
    518. 

  518.             $comment = substr ( $data, $headerlen, $commentlen );
    519. 

  519.             $headerlen += $commentlen + 1;
    520. 

  520.         }
    521. 

  521.      
    522. 

  522.         $headercrc = "";
    523. 

  523.         if ($flags & 1) {
    524. 

  524.             // 2-bytes (lowest order) of CRC32 on header present 
    525. 

  525.             if ($len - $headerlen - 2 < 8) {
    526. 

  526.                 return false; // Invalid format 
    527. 

  527.             }
    528. 

  528.             $calccrc = crc32 ( substr ( $data, 0, $headerlen ) ) & 0xffff;
    529. 

  529.             $headercrc = unpack ( "v", substr ( $data, $headerlen, 2 ) );
    530. 

  530.             $headercrc = $headercrc [1];
    531. 

  531.             if ($headercrc != $calccrc) {
    532. 

  532.                 return false; // Bad header CRC 
    533. 

  533.             }
    534. 

  534.             $headerlen += 2;
    535. 

  535.         }
    536. 

  536.      
    537. 

  537.         // GZIP FOOTER - These be negative due to PHP's limitations 
    538. 

  538.         $datacrc = unpack ( "V", substr ( $data, - 8, 4 ) );
    539. 

  539.         $datacrc = $datacrc [1];
    540. 

  540.         $isize = unpack ( "V", substr ( $data, - 4 ) );
    541. 

  541.         $isize = $isize [1];
    542. 

  542.      
    543. 

  543.         // Perform the decompression: 
    544. 

  544.         $bodylen = $len - $headerlen - 8;
    545. 

  545.         if ($bodylen < 1) {
    546. 

  546.             // This should never happen - IMPLEMENTATION BUG! 
    547. 

  547.             return null;
    548. 

  548.         }
    549. 

  549.         $body = substr ( $data, $headerlen, $bodylen );
    550. 

  550.         $data = "";
    551. 

  551.         if ($bodylen > 0) {
    552. 

  552.             switch ($method) {
    553. 

  553.                 case 8 :
    554. 

  554.                     // Currently the only supported compression method: 
    555. 

  555.                     $data = gzinflate ( $body );
    556. 

  556.                     break;
    557. 

  557.                 default :
    558. 

  558.                     // Unknown compression method 
    559. 

  559.                     return false;
    560. 

  560.             }
    561. 

  561.         } else {
    562. 

  562.             //...
    563. 

  563.         }
    564. 

  564.      
    565. 

  565.         if ($isize != strlen ( $data ) || crc32 ( $data ) != $datacrc) {
    566. 

  566.             // Bad format!  Length or CRC doesn't match! 
    567. 

  567.             return false;
    568. 

  568.         }
    569. 

  569.         return $data;
    570. 

  570.     }
    571. 

  571. }
    572. 

  572.