搜索

首页  >  文章  >  后端开发  >  php各种优酷，土豆，视频封装类

php各种优酷，土豆，视频封装类

WBOY
WBOY原创
2016-07-25 08:49:371075浏览
php各种视频采集类封装，优酷，土豆，腾讯视频、56、搜狐视频、酷六、新浪视频、乐视.......

九弄 jigwang.com
  2. /**
  3. * Video
  4. *
  5. * @package
  6. * @version 1.3
  7. * @copyright 2011 - 2013
  8. *
  9. * Usage
  10. * require_once "VideoUrlParser.class.php";
  11. * $urls[] = "http://v.youku.com/v_show/id_XMjI4MDM4NDc2.html";
  12. * $urls[] = "http://www.tudou.com/playlist/p/l13087099.html";
  13. * $urls[] = "http://www.tudou.com/programs/view/ufg-A3tlcxk/";
  14. * $urls[] = "http://v.ku6.com/special/show_4926690/Klze2mhMeSK6g05X.html";
  15. * $urls[] = "http://www.56.com/u68/v_NjI2NTkxMzc.html";
  16. * $urls[] = "http://www.letv.com/ptv/vplay/1168109.html";
  17. * $urls[] = "http://video.sina.com.cn/v/b/46909166-1290055681.html";
  18. *
  19. * foreach($urls as $url){
  20. * $info = VideoUrlParser::parse($url);
  21. * //var_dump($info);
  22. * echo "{$info['title']}";
  23. * echo "
    ";
  24. * echo $info['object'];
  25. * echo "
    ";
  26. * }
  27. *
  28. *
  29. *
  30. * //优酷
  31. * http://v.youku.com/v_show/id_XMjU0NjY4OTEy.html
  32. *
  33. *
  34. * //酷六
  35. * http://v.ku6.com/special/show_3917484/x0BMXAbgZdQS6FqN.html
  36. *
  37. *
  38. * //土豆
  39. * http://www.tudou.com/playlist/p/a65929.html?iid=74905844
  40. *
  41. *
  42. * //56
  43. * http://www.56.com/u98/v_NTkyODY2NTU.html
  44. *
  45. *
  46. * //新浪播客
  47. * http://video.sina.com.cn/v/b/46909166-1290055681.html
  48. *
  49. *
  50. * //乐视
  51. * http://www.letv.com/ptv/vplay/1168109.html
  52. *
  53. */
  55. class VideoUrlparser
  56. {
  57. const USER_AGENT = "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.10 (KHTML, like Gecko)
  58. Chrome/8.0.552.224 Safari/534.10";
  59. 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)/";
  61. /**
  62. * parse
  63. *
  64. * @param string $url
  65. * @param mixed $createObject
  66. * @static
  67. * @access public
  68. * @return void
  69. */
  70. static public function parse($url='', $createObject=true){
  71. $lowerurl = strtolower($url);
  72. preg_match(self::CHECK_URL_VALID, $lowerurl, $matches);
  73. if(!$matches) return false;
  75. switch($matches[1]){
  76. case 'youku.com':
  77. $data = self::_parseYouku($url);
  78. break;
  79. case 'tudou.com':
  80. $data = self::_parseTudou($url);
  81. break;
  82. case 'ku6.com':
  83. $data = self::_parseKu6($url);
  84. break;
  85. case '56.com':
  86. $data = self::_parse56($url);
  87. break;
  88. case 'letv.com':
  89. $data = self::_parseLetv($url);
  90. break;
  91. case 'video.sina.com.cn':
  92. $data = self::_parseSina($url);
  93. break;
  94. case 'my.tv.sohu.com':
  95. case 'tv.sohu.com':
  96. case 'sohu.com':
  97. $data = self::_parseSohu($url);
  98. break;
  99. case 'v.qq.com':
  100. $data = self::_parseQq($url);
  101. break;
  102. default:
  103. $data = false;
  104. }
  106. if($data && $createObject) $data['object'] = "";
  107. return $data;
  108. }
  109. /**
  110. * 腾讯视频
  111. * http://v.qq.com/cover/o/o9tab7nuu0q3esh.html?vid=97abu74o4w3_0
  112. * http://v.qq.com/play/97abu74o4w3.html
  113. * http://v.qq.com/cover/d/dtdqyd8g7xvoj0o.html
  114. * http://v.qq.com/cover/d/dtdqyd8g7xvoj0o/9SfqULsrtSb.html
  115. * http://imgcache.qq.com/tencentvideo_v1/player/TencentPlayer.swf?_v=20110829&vid=97abu74o4w3&autoplay=1&list=2&showcfg=1&tpid=23&title=%E7%AC%AC%E4%B8%80%E7%8E%B0%E5%9C%BA&adplay=1&cid=o9tab7nuu0q3esh
  116. */
  117. private static function _parseQq($url){
  118. if(preg_match("/\/play\//", $url)){
  119. $html = self::_fget($url);
  120. preg_match("/url=[^\"]+/", $html, $matches);
  121. if(!$matches); return false;
  122. $url = $matches[0];
  123. }
  124. preg_match("/vid=([^\_]+)/", $url, $matches);
  125. $vid = $matches[1];
  126. $html = self::_fget($url);
  127. // query
  128. preg_match("/flashvars\s=\s\"([^;]+)/s", $html, $matches);
  129. $query = $matches[1];
  130. if(!$vid){
  131. preg_match("/vid\s?=\s?vid\s?\|\|\s?\"(\w+)\";/i", $html, $matches);
  132. $vid = $matches[1];
  133. }
  134. $query = str_replace('"+vid+"', $vid, $query);
  135. parse_str($query, $output);
  136. $data['img'] = "http://vpic.video.qq.com/{$$output['cid']}/{$vid}_1.jpg";
  137. $data['url'] = $url;
  138. $data['title'] = $output['title'];
  139. $data['swf'] = "http://imgcache.qq.com/tencentvideo_v1/player/TencentPlayer.swf?".$query;
  140. return $data;
  141. }
  143. /*
  144. * 优酷网
  145. * http://v.youku.com/v_show/id_XMjI4MDM4NDc2.html
  146. * http://player.youku.com/player.php/sid/XMjU0NjI2Njg4/v.swf
  147. */
  148. private static function _parseYouku($url){
  149. preg_match("#id\_(\w+)#", $url, $matches);
  151. if (empty($matches)){
  152. preg_match("#v_playlist\/#", $url, $mat);
  153. if(!$mat) return false;
  155. $html = self::_fget($url);
  157. preg_match("#videoId2\s*=\s*\'(\w+)\'#", $html, $matches);
  158. if(!$matches) return false;
  159. }
  161. $link = "http://v.youku.com/player/getPlayList/VideoIDS/{$matches[1]}/timezone/+08/version/5/source/out?password=&ran=2513&n=3";
  163. $retval = self::_cget($link);
  164. if ($retval) {
  165. $json = json_decode($retval, true);
  167. $data['img'] = $json['data'][0]['logo'];
  168. $data['title'] = $json['data'][0]['title'];
  169. $data['url'] = $url;
  170. $data['swf'] = "http://player.youku.com/player.php/sid/{$matches[1]}/v.swf";
  172. // echo "
    "; var_dump($data);
  174. return $data;
  175. } else {
  176. return false;
  177. }
  178. }
  180. /**
  181. * 土豆网
  182. * http://www.tudou.com/programs/view/Wtt3FjiDxEE/
  183. * http://www.tudou.com/v/Wtt3FjiDxEE/v.swf
  184. *
  185. * http://www.tudou.com/playlist/p/a65718.html?iid=74909603
  186. * http://www.tudou.com/l/G5BzgI4lAb8/&iid=74909603/v.swf
  187. */
  188. private static function _parseTudou($url){
  189. preg_match("#view/([-\w]+)/#", $url, $matches);
  191. if (empty($matches)) {
  192. if (strpos($url, "/playlist/") == false) return false;
  194. if(strpos($url, 'iid=') !== false){
  195. $quarr = explode("iid=", $lowerurl);
  196. if (empty($quarr[1])) return false;
  197. }elseif(preg_match("#p\/l(\d+).#", $lowerurl, $quarr)){
  198. if (empty($quarr[1])) return false;
  199. }
  201. $html = self::_fget($url);
  202. $html = iconv("GB2312", "UTF-8", $html);
  204. preg_match("/lid_code\s=\slcode\s=\s[\'\"]([^\'\"]+)/s", $html, $matches);
  205. $icode = $matches[1];
  207. preg_match("/iid\s=\s.*?\|\|\s(\d+)/sx", $html, $matches);
  208. $iid = $matches[1];
  210. preg_match("/listData\s=\s(\[\{.*\}\])/sx", $html, $matches);
  212. $find = array("/\n/", '/\s/', "/:[^\d\"]\w+[^\,]*,/i", "/(\{|,)(\w+):/");
  213. $replace = array("", "", ':"",', '\\1"\\2":');
  214. $str = preg_replace($find, $replace, $matches[1]);
  215. //var_dump($str);
  216. $json = json_decode($str);
  217. //var_dump($json);exit;
  218. if(is_array($json) || is_object($json) && !empty($json)){
  219. foreach ($json as $val) {
  220. if ($val->iid == $iid) {
  221. break;
  222. }
  223. }
  224. }
  226. $data['img'] = $val->pic;
  227. $data['title'] = $val->title;
  228. $data['url'] = $url;
  229. $data['swf'] = "http://www.tudou.com/l/{$icode}/&iid={$iid}/v.swf";
  231. return $data;
  232. }
  234. $host = "www.tudou.com";
  235. $path = "/v/{$matches[1]}/v.swf";
  237. $ret = self::_fsget($path, $host);
  239. if (preg_match("#\nLocation: (.*)\n#", $ret, $mat)) {
  240. parse_str(parse_url(urldecode($mat[1]), PHP_URL_QUERY));
  242. $data['img'] = $snap_pic;
  243. $data['title'] = $title;
  244. $data['url'] = $url;
  245. $data['swf'] = "http://www.tudou.com/v/{$matches[1]}/v.swf";
  247. return $data;
  248. }
  249. return false;
  250. }
  252. /**
  253. * 酷6网
  254. * http://v.ku6.com/film/show_520/3X93vo4tIS7uotHg.html
  255. * http://v.ku6.com/special/show_4926690/Klze2mhMeSK6g05X.html
  256. * http://v.ku6.com/show/7US-kDXjyKyIInDevhpwHg...html
  257. * http://player.ku6.com/refer/3X93vo4tIS7uotHg/v.swf
  258. */
  259. private static function _parseKu6($url){
  260. if(preg_match("/show\_/", $url)){
  261. preg_match("#/([-\w]+)\.html#", $url, $matches);
  262. $url = "http://v.ku6.com/fetchVideo4Player/{$matches[1]}.html";
  263. $html = self::_fget($url);
  265. if ($html) {
  266. $json = json_decode($html, true);
  267. if(!$json) return false;
  269. $data['img'] = $json['data']['picpath'];
  270. $data['title'] = $json['data']['t'];
  271. $data['url'] = $url;
  272. $data['swf'] = "http://player.ku6.com/refer/{$matches[1]}/v.swf";
  274. return $data;
  275. } else {
  276. return false;
  277. }
  278. }elseif(preg_match("/show\//", $url, $matches)){
  279. $html = self::_fget($url);
  280. preg_match("/ObjectInfo\s?=\s?([^\n]*)};/si", $html, $matches);
  281. $str = $matches[1];
  282. // img
  283. preg_match("/cover\s?:\s?\"([^\"]+)\"/", $str, $matches);
  284. $data['img'] = $matches[1];
  285. // title
  286. preg_match("/title\"?\s?:\s?\"([^\"]+)\"/", $str, $matches);
  287. $jsstr = "{\"title\":\"{$matches[1]}\"}";
  288. $json = json_decode($jsstr, true);
  289. $data['title'] = $json['title'];
  290. // url
  291. $data['url'] = $url;
  292. // query
  293. preg_match("/\"(vid=[^\"]+)\"\sname=\"flashVars\"/s", $html, $matches);
  294. $query = str_replace("&", '&', $matches[1]);
  295. preg_match("/\/\/player\.ku6cdn\.com[^\"\']+/", $html, $matches);
  296. $data['swf'] = 'http:'.$matches[0].'?'.$query;
  298. return $data;
  299. }
  300. }
  302. /**
  303. * 56网
  304. * http://www.56.com/u73/v_NTkzMDcwNDY.html
  305. * http://player.56.com/v_NTkzMDcwNDY.swf
  306. */
  307. private static function _parse56($url){
  308. preg_match("#/v_(\w+)\.html#", $url, $matches);
  310. if (empty($matches)) return false;
  312. $link="http://vxml.56.com/json/{$matches[1]}/?src=out";
  313. $retval = self::_cget($link);
  315. if ($retval) {
  316. $json = json_decode($retval, true);
  318. $data['img'] = $json['info']['img'];
  319. $data['title'] = $json['info']['Subject'];
  320. $data['url'] = $url;
  321. $data['swf'] = "http://player.56.com/v_{$matches[1]}.swf";
  323. return $data;
  324. } else {
  325. return false;
  326. }
  327. }
  329. /**
  330. * 乐视网
  331. * http://www.letv.com/ptv/vplay/1168109.html
  332. * http://www.letv.com/player/x1168109.swf
  333. */
  334. private static function _parseLetv($url){
  335. $html = self::_fget($url);
  336. preg_match("#http://v.t.sina.com.cn/([^'\"]*)#", $html, $matches);
  337. parse_str(parse_url(urldecode($matches[0]), PHP_URL_QUERY));
  338. preg_match("#vplay/(\d+)#", $url, $matches);
  339. $data['img'] = $pic;
  340. $data['title'] = $title;
  341. $data['url'] = $url;
  342. $data['swf'] = "http://www.letv.com/player/x{$matches[1]}.swf";
  344. return $data;
  345. }
  347. // 搜狐TV http://my.tv.sohu.com/u/vw/5101536
  348. private static function _parseSohu($url){
  349. $html = self::_fget($url);
  350. $html = iconv("GB2312", "UTF-8", $html);
  351. preg_match_all("/og:(?:title|image|videosrc)\"\scontent=\"([^\"]+)\"/s", $html, $matches);
  352. $data['img'] = $matches[1][1];
  353. $data['title'] = $matches[1][0];
  354. $data['url'] = $url;
  355. $data['swf'] = $matches[1][2];
  356. return $data;
  357. }
  359. /*
  360. * 新浪播客
  361. * http://video.sina.com.cn/v/b/48717043-1290055681.html
  362. * http://you.video.sina.com.cn/api/sinawebApi/outplayrefer.php/vid=48717043_1290055681_PUzkSndrDzXK+l1lHz2stqkP7KQNt6nki2O0u1ehIwZYQ0/XM5GdatoG5ynSA9kEqDhAQJA4dPkm0x4/s.swf
  363. */
  364. private static function _parseSina($url){
  365. preg_match("/(\d+)(?:\-|\_)(\d+)/", $url, $matches);
  366. $url = "http://video.sina.com.cn/v/b/{$matches[1]}-{$matches[2]}.html";
  367. $html = self::_fget($url);
  368. preg_match("/video\s?:\s?([^ $find = array("/\n/", "/\s*/", "/\'/", "/\{([^:,]+):/", "/,([^:]+):/", "/:[^\d\"]\w+[^\,]*,/i");
  369. $replace = array('', '', '"', '{"\\1":', ',"\\1":', ':"",');
  370. $str = preg_replace($find, $replace, $matches[1]);
  371. $arr = json_decode($str, true);
  373. $data['img'] = $arr['pic'];
  374. $data['title'] = $arr['title'];
  375. $data['url'] = $url;
  376. $data['swf'] = $arr['swfOutsideUrl'];
  378. return $data;
  379. }
  381. /*
  382. * 通过 file_get_contents 获取内容
  383. */
  384. private static function _fget($url=''){
  385. if(!$url) return false;
  386. $html = file_get_contents($url);
  387. // 判断是否gzip压缩
  388. if($dehtml = self::_gzdecode($html))
  389. return $dehtml;
  390. else
  391. return $html;
  392. }
  394. /*
  395. * 通过 fsockopen 获取内容
  396. */
  397. private static function _fsget($path='/', $host='', $user_agent=''){
  398. if(!$path || !$host) return false;
  399. $user_agent = $user_agent ? $user_agent : self::USER_AGENT;
  401. $out = GET $path HTTP/1.1
  402. Host: $host
  403. User-Agent: $user_agent
  404. Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
  405. Accept-Language: zh-cn,zh;q=0.5
  406. Accept-Charset: GB2312,utf-8;q=0.7,*;q=0.7\r\n\r\n
  407. HEADER;
  408. $fp = @fsockopen($host, 80, $errno, $errstr, 10);
  409. if (!$fp) return false;
  410. if(!fputs($fp, $out)) return false;
  411. while ( !feof($fp) ) {
  412. $html .= fgets($fp, 1024);
  413. }
  414. fclose($fp);
  415. // 判断是否gzip压缩
  416. if($dehtml = self::_gzdecode($html))
  417. return $dehtml;
  418. else
  419. return $html;
  420. }
  422. /*
  423. * 通过 curl 获取内容
  424. */
  425. private static function _cget($url='', $user_agent=''){
  426. if(!$url) return;
  428. $user_agent = $user_agent ? $user_agent : self::USER_AGENT;
  430. $ch = curl_init();
  431. curl_setopt($ch, CURLOPT_URL, $url);
  432. curl_setopt($ch, CURLOPT_HEADER, 0);
  433. if(strlen($user_agent)) curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
  435. ob_start();
  436. curl_exec($ch);
  437. $html = ob_get_contents();
  438. ob_end_clean();
  440. if(curl_errno($ch)){
  441. curl_close($ch);
  442. return false;
  443. }
  444. curl_close($ch);
  445. if(!is_string($html) || !strlen($html)){
  446. return false;
  447. }
  448. return $html;
  449. // 判断是否gzip压缩
  450. if($dehtml = self::_gzdecode($html))
  451. return $dehtml;
  452. else
  453. return $html;
  454. }
  456. private static function _gzdecode($data) {
  457. $len = strlen ( $data );
  458. if ($len return null; // Not GZIP format (See RFC 1952)
  459. }
  460. $method = ord ( substr ( $data, 2, 1 ) ); // Compression method
  461. $flags = ord ( substr ( $data, 3, 1 ) ); // Flags
  462. if ($flags & 31 != $flags) {
  463. // Reserved bits are set -- NOT ALLOWED by RFC 1952
  464. return null;
  465. }
  466. // NOTE: $mtime may be negative (PHP integer limitations)
  467. $mtime = unpack ( "V", substr ( $data, 4, 4 ) );
  468. $mtime = $mtime [1];
  469. $xfl = substr ( $data, 8, 1 );
  470. $os = substr ( $data, 8, 1 );
  471. $headerlen = 10;
  472. $extralen = 0;
  473. $extra = "";
  474. if ($flags & 4) {
  475. // 2-byte length prefixed EXTRA data in header
  476. if ($len - $headerlen - 2 return false; // Invalid format
  477. }
  478. $extralen = unpack ( "v", substr ( $data, 8, 2 ) );
  479. $extralen = $extralen [1];
  480. if ($len - $headerlen - 2 - $extralen return false; // Invalid format
  481. }
  482. $extra = substr ( $data, 10, $extralen );
  483. $headerlen += 2 + $extralen;
  484. }
  486. $filenamelen = 0;
  487. $filename = "";
  488. if ($flags & 8) {
  489. // C-style string file NAME data in header
  490. if ($len - $headerlen - 1 return false; // Invalid format
  491. }
  492. $filenamelen = strpos ( substr ( $data, 8 + $extralen ), chr ( 0 ) );
  493. if ($filenamelen === false || $len - $headerlen - $filenamelen - 1 return false; // Invalid format
  494. }
  495. $filename = substr ( $data, $headerlen, $filenamelen );
  496. $headerlen += $filenamelen + 1;
  497. }
  499. $commentlen = 0;
  500. $comment = "";
  501. if ($flags & 16) {
  502. // C-style string COMMENT data in header
  503. if ($len - $headerlen - 1 return false; // Invalid format
  504. }
  505. $commentlen = strpos ( substr ( $data, 8 + $extralen + $filenamelen ), chr ( 0 ) );
  506. if ($commentlen === false || $len - $headerlen - $commentlen - 1 return false; // Invalid header format
  507. }
  508. $comment = substr ( $data, $headerlen, $commentlen );
  509. $headerlen += $commentlen + 1;
  510. }
  512. $headercrc = "";
  513. if ($flags & 1) {
  514. // 2-bytes (lowest order) of CRC32 on header present
  515. if ($len - $headerlen - 2 return false; // Invalid format
  516. }
  517. $calccrc = crc32 ( substr ( $data, 0, $headerlen ) ) & 0xffff;
  518. $headercrc = unpack ( "v", substr ( $data, $headerlen, 2 ) );
  519. $headercrc = $headercrc [1];
  520. if ($headercrc != $calccrc) {
  521. return false; // Bad header CRC
  522. }
  523. $headerlen += 2;
  524. }
  526. // GZIP FOOTER - These be negative due to PHP's limitations
  527. $datacrc = unpack ( "V", substr ( $data, - 8, 4 ) );
  528. $datacrc = $datacrc [1];
  529. $isize = unpack ( "V", substr ( $data, - 4 ) );
  530. $isize = $isize [1];
  532. // Perform the decompression:
  533. $bodylen = $len - $headerlen - 8;
  534. if ($bodylen // This should never happen - IMPLEMENTATION BUG!
  535. return null;
  536. }
  537. $body = substr ( $data, $headerlen, $bodylen );
  538. $data = "";
  539. if ($bodylen > 0) {
  540. switch ($method) {
  541. case 8 :
  542. // Currently the only supported compression method:
  543. $data = gzinflate ( $body );
  544. break;
  545. default :
  546. // Unknown compression method
  547. return false;
  548. }
  549. } else {
  550. //...
  551. }
  553. if ($isize != strlen ( $data ) || crc32 ( $data ) != $datacrc) {
  554. // Bad format! Length or CRC doesn't match!
  555. return false;
  556. }
  557. return $data;
  558. }
  559. }
  561. /*
  563. $url = "http://v.youku.com/v_show/id_XNjIxNjUyOTky.html";
  565. $obj = new VideoUrlparser();
  567. $data = $obj->parse($url);
  569. var_dump($data);
  571. */
复制代码


声明：
本文内容由网友自发贡献，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系admin@php.cn
上一篇：一个简单的数据库连接和文本缓存综合类 下一篇：对word直接从数据库查询进行下载

相关文章

查看更多