网上帖子基本上获得的都是假路径,用httpclient根本无法下载视频
例如:
优酷视频地址:http://v.youku.com/v_show/id_XNDM2NTcyOTM2.html?f=17977385
虚假地址:http://static.youku.com/v1.0.0255/v/swf/player.swf
用firebug获得视频的路径:其实真实路径是:http://119.167.222.14/youku/65716DFC6F9388254A1CF6480D/0300080100502107179D450727D0CD7450768F-5C38-9529-5B70-574065346233.mp4 视频大小为:4.9M怎样运用java程序获得视频的真实路径,并且下载??
例如:
优酷视频地址:http://v.youku.com/v_show/id_XNDM2NTcyOTM2.html?f=17977385
虚假地址:http://static.youku.com/v1.0.0255/v/swf/player.swf
用firebug获得视频的路径:其实真实路径是:http://119.167.222.14/youku/65716DFC6F9388254A1CF6480D/0300080100502107179D450727D0CD7450768F-5C38-9529-5B70-574065346233.mp4 视频大小为:4.9M怎样运用java程序获得视频的真实路径,并且下载??
//获取优酷视频图片地址
class VideoUrlParser {
const USER_AGENT = "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.10 (KHTML, like Gecko)
Chrome/8.0.552.224 Safari/534.10";
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)/"; /**
* parse
*
* @param string $url
* @param mixed $createObject
* @static
* @access public
* @return void
*/
public static function parse($url = ''){
$lowerurl = strtolower($url);
preg_match(self::CHECK_URL_VALID, $lowerurl, $matches);
if(!$matches) return false; switch($matches[1]){
case 'youku.com':
$data = self::_parseYouku($url);
break;
case 'tudou.com':
$data = self::_parseTudou($url);
break;
default:
$data = false;
}
return $data;
}
/**
* 优酷网
* http://v.youku.com/v_show/id_XMjI4MDM4NDc2.html
* http://player.youku.com/player.php/sid/XMjU0NjI2Njg4/v.swf
*/
private function _parseYouku($url){
preg_match("#id\_(\w+)#", $url, $matches); if (empty($matches)){
preg_match("#v_playlist\/#", $url, $mat);
if(!$mat) return false; $html = self::_fget($url); preg_match("#videoId2\s*=\s*\'(\w+)\'#", $html, $matches);
if(!$matches) return false;
} $link = "http://v.youku.com/player/getPlayList/VideoIDS/{$matches[1]}/timezone/+08/version/5/source/out?password=&ran=2513&n=3"; $retval = self::_cget($link);
if ($retval) {
$json = json_decode($retval, true); $data['img'] = $json['data'][0]['logo'];
$data['title'] = $json['data'][0]['title'];
$data['url'] = $url;
$data['swf'] = "http://player.youku.com/player.php/sid/{$matches[1]}/v.swf"; return $data;
} else {
return false;
}
} /**
* 土豆网
* http://www.tudou.com/programs/view/Wtt3FjiDxEE/
* http://www.tudou.com/v/Wtt3FjiDxEE/v.swf
*
* http://www.tudou.com/playlist/p/a65718.html?iid=74909603
* http://www.tudou.com/l/G5BzgI4lAb8/&iid=74909603/v.swf
*/
private function _parseTudou($url){
/* add part */
if (strpos($url, "/listplay/") === false) return false;
$html = file_get_contents($url);
preg_match_all("/,pic:\"([\w\/\.\:]+)\"/", $html, $matches);
if($matches[1][0]){
$data['img'] = $matches[1][0];
return $data;
}
return false;
} /*
* 通过 file_get_contents 获取内容
*/
private function _fget($url=''){
if(!$url) return false;
$html = file_get_contents($url);
// 判断是否gzip压缩
if($dehtml = self::_gzdecode($html))
return $dehtml;
else
return $html;
} /*
* 通过 curl 获取内容
*/
private function _cget($url='', $user_agent=''){
if(!$url) return; $user_agent = $user_agent ? $user_agent : self::USER_AGENT; $ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 0);
if(strlen($user_agent)) curl_setopt($ch, CURLOPT_USERAGENT, $user_agent); ob_start();
curl_exec($ch);
$html = ob_get_contents();
ob_end_clean(); if(curl_errno($ch)){
curl_close($ch);
return false;
}
curl_close($ch);
if(!is_string($html) || !strlen($html)){
return false;
}
return $html;
// 判断是否gzip压缩
if($dehtml = self::_gzdecode($html))
return $dehtml;
else
return $html;
}
private function _gzdecode($data) {
$len = strlen ( $data );
if ($len < 18 || strcmp ( substr ( $data, 0, 2 ), "\x1f\x8b" )) {
return null; // Not GZIP format (See RFC 1952)
}
$method = ord ( substr ( $data, 2, 1 ) ); // Compression method
$flags = ord ( substr ( $data, 3, 1 ) ); // Flags
if ($flags & 31 != $flags) {
// Reserved bits are set -- NOT ALLOWED by RFC 1952
return null;
}
// NOTE: $mtime may be negative (PHP integer limitations)
$mtime = unpack ( "V", substr ( $data, 4, 4 ) );
$mtime = $mtime [1];
$xfl = substr ( $data, 8, 1 );
$os = substr ( $data, 8, 1 );
$headerlen = 10;
$extralen = 0;
$extra = "";
if ($flags & 4) {
// 2-byte length prefixed EXTRA data in header
if ($len - $headerlen - 2 < 8) {
return false; // Invalid format
}
$extralen = unpack ( "v", substr ( $data, 8, 2 ) );
$extralen = $extralen [1];
if ($len - $headerlen - 2 - $extralen < 8) {
return false; // Invalid format
}
$extra = substr ( $data, 10, $extralen );
$headerlen += 2 + $extralen;
}
$filenamelen = 0;
$filename = "";
if ($flags & 8) {
// C-style string file NAME data in header
if ($len - $headerlen - 1 < 8) {
return false; // Invalid format
}
$filenamelen = strpos ( substr ( $data, 8 + $extralen ), chr ( 0 ) );
if ($filenamelen === false || $len - $headerlen - $filenamelen - 1 < 8) {
return false; // Invalid format
}
$filename = substr ( $data, $headerlen, $filenamelen );
$headerlen += $filenamelen + 1;
}
$commentlen = 0;
$comment = "";
if ($flags & 16) {
// C-style string COMMENT data in header
if ($len - $headerlen - 1 < 8) {
return false; // Invalid format
}
$commentlen = strpos ( substr ( $data, 8 + $extralen + $filenamelen ), chr ( 0 ) );
if ($commentlen === false || $len - $headerlen - $commentlen - 1 < 8) {
return false; // Invalid header format
}
$comment = substr ( $data, $headerlen, $commentlen );
$headerlen += $commentlen + 1;
}
$headercrc = "";
if ($flags & 1) {
// 2-bytes (lowest order) of CRC32 on header present
if ($len - $headerlen - 2 < 8) {
return false; // Invalid format
}
$calccrc = crc32 ( substr ( $data, 0, $headerlen ) ) & 0xffff;
$headercrc = unpack ( "v", substr ( $data, $headerlen, 2 ) );
$headercrc = $headercrc [1];
if ($headercrc != $calccrc) {
return false; // Bad header CRC
}
$headerlen += 2;
}
// GZIP FOOTER - These be negative due to PHP's limitations
$datacrc = unpack ( "V", substr ( $data, - 8, 4 ) );
$datacrc = $datacrc [1];
$isize = unpack ( "V", substr ( $data, - 4 ) );
$isize = $isize [1];
// Perform the decompression:
$bodylen = $len - $headerlen - 8;
if ($bodylen < 1) {
// This should never happen - IMPLEMENTATION BUG!
return null;
}
$body = substr ( $data, $headerlen, $bodylen );
$data = "";
if ($bodylen > 0) {
switch ($method) {
case 8 :
// Currently the only supported compression method:
$data = gzinflate ( $body );
break;
default :
// Unknown compression method
return false;
}
} else {
//...
}
if ($isize != strlen ( $data ) || crc32 ( $data ) != $datacrc) {
// Bad format! Length or CRC doesn't match!
return false;
}
return $data;
}
}
?>
这个是网页中内嵌视频的方法
这是一个播放器:http://static.youku.com/v1.0.0255/v/swf/player.swf
这些是请求参数:
VideoIDS=XNDM2NTcyOTM2&ShowId=0&Cp=0&Light=on&THX=off&unCookie=0&frame=0&pvid=1344410210096YCD&Tid=0&isAutoPlay=true&Version=/v1.0.0788&show_ce=1&winType=interior&Type=Folder&Fid=17977385&Pt=0&Ob=1&embedid=AjEwOTE0MzIzNAJ2LnlvdWt1LmNvbQIvdl9zaG93L2lkX1hORE0yTlRjeU9UTTIuaHRtbA==访问视频:把参数传给播放器
http://static.youku.com/v1.0.0255/v/swf/player.swf?VideoIDS=XNDM2NTcyOTM2&ShowId=0&Cp=0&Light=on&THX=off&unCookie=0&frame=0&pvid=1344410210096YCD&Tid=0&isAutoPlay=true&Version=/v1.0.0788&show_ce=1&winType=interior&Type=Folder&Fid=17977385&Pt=0&Ob=1&embedid=AjEwOTE0MzIzNAJ2LnlvdWt1LmNvbQIvdl9zaG93L2lkX1hORE0yTlRjeU9UTTIuaHRtbA==但是这只是表面现象,根本无法根据这个地址下载视频,因为视频的绝对路径没获得
这个是硕鼠网站会把你嗅出真是的下载地址,然后你去爬取这个里面给你的真实地址