56.com视频采集接口程序(PHP)
2015-01-24信息快讯网
我给大家个采集接口，你爱自己采集可以用自己的FLASH播放器直接播放56.com的flv吧！不用帮人家做免费广告那么傻了！
<?php
$url = "http://www.56.com/u75/v_MTkwMTIwMjQ.html";
$html = @file_get_contents($url);
preg_match_all("/var _oFlv_o = '([\S|\s]+)'/isU", $html, $matches);
$o = decode56($matches[1][0]);
include_once "json.php"; //当php没有配置支持json的时候有用
$o = str_replace("'", '"', $o);
$o = json_decode($o);
//print_r($o);
$swf = "http://www.56.com/n_" . str_replace(":88", "", str_replace(".56.com", "", $o->img_host)) .
"_/" . str_replace(".56.com", "", $o->URL_host) .
"_/" . $o->URL_pURL .
"_/" . $o->URL_sURL .
"_/" . $o->user_id .
"_/" . $o->URL_URLid .
"_/" . $o->totaltime .
"_/" . $o->effectID .
"_/" . $o->id . ".swf";
$flv = "http://hot-chinacache.56.com/flvdownload/" . $o->URL_pURL .
"/" . $o->URL_sURL .
"/" . $o->user_id .
"@56.com_56flv_" . $o->URL_URLid . ".flv";
echo "FLASH文件路径: " . $swf;
echo "<br>";
echo "FLV文件路径: " . $flv;
$de = 0;
function decode56($str) {
global $de;
$c1 = "";
$c2 = "";
$c3 = "";
$c4 = "";
$c5 = array(-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,62,-1,-1,-1,63,52,53,54,55,56,57,58,59,60,61,-1,-1,-1,-1,-1,-1,-1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,-1,-1,-1,-1,-1,-1,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40, 41,42,43,44,45,46,47,48,49,50,51,-1,-1,-1,-1,-1);
$c6 = charCodeAt($str, 0);
$c7 = "";
$i = "";
$len = "";
$out = "";
if(!$de) {
$de = 1;
$c7 = decode56($str);
$str = substr($c7, $c6);
}
$len = strlen($str);
$i = 1;
$out = "";
while ($i < $len) {
do {
$c1 = $c5[charCodeAt($str, $i++) & 0xff];
}
while($i < $len && $c1 == -1);
if ($c1 == -1) break;
do {
$c2 = $c5[charCodeAt($str, $i++) & 0xff];
}
while ($i < $len && $c2 == -1);
if($c2 == -1) break;
$out .= chr(($c1 << 2) | (($c2 & 0x30) >> 4));
do {
$c3 = charCodeAt($str, $i++) & 0xff;
if($c3 == 61) return $out;
$c3 = $c5[$c3];
}
while ($i < $len && $c3 == -1);
if($c3 == -1) break;
$out .= chr((($c2 & 0XF) << 4) | (($c3 & 0x3C) >> 2));
do {
$c4 = charCodeAt($str, $i++) & 0xff;
if($c4 == 61) return $out;
$c4 = $c5[$c4];
}
while ($i < $len && $c4 == -1);
if ($c4 == -1) break;
$out .= chr((($c3 & 0x03) << 6) | $c4);
}
return $out;
}
function charCodeAt($str, $i){
return ord(substr($str, $i, 1));
}
//该程序仅为技术交流，交流可加QQ群: 1714987
?>
json.php
<?php
define('HTML_AJAX_JSON_SLICE', 1);
define('HTML_AJAX_JSON_IN_STR', 2);
define('HTML_AJAX_JSON_IN_ARR', 4);
define('HTML_AJAX_JSON_IN_OBJ', 8);
define('HTML_AJAX_JSON_IN_CMT', 16);
define('HTML_AJAX_JSON_LOOSE_TYPE', 10);
define('HTML_AJAX_JSON_STRICT_TYPE', 11);
class HTML_AJAX_JSON
{
function HTML_AJAX_JSON($use=HTML_AJAX_JSON_STRICT_TYPE)
{
$this->use = $use;
}
function encode($var)
{
switch(gettype($var)) {
case 'boolean':
return $var ? 'true' : 'false';
case 'NULL':
return 'null';
case 'integer':
return sprintf('%d', $var);
case 'double':
case 'float':
return sprintf('%f', $var);
case 'string': // STRINGS ARE EXPECTED TO BE IN ASCII OR UTF-8 FORMAT
$ascii = '';
$strlen_var = strlen($var);
for($c = 0; $c < $strlen_var; $c++) {
$ord_var_c = ord($var{$c});
if($ord_var_c == 0x08) {
$ascii .= '\b';
} elseif($ord_var_c == 0x09) {
$ascii .= '\t';
} elseif($ord_var_c == 0x0A) {
$ascii .= '\n';
} elseif($ord_var_c == 0x0C) {
$ascii .= '\f';
} elseif($ord_var_c == 0x0D) {
$ascii .= '\r';
} elseif(($ord_var_c == 0x22) || ($ord_var_c == 0x2F) || ($ord_var_c == 0x5C)) {
$ascii .= '\\'.$var{$c}; // double quote, slash, slosh
} elseif(($ord_var_c >= 0x20) && ($ord_var_c <= 0x7F)) {
// characters U-00000000 - U-0000007F (same as ASCII)
$ascii .= $var{$c}; // most normal ASCII chars
} elseif(($ord_var_c & 0xE0) == 0xC0) {
// characters U-00000080 - U-000007FF, mask 110XXXXX, see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c, ord($var{$c+1})); $c+=1;
$ascii .= sprintf('\u%04s', bin2hex(mb_convert_encoding($char, 'UTF-16', 'UTF-8')));
} elseif(($ord_var_c & 0xF0) == 0xE0) {
// characters U-00000800 - U-0000FFFF, mask 1110XXXX, see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c, ord($var{$c+1}), ord($var{$c+2})); $c+=2;
$ascii .= sprintf('\u%04s', bin2hex(mb_convert_encoding($char, 'UTF-16', 'UTF-8')));
} elseif(($ord_var_c & 0xF8) == 0xF0) {
// characters U-00010000 - U-001FFFFF, mask 11110XXX, see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c, ord($var{$c+1}), ord($var{$c+2}), ord($var{$c+3})); $c+=3;
$ascii .= sprintf('\u%04s', bin2hex(mb_convert_encoding($char, 'UTF-16', 'UTF-8')));
} elseif(($ord_var_c & 0xFC) == 0xF8) {
// characters U-00200000 - U-03FFFFFF, mask 111110XX, see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c, ord($var{$c+1}), ord($var{$c+2}), ord($var{$c+3}), ord($var{$c+4})); $c+=4;
$ascii .= sprintf('\u%04s', bin2hex(mb_convert_encoding($char, 'UTF-16', 'UTF-8')));
} elseif(($ord_var_c & 0xFE) == 0xFC) {
// characters U-04000000 - U-7FFFFFFF, mask 1111110X, see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c, ord($var{$c+1}), ord($var{$c+2}), ord($var{$c+3}), ord($var{$c+4}), ord($var{$c+5})); $c+=5;
$ascii .= sprintf('\u%04s', bin2hex(mb_convert_encoding($char, 'UTF-16', 'UTF-8')));
}
}
return sprintf('"%s"', $ascii);
case 'array':
if(is_array($var) && (array_keys($var) !== range(0, sizeof($var) - 1)))
return sprintf('{%s}', join(',', array_map(array($this, 'name_value'), array_keys($var), array_values($var))));
return sprintf('[%s]', join(',', array_map(array($this, 'encode'), $var)));
case 'object':
$vars = get_object_vars($var);
return sprintf('{%s}', join(',', array_map(array($this, 'name_value'), array_keys($vars), array_values($vars))));
default:
return '';
}
}
function name_value($name, $value)
{
return (sprintf("%s:%s", $this->encode(strval($name)), $this->encode($value)));
}
function reduce_string($str)
{
$str = preg_replace('#^\s*//(.+)$#m', '', $str); // eliminate single line comments in '// ...' form
$str = preg_replace('#^\s*/\*(.+)\*/#Us', '', $str); // eliminate multi-line comments in '/* ... */' form, at start of string
$str = preg_replace('#/\*(.+)\*/\s*$#Us', '', $str); // eliminate multi-line comments in '/* ... */' form, at end of string
$str = trim($str); // eliminate extraneous space
return $str;
}
function decode($str)
{
$str = $this->reduce_string($str);
switch(strtolower($str)) {
case 'true':
return true;
case 'false':
return false;
case 'null':
return null;
default:
if(is_numeric($str)) {
return ((float)$str == (integer)$str)
? (integer)$str
: (float)$str;
} elseif(preg_match('/^".+"$/s', $str) || preg_match('/^\'.+\'$/s', $str)) {
$delim = substr($str, 0, 1);
$chrs = substr($str, 1, -1);
$utf8 = '';
$strlen_chrs = strlen($chrs);
for($c = 0; $c < $strlen_chrs; $c++) {
$substr_chrs_c_2 = substr($chrs, $c, 2);
$ord_chrs_c = ord($chrs{$c});
if($substr_chrs_c_2 == '\b') {
$utf8 .= chr(0x08); $c+=1;
} elseif($substr_chrs_c_2 == '\t') {
$utf8 .= chr(0x09); $c+=1;
} elseif($substr_chrs_c_2 == '\n') {
$utf8 .= chr(0x0A); $c+=1;
} elseif($substr_chrs_c_2 == '\f') {
$utf8 .= chr(0x0C); $c+=1;
} elseif($substr_chrs_c_2 == '\r') {
$utf8 .= chr(0x0D); $c+=1;
} elseif(($delim == '"') && (($substr_chrs_c_2 == '\\"') || ($substr_chrs_c_2 == '\\\\') || ($substr_chrs_c_2 == '\\/'))) {
$utf8 .= $chrs{++$c};
} elseif(($delim == "'") && (($substr_chrs_c_2 == '\\\'') || ($substr_chrs_c_2 == '\\\\') || ($substr_chrs_c_2 == '\\/'))) {
$utf8 .= $chrs{++$c};
} elseif(preg_match('/\\\u[0-9A-F]{4}/i', substr($chrs, $c, 6))) { // single, escaped unicode character
$utf16 = chr(hexdec(substr($chrs, ($c+2), 2))) . chr(hexdec(substr($chrs, ($c+4), 2)));
$utf8 .= mb_convert_encoding($utf16, 'UTF-8', 'UTF-16');
$c+=5;
} elseif(($ord_chrs_c >= 0x20) && ($ord_chrs_c <= 0x7F)) {
$utf8 .= $chrs{$c};
} elseif(($ord_chrs_c & 0xE0) == 0xC0) {
$utf8 .= substr($chrs, $c, 2); $c += 1;
} elseif(($ord_chrs_c & 0xF0) == 0xE0) {
$utf8 .= substr($chrs, $c, 3); $c += 2;
} elseif(($ord_chrs_c & 0xF8) == 0xF0) {
$utf8 .= substr($chrs, $c, 4); $c += 3;
} elseif(($ord_chrs_c & 0xFC) == 0xF8) {
$utf8 .= substr($chrs, $c, 5); $c += 4;
} elseif(($ord_chrs_c & 0xFE) == 0xFC) {
$utf8 .= substr($chrs, $c, 6); $c += 5;
}
}
return $utf8;
} elseif(preg_match('/^\[.*\]$/s', $str) || preg_match('/^{.*}$/s', $str)) {
if($str{0} == '[') {
$stk = array(HTML_AJAX_JSON_IN_ARR);
$arr = array();
} else {
if($this->use == HTML_AJAX_JSON_LOOSE_TYPE) {
$stk = array(HTML_AJAX_JSON_IN_OBJ);
$obj = array();
} else {
$stk = array(HTML_AJAX_JSON_IN_OBJ);
$obj = new stdClass();
}
}
array_push($stk, array('what' => HTML_AJAX_JSON_SLICE, 'where' => 0, 'delim' => false));
$chrs = substr($str, 1, -1);
$chrs = $this->reduce_string($chrs);
if($chrs == '') {
if(reset($stk) == HTML_AJAX_JSON_IN_ARR) {
return $arr;
} else {
return $obj;
}
}
$strlen_chrs = strlen($chrs);
for($c = 0; $c <= $strlen_chrs; $c++) {
$top = end($stk);
$substr_chrs_c_2 = substr($chrs, $c, 2);
if(($c == $strlen_chrs) || (($chrs{$c} == ',') && ($top['what'] == HTML_AJAX_JSON_SLICE))) {
$slice = substr($chrs, $top['where'], ($c - $top['where']));
array_push($stk, array('what' => HTML_AJAX_JSON_SLICE, 'where' => ($c + 1), 'delim' => false));
if(reset($stk) == HTML_AJAX_JSON_IN_ARR) { // we are in an array, so just push an element onto the stack
array_push($arr, $this->decode($slice));
} elseif(reset($stk) == HTML_AJAX_JSON_IN_OBJ) { // we are in an object, so figure out the property name and set an element in an associative array, for now
if(preg_match('/^\s*(["\'].*[^\\\]["\'])\s*:\s*(\S.*),?$/Uis', $slice, $parts)) { // "name":value pair
$key = $this->decode($parts[1]);
$val = $this->decode($parts[2]);
if($this->use == HTML_AJAX_JSON_LOOSE_TYPE) {
$obj[$key] = $val;
} else {
$obj->$key = $val;
}
} elseif(preg_match('/^\s*(\w+)\s*:\s*(\S.*),?$/Uis', $slice, $parts)) { // name:value pair, where name is unquoted
$key = $parts[1];
$val = $this->decode($parts[2]);
if($this->use == HTML_AJAX_JSON_LOOSE_TYPE) {
$obj[$key] = $val;
} else {
$obj->$key = $val;
}
}
}
} elseif((($chrs{$c} == '"') || ($chrs{$c} == "'")) && ($top['what'] != HTML_AJAX_JSON_IN_STR)) { // found a quote, and we are not inside a string
array_push($stk, array('what' => HTML_AJAX_JSON_IN_STR, 'where' => $c, 'delim' => $chrs{$c}));
//print("Found start of string at {$c}\n");
} elseif(($chrs{$c} == $top['delim']) && ($top['what'] == HTML_AJAX_JSON_IN_STR) && (($chrs{$c - 1} != "\\") || ($chrs{$c - 1} == "\\" && $chrs{$c - 2} == "\\"))) { // found a quote, we're in a string, and it's not escaped
array_pop($stk);
//print("Found end of string at {$c}: ".substr($chrs, $top['where'], (1 + 1 + $c - $top['where']))."\n");
} elseif(($chrs{$c} == '[') && in_array($top['what'], array(HTML_AJAX_JSON_SLICE, HTML_AJAX_JSON_IN_ARR, HTML_AJAX_JSON_IN_OBJ))) { // found a left-bracket, and we are in an array, object, or slice
array_push($stk, array('what' => HTML_AJAX_JSON_IN_ARR, 'where' => $c, 'delim' => false));
//print("Found start of array at {$c}\n");
} elseif(($chrs{$c} == ']') && ($top['what'] == HTML_AJAX_JSON_IN_ARR)) { // found a right-bracket, and we're in an array
array_pop($stk);
//print("Found end of array at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
} elseif(($chrs{$c} == '{') && in_array($top['what'], array(HTML_AJAX_JSON_SLICE, HTML_AJAX_JSON_IN_ARR, HTML_AJAX_JSON_IN_OBJ))) { // found a left-brace, and we are in an array, object, or slice
array_push($stk, array('what' => HTML_AJAX_JSON_IN_OBJ, 'where' => $c, 'delim' => false));
//print("Found start of object at {$c}\n");
} elseif(($chrs{$c} == '}') && ($top['what'] == HTML_AJAX_JSON_IN_OBJ)) { // found a right-brace, and we're in an object
array_pop($stk);
//print("Found end of object at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
} elseif(($substr_chrs_c_2 == '/*') && in_array($top['what'], array(HTML_AJAX_JSON_SLICE, HTML_AJAX_JSON_IN_ARR, HTML_AJAX_JSON_IN_OBJ))) { // found a comment start, and we are in an array, object, or slice
array_push($stk, array('what' => HTML_AJAX_JSON_IN_CMT, 'where' => $c, 'delim' => false));
$c++;
//print("Found start of comment at {$c}\n");
} elseif(($substr_chrs_c_2 == '*/') && ($top['what'] == HTML_AJAX_JSON_IN_CMT)) { // found a comment end, and we're in one now
array_pop($stk);
$c++;
for($i = $top['where']; $i <= $c; $i++)
$chrs = substr_replace($chrs, ' ', $i, 1);
//print("Found end of comment at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
}
}
if(reset($stk) == HTML_AJAX_JSON_IN_ARR) {
return $arr;
} elseif(reset($stk) == HTML_AJAX_JSON_IN_OBJ) {
return $obj;
}
}
}
}
}
if ( !function_exists("json_encode") || !function_exists("json_decode") ) {
include_once "json.php";
function json_encode($data) {
$json = new HTML_AJAX_JSON();
return $json->encode($data);
}
function json_decode($data) {
$json = new HTML_AJAX_JSON();
return $json->decode($data);
}
}
?>
php 无极分类(递归)实现代码
php 文件上传代码(限制jpg文件)
php下将XML转换为数组
PHP 巧用数组降低程序的时间复杂度
使用PHP获取网络文件的实现代码
php 文章采集正则代码
PHP simple_html_dom.php+正则 采集文章代码
PHP下编码转换函数mb_convert_encoding与iconv的使用说明
PHP 采集程序中常用的函数
Php 构造函数construct的前下划线是双的_
php self,$this,const,static,->的使用
PHP iconv 函数转gb2312的bug解决方法
php面向对象全攻略 （十） final static const关键字的使用
火车采集器 免费版使出收费版本功能实现原理
火车头discuz6.1 完美采集的php接口文件
Uchome1.2 1.5 代码学习 common.php
PHPMailer邮件类利用smtp.163.com发送邮件方法
首页四格,首页五格For6.0(GBK)(UTF-8)[12种组合][9-18][版主安装测试通过]
从MySQL数据库表中取出随机数据的代码
小结下MySQL中文乱码，phpmyadmin乱码，php乱码 产生原因及其解决方法第1/3页
海河写的 Discuz论坛帖子调用js的php代码
PHP下几种删除目录的方法总结
wordpress之wp-settings.php
PHP4和PHP5性能测试和对比 测试代码与环境
中国站长站 For Dede4.0 采集规则
15种PHP Encoder的比较
给apache2.2加上mod_encoding模块後 php5.2.0 处理url出现bug
手把手教你使用DedeCms V3的在线采集图文教程
dede3.1分页文字采集过滤规则详说(图文教程)续四
dede3.1分页文字采集过滤规则详说(图文教程)续二
dede3.1分页文字采集过滤规则详说(图文教程)
完美解决dedecms中的[html][/html]和[code][/code]问题
理解PHP5中static和const关键字的区别
对Session和Cookie的区分与解释
PHP通过COM使用ADODB的简单例子
COM in PHP (winows only)
怎样在PHP中通过ADO调用Asscess数据库和COM程序