1.获取页面闭合带id标签数据
1 <?php 2 header("Content-type: text/html; charset=utf-8"); 3 /** 4 * $tag_id HTML tag_id like 5 * $url web url 6 * $tag HTML tag 7 * $data HTML data if $url set to false 8 * @example echo getWebTag('','http://mail.163.com/html/mail_intro/','ul'); 9 */ 10 function getWebTag($tag_id,$url=false,$tag='div',$data=false){ 11 if($url !== false){ 12 $data = file_get_contents( $url ); 13 } 14 $charset_pos = stripos($data,'charset'); 15 if($charset_pos) { 16 if(stripos($data,'utf-8',$charset_pos)) { 17 $data = iconv('utf-8','utf-8',$data); 18 }else if(stripos($data,'gb2312',$charset_pos)) { 19 $data = iconv('gb2312','utf-8',$data); 20 }else if(stripos($data,'gbk',$charset_pos)) { 21 $data = iconv('gbk','utf-8',$data); 22 } 23 } 24 25 preg_match_all('/<'.$tag.'/i',$data,$pre_matches,PREG_OFFSET_CAPTURE); //获取所有div前缀 26 preg_match_all('/<\/'.$tag.'/i',$data,$suf_matches,PREG_OFFSET_CAPTURE); //获取所有div后缀 27 $hit = strpos($data,$tag_id); 28 if($hit == -1) return false; //未命中 29 $divs = array(); //合并所有div 30 foreach($pre_matches[0] as $index=>$pre_div){ 31 $divs[(int)$pre_div[1]] = 'p'; 32 $divs[(int)$suf_matches[0][$index][1]] = 's'; 33 } 34 35 //对div进行排序 36 $sort = array_keys($divs); 37 asort($sort); 38 39 $count = count($pre_matches[0]); 40 foreach($pre_matches[0] as $index=>$pre_div){ 41 //<div $hit <div+1 时div被命中 42 if(($pre_matches[0][$index][1] < $hit) && ($hit < $pre_matches[0][$index+1][1])){ 43 $deeper = 0; 44 //弹出被命中div前的div 45 while(array_shift($sort) != $pre_matches[0][$index][1] && ($count--)) continue; 46 //对剩余div进行匹配，若下一个为前缀，则向下一层，$deeper加1， 47 //否则后退一层，$deeper减1，$deeper为0则命中匹配，计算div长度 48 foreach($sort as $key){ 49 if($divs[$key] == 'p') $deeper++; 50 else if($deeper == 0) { 51 $length = $key-$pre_matches[0][$index][1]; 52 break; 53 }else { 54 $deeper--; 55 } 56 } 57 $hitDivString = substr($data,$pre_matches[0][$index][1],$length).'</'.$tag.'>'; 58 break; 59 } 60 } 61 return $hitDivString; 62 } 63 64 echo getWebTag('>); 65 echo getWebTag('>); 66 echo getWebTag('>); 67 68 //End_php
1.1 由（1）改进为获取页面任意标签，参考《颠覆想象的php解析获取跨域HTML标签》
1 <?php 2 header("Content-type: text/html; charset=utf-8"); 3 /** 4 * $tag_id HTML tag_id like 5 * $url web url 6 * $tag HTML tag 7 * $data HTML data if $url set to false 8 * $first Only get the first match 9 * @example 10 var_dump(getWebTag('','http://mail.163.com/html/mail_intro/','ul')); 11 */ 12 function getWebTag($tag_id,$url=false,$tag='div',$data=false,$first=false){ 13 //默认采用URL获取数据 14 if($url !== false){ 15 $data = file_get_contents( $url ); 16 } 17 //页面编码判定及转码 18 $charset_pos = stripos($data,'charset'); 19 if($charset_pos) { 20 if(stripos($data,'charset=utf-8',$charset_pos)) { 21 $data = iconv('utf-8','utf-8',$data); 22 }else if(stripos($data,'charset=gb2312',$charset_pos)) { 23 $data = iconv('gb2312','utf-8',$data); 24 }else if(stripos($data,'charset=gbk',$charset_pos)) { 25 $data = iconv('gbk','utf-8',$data); 26 } 27 } 28 29 //匹配命中标签至数组$hits 30 preg_match_all('/<'.$tag.'[^<]*?'.$tag_id.'/i',$data,$hits,PREG_OFFSET_CAPTURE); 31 if(count($hits[0]) === 0) { //未命中，直接返回 32 return '没有匹配项！'; 33 } 34 35 preg_match_all('/<'.$tag.'/i',$data,$pre_matches,PREG_OFFSET_CAPTURE); //获取所有HTML标签前缀 36 preg_match_all('/<\/'.$tag.'/i',$data,$suf_matches,PREG_OFFSET_CAPTURE); //获取所有HTML标签后缀 37 38 //判断是否<div></div>格式，是则添加结束标签，否则为false; 注：img、input等可能不是这种格式，此时$suf_matches[0]为空。 39 if(!empty($suf_matches[0])) $endTag = '</'.$tag.'>'; 40 else $endTag = false; 41 42 //合并所有HTML标签 43 $htmltags = array(); 44 if($endTag !== false){ 45 foreach($pre_matches[0] as $index=>$pre_div){ 46 $htmltags[(int)$pre_matches[0][$index][1]] = 'p'; 47 $htmltags[(int)$suf_matches[0][$index][1]] = 's'; 48 } 49 }else{ 50 foreach($pre_matches[0] as $index=>$pre_div){ 51 //非<div></div>格式，获取前缀下标后的第一个>作为标签结束 52 $suf_matches[0][$index][1] = stripos($data,'>',$pre_matches[0][$index][1])+1; 53 54 $htmltags[(int)$pre_matches[0][$index][1]] = 'p'; 55 $htmltags[(int)$suf_matches[0][$index][1]] = 's'; 56 } 57 } 58 //对所有HTML标签按index进行排序 59 $sort = array_keys($htmltags); 60 asort($sort); 61 62 //开始获取命中字符串 63 $hitTagStrings = array(); 64 foreach($hits[0] as $hit){ 65 $hit = $hit[1]; //获取命中index 66 67 $count = count($sort); //循环控制，$count--避免无限循环 68 foreach($pre_matches[0] as $index=>$pre_div){ 69 //最后一个$pre_matches[0][$index+1]会造成数组出界，因此设置其index等于总长度 70 if(!isset($pre_matches[0][$index+1][1])) $pre_matches[0][$index+1][1] = strlen($data); 71 72 //<div $hit <div+1 时div被命中 73 if(($pre_matches[0][$index][1] <= $hit) && ($hit < $pre_matches[0][$index+1][1])){ 74 $deeper = 0; 75 //弹出被命中HTML标签前的所有HTML标签 76 while(array_shift($sort) != $pre_matches[0][$index][1] && ($count--)) continue; 77 //对剩余HTML标签进行匹配，若下一个为前缀(p)，则向下一层，$deeper加1， 78 //否则后退一层，$deeper减1，$deeper为0则命中匹配结束标记，计算div长度 79 foreach($sort as $key){ 80 if($htmltags[$key] == 'p') { //进入子层 81 $deeper++; 82 }else if($deeper == 0) { //碰到结束标记 83 $length = $key-$pre_matches[0][$index][1]; //长度等于结束标记index 减去 前缀index 84 break; 85 }else { //碰到子层结束标记 86 $deeper--; 87 } 88 } 89 $hitTagStrings[] = substr($data,$pre_matches[0][$index][1],$length).$endTag; 90 break; 91 } 92 } 93 //若只获取第一个匹配项，退出循环 94 if($first && count($hitTagStrings) == 1) break; 95 } 96 97 return $hitTagStrings; 98 } 99 100 //直接用例 101 var_dump(getWebTag('>)); 102 103 /* //注释这句即可显示 104 //ajax请求用例，必要参数：dataType:'json',type:'POST' 105 $tag_id = urldecode($_POST['tag_id']); 106 $url = urldecode($_POST['url']); 107 $tag = isset($_POST['tag'])? urldecode($_POST['tag']) : 'div'; 108 $data = urldecode($_POST['data']); 109 $first = (urldecode($_POST['first']) == 'checked')? true : false; 110 foreach($_POST as $key => $value){ 111 if($value == 'EmPtYValue') $$key = false; 112 } 113 echo json_encode(getWebTag($tag_id,$url,$tag,$data,$first)); 114 //*/ 115 116 //End_php
2.虚拟POST数据至远程服务器并获取返回数据
1 <?php 2 header("Content-type: text/html; charset=utf-8"); 3 /** 4 * $url web url 5 * $post POST data 6 * @example 7 $data = array ( 8 'type' => 'text', 9 'inputValue' => '哈哈' 10 ); 11 $result = Post('http://tool.anzhuoxiazai.com:80//servlet/QRServlet', $data); 12 echo str_replace("src='","src='http://tool.anzhuoxiazai.com/",$result); 13 */ 14 function Post($url, $post = null) { 15 $context = array(); 16 if (is_array($post)) { 17 ksort($post); 18 $context['http'] = array ( 19 'timeout'=>60, 20 'method' => 'POST', 21 'content' => http_build_query($post) 22 ); 23 } 24 return file_get_contents($url, false, stream_context_create($context)); 25 } 26 27 $data = array ( 28 'type' => 'text', 29 'inputValue' => '哈哈' 30 ); 31 $result = Post('http://tool.anzhuoxiazai.com:80//servlet/QRServlet', $data); 32 echo str_replace("src='","src='http://tool.anzhuoxiazai.com/",$result); 33 //End_php
3.文件夹复制
1 /** 2 * Copy file or folder from source to destination, it can do 3 * recursive copy as well and is very smart 4 * It recursively creates the dest file or directory path if there weren't exists 5 * Situtaions : 6 * - Src:/home/test/file.txt ,Dst:/home/test/b ,Result:/home/test/b -> If source was file copy file.txt name with b as name to destination 7 * - Src:/home/test/file.txt ,Dst:/home/test/b/ ,Result:/home/test/b/file.txt -> If source was file Creates b directory if does not exsits and copy file.txt into it 8 * - Src:/home/test ,Dst:/home/ ,Result:/home/test/** -> If source was directory copy test directory and all of its content into dest 9 * - Src:/home/test/ ,Dst:/home/ ,Result:/home/**-> if source was direcotry copy its content to dest 10 * - Src:/home/test ,Dst:/home/test2 ,Result:/home/test2/** -> if source was directoy copy it and its content to dest with test2 as name 11 * - Src:/home/test/ ,Dst:/home/test2 ,Result:->/home/test2/** if source was directoy copy it and its content to dest with test2 as name 12 * @todo 13 * - Should have rollback technique so it can undo the copy when it wasn't successful 14 * - Auto destination technique should be possible to turn off 15 * - Supporting callback function 16 * - May prevent some issues on shared enviroments : http://us3.php.net/umask 17 * @param $source //file or folder 18 * @param $dest ///file or folder 19 * @param $options //folderPermission,filePermission 20 * @return boolean 21 */ 22 function smartCopy($source, $dest, $options=array('folderPermission'=>0755,'filePermission'=>0755)) 23 { 24 $result=false; 25 26 if (is_file($source)) { 27 if ($dest[strlen($dest)-1]=='/') { 28 if (!file_exists($dest)) { 29 cmfcDirectory::makeAll($dest,$options['folderPermission'],true); 30 } 31 $__dest=$dest."/".basename($source); 32 } else { 33 $__dest=$dest; 34 } 35 $result=copy($source, $__dest); 36 chmod($__dest,$options['filePermission']); 37 38 } elseif(is_dir($source)) { 39 if ($dest[strlen($dest)-1]=='/') { 40 if ($source[strlen($source)-1]=='/') { 41 //Copy only contents 42 } else { 43 //Change parent itself and its contents 44 $dest=$dest.basename($source); 45 @mkdir($dest); 46 chmod($dest,$options['filePermission']); 47 } 48 } else { 49 if ($source[strlen($source)-1]=='/') { 50 //Copy parent directory with new name and all its content 51 @mkdir($dest,$options['folderPermission']); 52 chmod($dest,$options['filePermission']); 53 } else { 54 //Copy parent directory with new name and all its content 55 @mkdir($dest,$options['folderPermission']); 56 chmod($dest,$options['filePermission']); 57 } 58 } 59 60 $dirHandle=opendir($source); 61 while($file=readdir($dirHandle)) 62 { 63 if($file!="." && $file!="..") 64 { 65 if(!is_dir($source."/".$file)) { 66 $__dest=$dest."/".$file; 67 } else { 68 $__dest=$dest."/".$file; 69 } 70 //echo "$source/$file ||| $__dest<br />"; 71 $result=smartCopy($source."/".$file, $__dest, $options); 72 } 73 } 74 closedir($dirHandle); 75 76 } else { 77 $result=false; 78 } 79 return $result; 80 }
4.文件遍历（可匹配模式）
1 /** 2 * 遍历目录并获取所有目录即文件，以数组array('dirs'=>$dirs,'files'=>$files)方式返回。 3 * @param $dir //搜索目录 4 * @param $pattern // '*'搜索全部文件，可以智能匹配，如*.jpg 搜索jpg文件，*.{jpg,png}搜索jpg和png文件，区分大小写！！ 5 * @param $skip //排除遍历文件，如"*.{jpg,png}"排除.jpg和.png类型文件 6 * @param $subInclude //默认遍历子目录，$subInclude设置为false则仅遍历当前目录 7 * @param @flag //glob函数的标记，有效标记如下： 8 GLOB_MARK - 在每个返回的项目中加一个斜线 9 GLOB_NOSORT - 按照文件在目录中出现的原始顺序返回（不排序） 10 GLOB_NOCHECK - 如果没有文件匹配则返回用于搜索的模式 11 GLOB_NOESCAPE - 反斜线不转义元字符 12 GLOB_BRACE - 扩充 {a,b,c} 来匹配 'a'，'b' 或 'c' 13 GLOB_ONLYDIR - 仅返回与模式匹配的目录项 14 */ 15 function scandir_through($dir,$pattern='*',$skip=false,$subInclude=true,$flag=GLOB_BRACE){ 16 $dirs = array(); 17 $files = array(); 18 //获取当前目录下所有文件及文件夹 19 $items = glob($dir . '/*'); 20 21 //遍历所有项目，若设置$subInclude为true，则继续遍历子目录 22 for ($i = 0; $i < count($items); $i++) { 23 if ($subInclude && is_dir($items[$i])) { 24 $dirs[] = iconv('gb2312','utf-8',$items[$i]); 25 $add = glob($items[$i] . '/*'); 26 if($add === false) $add = array(); 27 $items = array_merge($items, $add); 28 }else { 29 $slash = strrpos($items[$i],'/'); 30 $dir = substr($items[$i],0,$slash); 31 //若当前文件匹配文件查找模式$pattern，则加入$files数组中 32 if(in_array($items[$i],glob($dir.'/'.$pattern,$flag)) && (($skip===false) || !in_array($items[$i],glob($dir.'/'.$skip,$flag)))) { 33 $items[$i] = iconv('gb2312','utf-8',$items[$i]); 34 $file = substr($items[$i],$slash+1); 35 $files[] = $items[$i]; 36 } 37 } 38 } 39 return array('dirs'=>$dirs,'files'=>$files); 40 }
5.zip压缩文件夹
1 /** 2 * 打包文件夹成zip文件函数 3 * @param $path //打包文件夹路径 4 * @param $zip //ZipArchive 对象 5 */ 6 function addFileToZip($path, $zip) { 7 $handler = opendir($path); //打开当前文件夹由$path指定。 8 /* 9 循环的读取文件夹下的所有文件和文件夹 10 其中$filename = readdir($handler)是每次循环的时候将读取的文件名赋值给$filename， 11 为了不陷于死循环，所以还要让$filename !== false。 12 一定要用!==，因为如果某个文件名如果叫'0'，或者某些被系统认为是代表false，用!=就会停止循环 13 */ 14 while (($filename = readdir($handler)) !== false) { 15 if ($filename != "." && $filename != "..") {//文件夹文件名字为'.'和‘..’，不要对他们进行操作 16 if (is_dir($path . "/" . $filename)) {// 如果读取的某个对象是文件夹，则递归 17 addFileToZip($path . "/" . $filename, $zip); 18 } else { //将文件加入zip对象 19 $zip->addFile($path . "/" . $filename); 20 } 21 } 22 } 23 @closedir($path); 24 } 25 //运用 26 $zip = new ZipArchive(); 27 if ($zip->open('test.zip', ZipArchive::OVERWRITE) === TRUE) { 28 addFileToZip('./testdir', $zip); //调用方法，对要打包的根目录进行操作，并将ZipArchive的对象传递给方法 29 $zip->close(); //关闭处理的zip文件 30 }
6.打印两个日期之间的日期
1 function prDates($start, $end) { 2 //将ISO Date 转成 Timestamp 3 $dt_start = strtotime($start); 4 $dt_end = strtotime($end); 5 do { 6 //将 Timestamp 转成 ISO Date 输出 7 echo date('Y-m-d', $dt_start).PHP_EOL; 8 } while (($dt_start += 86400) <= $dt_end); // 重复 Timestamp + 1 天(86400), 直至大于结束日期中止 9 }
7.RC4加密算法
1 /* 2 * rc4加密算法，二次加密即可还原 3 * $pwd 密钥 4 * $data 要加密的数据 5 */ 6 function rc4 ($pwd, $data)//$pwd密钥 $data需加密字符串 7 { 8 $key[] =""; 9 $box[] =""; 10 11 $pwd_length = strlen($pwd); 12 $data_length = strlen($data); 13 14 for ($i = 0; $i < 256; $i++) 15 { 16 $key[$i] = ord($pwd[$i % $pwd_length]); 17 $box[$i] = $i; 18 } 19 20 for ($j = $i = 0; $i < 256; $i++) 21 { 22 $j = ($j + $box[$i] + $key[$i]) % 256; 23 $tmp = $box[$i]; 24 $box[$i] = $box[$j]; 25 $box[$j] = $tmp; 26 } 27 28 for ($a = $j = $i = 0; $i < $data_length; $i++) 29 { 30 $a = ($a + 1) % 256; 31 $j = ($j + $box[$a]) % 256; 32 33 $tmp = $box[$a]; 34 $box[$a] = $box[$j]; 35 $box[$j] = $tmp; 36 37 $k = $box[(($box[$a] + $box[$j]) % 256)]; 38 $cipher .= chr(ord($data[$i]) ^ $k); 39 } 40 41 return $cipher; 42 }
8.utf8_substr UTF8编码字符串截取，解决中英文混杂截取
1 /** 2 * $sting 输入字符串 3 * $start 截取起始位，默认为0 4 * $length 截取长度，中英文长度都为1，默认为''，跟输入负数一样截取至字符串结束。 5 * [\x00-\x7F] 匹配英文字符 6 * [\xC0-\xFF][\x80-\xBF]+ 匹配中文字符 7 * 模式修正符s 将换行当成普通字符，此时.*能匹配包括换行任意字符 8 */ 9 function utf8_substr($string, $start=0, $length=''){ 10 return preg_replace('#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){0,'.$start.'}' 11 .'((?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){0,'.$length.'}).*#s','$1',$string); 12 }
9.创建透明图片
$image = imagecreatetruecolor(300,300); $transparent = imagecolorallocatealpha($image, 255, 255, 255,127); //创建透明背景色 imagecolortransparent($img, $transparent); imagefill($image, 0, 0, $transparent); //填充透明背景色