查询表格位于:
http://www.pjoke.com/tools/domain/deletingdomain.html
这个待删除的域名数据来自pool.com的Pending Delete List页面。页面上有下载链接http://www.pool.com/Downloads/PoolDeletingDomainsList.zip
是一个zip文件。这个文件是每日更新的,所以要做的事情是:
- 下载这个zip文件
- 解压这个zip文件
- 读文件中的数据,存储到数据库中
- 做数据库的查询页面
- 将上述1~3的程序设置成cron,每日定时运行
包含123步的php文件:
第一步,下载:
copy(”http://pool.com/Downloads/PoolDeletingDomainsList.zip”, “pool.zip”);
第二步,解压,这里使用faisun提供的程序里面的unzip类,稍作改动:
class zip
{
var $total_files = 0;
var $total_folders = 0;
function Extract ( $zn, $to, $index = Array(-1) )
{
$ok = 0; $zip = @fopen($zn,’rb’);
if(!$zip) return(-1);
$cdir = $this->ReadCentralDir($zip,$zn);
$pos_entry = $cdir['offset'];
if(!is_array($index)){ $index = array($index); }
for($i=0; $index[$i];$i++){
if(intval($index[$i])!=$index[$i]||$index[$i]>$cdir['entries'])
return(-1);
}
for ($i=0; $i<$cdir['entries']; $i++)
{
@fseek($zip, $pos_entry);
$header = $this->ReadCentralFileHeaders($zip);
$header['index'] = $i; $pos_entry = ftell($zip);
@rewind($zip); fseek($zip, $header['offset']);
if(in_array(”-1″,$index)||in_array($i,$index))
$stat[$header['filename']]=$this->ExtractFile($header, $to, $zip);
}
fclose($zip);
return $stat;
}
function ReadFileHeader($zip)
{
$binary_data = fread($zip, 30);
$data = unpack(’vchk/vid/vversion/vflag/vcompression/vmtime/vmdate/Vcrc/Vcompressed_size/Vsize/vfilename_len/vextra_len’, $binary_data);
$header['filename'] = fread($zip, $data['filename_len']);
if ($data['extra_len'] != 0) {
$header['extra'] = fread($zip, $data['extra_len']);
} else { $header['extra'] = ”; }
$header['compression'] = $data['compression'];$header['size'] = $data['size'];
$header['compressed_size'] = $data['compressed_size'];
$header['crc'] = $data['crc']; $header['flag'] = $data['flag'];
$header['mdate'] = $data['mdate'];$header['mtime'] = $data['mtime'];
if ($header['mdate'] && $header['mtime']){
$hour=($header['mtime']&0xF800)>>11;$minute=($header['mtime']&0×07E0)>>5;
$seconde=($header['mtime']&0×001F)*2;$year=(($header['mdate']&0xFE00)>>9)+1980;
$month=($header['mdate']&0×01E0)>>5;$day=$header['mdate']&0×001F;
$header['mtime'] = mktime($hour, $minute, $seconde, $month, $day, $year);
}else{$header['mtime'] = time();}
$header['stored_filename'] = $header['filename'];
$header['status'] = “ok”;
return $header;
}
function ReadCentralFileHeaders($zip){
$binary_data = fread($zip, 46);
$header = unpack(’vchkid/vid/vversion/vversion_extracted/vflag/vcompression/vmtime/vmdate/Vcrc/Vcompressed_size/Vsize/vfilename_len/vextra_len/vcomment_len/vdisk/vinternal/Vexternal/Voffset’, $binary_data);
if ($header['filename_len'] != 0)
$header['filename'] = fread($zip,$header['filename_len']);
else $header['filename'] = ”;
if ($header['extra_len'] != 0)
$header['extra'] = fread($zip, $header['extra_len']);
else $header['extra'] = ”;
if ($header['comment_len'] != 0)
$header['comment'] = fread($zip, $header['comment_len']);
else $header['comment'] = ”;
if ($header['mdate'] && $header['mtime'])
{
$hour = ($header['mtime'] & 0xF800) >> 11;
$minute = ($header['mtime'] & 0×07E0) >> 5;
$seconde = ($header['mtime'] & 0×001F)*2;
$year = (($header['mdate'] & 0xFE00) >> 9) + 1980;
$month = ($header['mdate'] & 0×01E0) >> 5;
$day = $header['mdate'] & 0×001F;
$header['mtime'] = mktime($hour, $minute, $seconde, $month, $day, $year);
} else {
$header['mtime'] = time();
}
$header['stored_filename'] = $header['filename'];
$header['status'] = ‘ok’;
if (substr($header['filename'], -1) == ‘/’)
$header['external'] = 0×41FF0010;
return $header;
}
function ReadCentralDir($zip,$zip_name){
$size = filesize($zip_name);
if ($size < 277) $maximum_size = $size;
else $maximum_size=277;
@fseek($zip, $size-$maximum_size);
$pos = ftell($zip); $bytes = 0×00000000;
while ($pos < $size){
$byte = @fread($zip, 1); $bytes=($bytes <<
| ord($byte);
if ($bytes == 0×504b0506 or $bytes == 0×2e706870504b0506){ $pos++;break;} $pos++;
}
$fdata=fread($zip,18);
$data=@unpack(’vdisk/vdisk_start/vdisk_entries/ventries/Vsize/Voffset/vcomment_size’,$fdata);
if ($data['comment_size'] != 0) $centd['comment'] = fread($zip, $data['comment_size']);
else $centd['comment'] = ”;
$centd['entries'] = $data['entries'];
$centd['disk_entries'] = $data['disk_entries'];
$centd['offset'] = $data['offset'];$centd['disk_start'] = $data['disk_start'];
$centd['size'] = $data['size']; $centd['disk'] = $data['disk'];
return $centd;
}
function ExtractFile($header,$to,$zip){
$header = $this->readfileheader($zip);
if(substr($to,-1)!=”/”) $to.=”/”;
if($to==’./’) $to = ”;
$pth = explode(”/”,$to.$header['filename']);
$mydir = ”;
for($i=0;$i<count($pth)-1;$i++){
if(!$pth[$i]) continue;
$mydir .= $pth[$i].”/”;
if((!is_dir($mydir) && @mkdir($mydir,0777)) || (($mydir==$to.$header['filename'] || ($mydir==$to && $this->total_folders==0)) && is_dir($mydir)) ){
@chmod($mydir,0777);
$this->total_folders ++;
echo “<input name=’dfile[]‘ type=’checkbox’ value=’$mydir’ checked> <a href=’$mydir’ target=’_blank’>Dir: $mydir</a><br>”;
}
}
if(strrchr($header['filename'],’/')==’/') return;
if (!($header['external']==0×41FF0010)&&!($header['external']==16)){
if ($header['compression']==0){
$fp = @fopen($to.$header['filename'], ‘wb’);
if(!$fp) return(-1);
$size = $header['compressed_size'];
while ($size != 0){
$read_size = ($size < 2048 ? $size : 2048);
$buffer = fread($zip, $read_size);
$binary_data = pack(’a’.$read_size, $buffer);
@fwrite($fp, $binary_data, $read_size);
$size -= $read_size;
}
fclose($fp);
touch($to.$header['filename'], $header['mtime']);
}else{
$fp = @fopen($to.$header['filename'].’.gz’,'wb’);
if(!$fp) return(-1);
$binary_data = pack(’va1a1Va1a1′, 0×8b1f, Chr($header['compression']),
Chr(0×00), time(), Chr(0×00), Chr(3));
fwrite($fp, $binary_data, 10);
$size = $header['compressed_size'];
while ($size != 0){
$read_size = ($size < 1024 ? $size : 1024);
$buffer = fread($zip, $read_size);
$binary_data = pack(’a’.$read_size, $buffer);
@fwrite($fp, $binary_data, $read_size);
$size -= $read_size;
}
$binary_data = pack(’VV’, $header['crc'], $header['size']);
fwrite($fp, $binary_data,8); fclose($fp);
$gzp = @gzopen($to.$header['filename'].’.gz’,'rb’) or die(”Cette archive est compress閑”);
if(!$gzp) return(-2);
$fp = @fopen($to.$header['filename'],’wb’);
if(!$fp) return(-1);
$size = $header['size'];
while ($size != 0){
$read_size = ($size < 2048 ? $size : 2048);
$buffer = gzread($gzp, $read_size);
$binary_data = pack(’a’.$read_size, $buffer);
@fwrite($fp, $binary_data, $read_size);
$size -= $read_size;
}
fclose($fp); gzclose($gzp);
touch($to.$header['filename'], $header['mtime']);
@unlink($to.$header['filename'].’.gz’);
}
}
$this->total_files ++;
echo “<input name=’dfile[]‘ type=’checkbox’ value=’$to$header[filename]‘ checked> <a href=’$to$header[filename]‘ target=’_blank’>File: $to$header[filename]</a><br>”;
return true;
}
// end class
}
$z = new Zip;
$result=$z->Extract(”pool.zip”,”./pool/”); //解压到./pool/目录下
第三步,读解开的文件,并插入到数据库中:
$filename = “./pool/PoolDeletingDomainsList.txt”;
if (!file_exists($filename)) exit;
$fp = fopen($filename, “r”);
if ($fp) {
$jkdb->query(”truncate pooldrop”);//$jkdb是一个数据库操作类的实例
$i = 0;
$tmpstr = “”;
while ($buffer = fgets($fp, 256)) {
$res = tproceed($buffer);
if ($i % 100 != 0) $tmpstr .= “,”;
$tmpstr .= $res;
$i = $i + 1;
if ($i % 100 == 0) { //每100行的数据,执行一次数据库插入,表名为pooldrop, name是域名,type是域名后缀,date是删除日期
$sqlstr = “insert into pooldrop (`name`, `type`, `date`) values “.$tmpstr;
$jkdb->query($sqlstr);
$tmpstr = “”;
}
}
if ($i % 100 != 0) {
$sqlstr = “insert into pooldrop (`name`, `type`, `date`) values “.$tmpstr;
$jkdb->query($sqlstr);
}
echo $i.” records”;
fclose($fp);
}
function tproceed($buf) {
$pat = ‘/(.*)\.([a-z]{2,4})\,([0-9]{2})\/([0-9]{2})\/([0-9]{4})\,([a-zA-Z]*)/i’;//提取每行的相关数据
preg_match_all($pat, $buf, $m);
return “(’”.$m[1][0].”‘,’”.$m[2][0].”‘,’”.$m[5][0].$m[3][0].$m[4][0].”‘)”;
}
太晚了,明天再写数据库查询部分。之所以要自己把数据抓下来再查询,是因为pool.com所提供的查询页面限制条件实在太少。
第四,简单做了个查询页面:
http://www.pjoke.com/tools/domain/deletingdomain.html
功能:
1.指定查询的域名后缀
2.指定域名中是否包含连接符“-”
3.指定域名中是否包含数字0-9
4.指定域名的最大长度和最小长度
5.指定域名中是否包含关键词,且关键词的位置分别在开头/结尾/任意位置
第五,在godaddy的cron里面将这个php设置成每天运行一次。
到此,基本上完成了。