php解压有时会失败

采集一个网站的数据时，返回的是以chunked编码，gzip压缩的文档，该网站的服务器显示是IIS，。。。

解码chunked没问题，但是解压gzip压缩文档时，偶尔会失败，这样就影响我提取下一组请求连接了。。。

解压10组左右，就会出现解压失败的情况。。

这是解压前的数据：

解压后的数据：

显然在最后一组，解压失败了。。

这是尝试用过的三组方法：

 private function _deCompressData()   {       if($this->is_gzip) {          $this->response_body =  gzinflate(substr($this->response_body,10));           //         <p>+本文来源gao!%daima.com搞$代*!码9网(</p><strong>搞gaodaima代码</strong>  //           if($temp = gzdecode($this->response_body)) {//               $this->response_body = $temp;//           } else {//              $this->response_body =  $this->mygzdecode($this->response_body);//           }                     //$this->response_body =  $this->mygzdecode($this->response_body);             //         $this->response_body = gzdecode($this->response_body);       }   }

mygzdecode函数是这一个

 /**    * @desc 自定义解压函数    */   function mygzdecode($data, &$filename = '', &$error = '', $maxlength = null)    {        $len = strlen($data);        if ($len < 18 || strcmp(substr($data, 0, 2), "\x1f\x8b")) {            $error = "Not in GZIP format.";            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) {            $error = "Reserved bits not allowed.";            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            }            $extralen = unpack("v", substr($data, 8, 2));            $extralen = $extralen[1];            if ($len - $headerlen - 2 - $extralen < 8) {                return false;  // invalid            }            $extra = substr($data, 10, $extralen);            $headerlen += 2 + $extralen;        }        $filenamelen = 0;        $filename = "";        if ($flags & 8) {            // C-style string            if ($len - $headerlen - 1 < 8) {                return false; // invalid            }            $filenamelen = strpos(substr($data, $headerlen), chr(0));            if ($filenamelen === false || $len - $headerlen - $filenamelen - 1 < 8) {                return false; // invalid            }            $filename = substr($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            }            $commentlen = strpos(substr($data, $headerlen), chr(0));            if ($commentlen === false || $len - $headerlen - $commentlen - 1 < 8) {                return false;    // Invalid header format            }            $comment = substr($data, $headerlen, $commentlen);            $headerlen += $commentlen + 1;        }        $headercrc = "";        if ($flags & 2) {            // 2-bytes (lowest order) of CRC32 on header present            if ($len - $headerlen - 2 < 8) {                return false;    // invalid            }            $calccrc = crc32(substr($data, 0, $headerlen)) & 0xffff;            $headercrc = unpack("v", substr($data, $headerlen, 2));            $headercrc = $headercrc[1];            if ($headercrc != $calccrc) {                $error = "Header checksum failed.";                return false;    // Bad header CRC            }            $headerlen += 2;        }        // GZIP FOOTER        $datacrc = unpack("V", substr($data, -8, 4));        $datacrc = sprintf('%u', $datacrc[1] & 0xFFFFFFFF);        $isize = unpack("V", substr($data, -4));        $isize = $isize[1];        // decompression:        $bodylen = $len - $headerlen - 8;        if ($bodylen  0) {            switch ($method) {                case 8:                    // Currently the only supported compression method:                    $data = gzinflate($body, $maxlength);                    break;                default:                    $error = "Unknown compression method.";                    return false;            }        }  // zero-byte body content is allowed        // Verifiy CRC32        $crc = sprintf("%u", crc32($data));        $crcOK = $crc == $datacrc;        $lenOK = $isize == strlen($data);        if (!$lenOK || !$crcOK) {            $error = ( $lenOK ? '' : 'Length check FAILED. ') . ( $crcOK ? '' : 'Checksum FAILED.');            return false;        }        return $data;    }

也就是说，连续解压时，会出现解压失败的情况

喜欢 (0)赏

[搞代码]

分享 (0)