Created
December 4, 2013 14:55
-
-
Save akkunchoi/7788829 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?php | |
| error_reporting(E_ALL); | |
| ini_set('display_errors', 'On'); | |
| function index(){ | |
| ?><!doctype html> | |
| <html> | |
| <head> | |
| <style type="text/css"> | |
| </style> | |
| </head> | |
| <body> | |
| <h1>ファイルクローラー</h1> | |
| <form action=""> | |
| 開始URL: <input type="text" size="80" name="url" /><br /> | |
| ステップ: <input type="text" size="2" name="step" value="2" /> <br /> | |
| <input type="submit" name="submit" value="実行" /> | |
| </form> | |
| </body></html><?php | |
| } | |
| $base = dirname(__FILE__); | |
| $filename = $base . '/out/'; | |
| if (isset($_GET['download'])){ | |
| $path = $filename . '_' . $_GET['download'] . '.csv'; | |
| if (!file_exists($path)){ | |
| die('file not found'); | |
| } | |
| $name = $_GET['download']; | |
| header('Content-Type: text/comma-separated-values'); | |
| header('Content-Disposition: attachment; filename="' . $name . '"'); | |
| header('Content-Length: '.filesize($path)); | |
| readfile($path); | |
| exit; | |
| } | |
| if (isset($_GET['url'])){ | |
| $url = $_GET['url']; | |
| $accept = dirname($url); | |
| }else{ | |
| index(); | |
| exit; | |
| } | |
| set_time_limit(0); | |
| $step = 2; | |
| if (isset($_GET['step'])){ | |
| $step = $_GET['step']; | |
| } | |
| $reject = ''; | |
| $python = '/usr/local/bin/python'; | |
| $baseid = date("YmdHis"); | |
| $exec = "$python $base/webstemmer/textcrawler.py -m$step -L $filename -b$baseid $accept $reject $url 2>&1"; | |
| $exec = str_replace(';', '', $exec); | |
| $exec = str_replace("\0", '', $exec); | |
| // 指定するとエラー。指定しなくてもchunkedになってた | |
| //header("Content-Encoding: chunked"); | |
| //header("Transfer-Encoding: chunked"); | |
| header("Content-Type: text/html; charset=utf-8"); | |
| header("Connection: keep-alive"); | |
| flush(); | |
| ob_flush(); | |
| ?><!doctype html> | |
| <html> | |
| <head> | |
| <style type="text/css"> | |
| </style> | |
| </head> | |
| <body><pre class="out"><?php | |
| $handle = popen($exec, 'r'); | |
| while(!feof($handle)){ | |
| echo fread($handle, 2096); | |
| flush(); | |
| ob_flush(); | |
| } | |
| pclose($handle); | |
| //echo passthru($exec); | |
| echo "\nDone!\n"; | |
| ?></pre> | |
| <?php | |
| $path = $filename . '_' . $baseid . '.csv'; | |
| if (file_exists($path)){ | |
| ?><a href="?download=<?php echo $baseid ?>">ダウンロード</a><?php | |
| }else{ | |
| ?>失敗しました<?php | |
| } | |
| ?> | |
| </body></html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment