97 lines
3.1 KiB
PHP
97 lines
3.1 KiB
PHP
#!/usr/bin/php -c/var/www/batch/config/php_batch_sd.ini
|
|
<?php
|
|
|
|
//Define cookie file for storage
|
|
$ckfile = '/tmp/cookies.txt';
|
|
if (file_exists($ckfile)) unlink($ckfile);
|
|
|
|
if ($argc != 4){
|
|
echo $argv[0].' type annee num';
|
|
echo "\n";
|
|
exit;
|
|
}
|
|
|
|
$type = strtoupper($argv[1]);
|
|
$annee = $argv[2];
|
|
|
|
$num = $argv[3];
|
|
$c = strlen($num);
|
|
for($i=0;$i<4-$c;$i++){
|
|
$num = '0'.$num;
|
|
}
|
|
$annonce = 1;
|
|
|
|
function getPage($url, $curl_data = '', $verbose=false)
|
|
{
|
|
global $ckfile;
|
|
|
|
//$user_agent = 'Mozilla/5.0 (Windows NT 5.1; rv:9.0.1) Gecko/20100101 Firefox/9.0.1';
|
|
//$user_agent = 'Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)';
|
|
$user_agent = 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)';
|
|
|
|
$post = false;
|
|
$fields = '';
|
|
if (is_array($curl_data) && count($curl_data)>0) {
|
|
foreach($curl_data as $key=>$value) {
|
|
$fields .= $key.'='.$value.'&';
|
|
}
|
|
rtrim($fields,'&');
|
|
$post = true;
|
|
}
|
|
|
|
$options = array(
|
|
CURLOPT_RETURNTRANSFER => true, // return web page
|
|
CURLOPT_HEADER => false, // don't return headers
|
|
CURLOPT_FOLLOWLOCATION => true, // follow redirects
|
|
CURLOPT_ENCODING => "", // handle all encodings
|
|
CURLOPT_USERAGENT => $user_agent, // who am i
|
|
CURLOPT_AUTOREFERER => true, // set referer on redirect
|
|
CURLOPT_CONNECTTIMEOUT => 120, // timeout on connect
|
|
CURLOPT_TIMEOUT => 120, // timeout on response
|
|
CURLOPT_MAXREDIRS => 10, // stop after 10 redirects
|
|
CURLOPT_POST => $post, // i am sending post data
|
|
CURLOPT_POSTFIELDS => $fields, // this are my post vars
|
|
CURLOPT_SSL_VERIFYHOST => 0, // don't verify ssl
|
|
CURLOPT_SSL_VERIFYPEER => false, //
|
|
CURLOPT_VERBOSE => $verbose , //
|
|
//CURLOPT_COOKIESESSION => true,
|
|
CURLOPT_COOKIEFILE => $ckfile,
|
|
CURLOPT_COOKIEJAR => $ckfile, // Stockage du cookie de session
|
|
);
|
|
|
|
$ch = curl_init($url);
|
|
curl_setopt_array($ch,$options);
|
|
$content = curl_exec($ch);
|
|
$err = curl_errno($ch);
|
|
$errmsg = curl_error($ch) ;
|
|
$header = curl_getinfo($ch);
|
|
curl_close($ch);
|
|
|
|
// $header['errno'] = $err;
|
|
// $header['errmsg'] = $errmsg;
|
|
// $header['content'] = $content;
|
|
return array('header'=>$header, 'content'=>$content);
|
|
}
|
|
|
|
//==> Start
|
|
$debug = false;
|
|
|
|
echo $url = "http://www.bodacc.fr/index.php?action=voir&p=$type&n=$annee$num&a=$annonce";
|
|
echo "\n";
|
|
$result = getPage($url);
|
|
if ($debug) file_put_contents('bodacc1.html', $result['content']);
|
|
preg_match('/\<a href="index\.php\?action=pdf&index=([0-9]{1,})"\>/', $result['content'], $matches);
|
|
echo $url = "http://www.bodacc.fr/index.php?action=pdf&index=".$matches[1];
|
|
echo "\n";
|
|
$result = getPage($url);
|
|
|
|
if (substr($result['content'],0,4)!='%PDF'){
|
|
if ($debug) file_put_contents('bodacc2.html', $result['content']);
|
|
echo 'Erreur : pas de PDF'.EOL;
|
|
exit;
|
|
}
|
|
echo strlen($result['content']).' octets'.EOL;
|
|
file_put_contents("BODACC_".$type."_".$annee."_".$num.".pdf", $result['content']);
|
|
|
|
die();
|
|
?>
|