dmca/2015/2015-09-29-mapanet.md

140 строки
4.6 KiB
Markdown
Исходник Ответственный История

Этот файл содержит невидимые символы Юникода!

Этот файл содержит невидимые символы Юникода, которые могут быть отображены не так, как показано ниже. Если это намеренно, можете спокойно проигнорировать это предупреждение. Используйте кнопку Экранировать, чтобы показать скрытые символы.

I have read and understand GitHub's Guide to Filing a DMCA Notice
I have a good faith belief that use of the copyrighted materials described
above on the infringing web pages is not authorized by the copyright owner,
or its agent, or the law.
I swear, under penalty of perjury, that the information in this
notification is accurate and that I am the copyright owner, or am
authorized to act on behalf of the owner, of an exclusive right that is
allegedly infringed.
[PRIVATE]
*Github user info:*
Name: [PRIVATE]
User: raihanhbh
Web: ArcticIntelligence.com
Join: Joined on Mar 28, 2011
Repository: arcticintelligence/yell-scrapper (copy of script below)
URL:
https://github.com/arcticintelligence/yell-scrapper/blob/master/mapanet_curl.php
URL: https://github.com/raihanhbh
User social pages: [PRIVATE]
*Infringement description:*
The php script was designed to gather information from our mapanet.eu web
pages by trying to execute the find.asp page and gather the results and
store them, we guess to use it, make it public in raw format or sell it.
In any case or copyright notice at: http://www.mapanet.eu/EN/terms.htm
which in shot sates:
All and any texts, data and images contained in the website mapanet.eu, are
copyrighted and all rights are reserved worldwide. Therefore and according
to copyright laws, only a private usage is allowed without prejudice of any
other enforcement, possibly more restrictive, of the above mentioned
copyright laws.
The script is provided publicly in Github allowing anybody to use it to
collect privileged information from our site.
*Proof*:
The offense script below clearly has the path of our website: $url = '
http://www.mapanet.eu/EN/Postal_Codes/Find.asp';
And the unique parameters: $fields = array('Action' => urlencode('ok'), 'C'
=> urlencode('CN'), 'F' => urlencode(''), 'GL' => urlencode(''), 'L' =>
urlencode(0).... etc.
Lines on the code below are in red.
*Ownership*:
Our domain is provided by EuroDNS.com where you can verify ownership to my
name: [PRIVATE]
We ask Github to retire the content of:
https://github.com/arcticintelligence/yell-scrapper/blob/master/mapanet_curl.php
and penalize the user who published it.
<?php
ini_set('max_execution_time', 0);
ini_set('memory_limit', '-1');
$postal_codes = file_get_contents('./input-data.txt', true);
//Convert special characters.
//$addresses = mb_convert_encoding($postal_codes, 'HTML-ENTITIES', "UTF-8");
$postal_codes = preg_split("/\\r\\n|\\r|\\n/", $postal_codes);
if(count($postal_codes)>0) {
//Save to file.
$file = fopen("parsed-data_".date('Y_m_d_h_i_s').".csv","w");
}
foreach($postal_codes as $key => $postal_code) {
echo $key+1 . ">>>>" . mb_convert_encoding($postal_code,
'HTML-ENTITIES', "UTF-8") . "<br>" . "\n";
get_post_html($postal_code, $file);
}
//Close the file pointer;
if(count($postal_codes)>0) {
fclose($file);
}
function get_post_html($postal_code, $file)
$fields_string = '';
//set POST variables
*$url = 'http://www.mapanet.eu/EN/Postal_Codes/Find.asp
<http://www.mapanet.eu/EN/Postal_Codes/Find.asp>';*
$fields = array(
'Action' => urlencode('ok'),
'C' => urlencode('CN'),
'F' => urlencode(''),
'GL' => urlencode(''),
'L' => urlencode(0),
'N' => urlencode(3),
'PC' => urlencode(''),
'T' => urlencode($postal_code),
'page' => urlencode('')
);
//url-ify the data for the POST
foreach($fields as $key=>$value) { $fields_string .=
$key.'='.$value.'&'; }
rtrim($fields_string, '&');
//open connection
$ch = curl_init();
$timeout = 5;
//set the url, number of POST vars, POST data
curl_setopt($ch,CURLOPT_URL, $url);
curl_setopt($ch,CURLOPT_HEADER, FALSE);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch,CURLOPT_POST, count($fields));
curl_setopt($ch,CURLOPT_POSTFIELDS, $fields_string);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt($ch,CURLOPT_USERAGENT,'Mozilla/5.0 (Windows; U; Windows NT
5.1; en-US; rv:1.8.1.13) Gecko/20080311 Firefox/2.0.0.13');
//execute post
$html = curl_exec($ch);
//close connection
curl_close($ch);
parse_html($html, $postal_code, $file);
}
function parse_html($html, $postal_code, $file) {
# Create a DOM parser object
$dom = new DOMDocument();
# Parse the HTML from Google.
# The @ before the method call suppresses any warnings that
# loadHTML might throw because of invalid HTML in the page.
@$dom->loadHTML($html);
# Iterate over all the <a> tags
foreach($dom->getElementsByTagName('a') as $link) {
echo $href = $link->getAttribute('href') ."<br>";
echo $value = $link->nodeValue . "<br>";
if( strpos($href, 'Postal_Codes') > 0 &&
strpos($href, 'R2=') > 0 &&
strpos($href, 'page=') > 0
) {
echo $content = $postal_code . ", " . $value . "\n";
// Entry row to file.
fwrite($file, $content);
}
}
}
Regards
[PRIVATE]