récupération du titre de la page pochée et rangement de fonctions dans un nouveau fichier

This commit is contained in:
nicosomb 2013-04-04 21:09:34 +02:00
parent a590ea55c2
commit 246195341c
5 changed files with 180 additions and 174 deletions

0
inc/index.html → cache/.gitignore vendored Executable file → Normal file
View file

Binary file not shown.

153
inc/functions.php Executable file
View file

@ -0,0 +1,153 @@
<?php
function url(){
$protocol = "http";
if(isset($_SERVER['HTTPS']))
if($_SERVER['HTTPS'] != "off")
$protocol = "https";
return $protocol . "://" . $_SERVER['HTTP_HOST'] . $_SERVER['REQUEST_URI'];
}
function generate_page($url,$title,$content) {
raintpl::$tpl_dir = './tpl/'; // template directory
raintpl::$cache_dir = "./cache/"; // cache directory
raintpl::$base_url = url(); // base URL of blog
raintpl::configure( 'path_replace', false );
raintpl::configure('debug', false);
$tpl = new raintpl(); //include Rain TPL
$tpl->assign( "url", $url);
$tpl->assign( "title", $title);
$tpl->assign( "content", $content);
$tpl->assign( "version", VERSION);
$tpl->draw( "index"); // draw the template
}
// function define to retrieve url content
function get_external_file($url, $timeout) {
// spoofing FireFox 18.0
$useragent="Mozilla/5.0 (Windows NT 5.1; rv:18.0) Gecko/20100101 Firefox/18.0";
if (in_array ('curl', get_loaded_extensions())) {
// Fetch feed from URL
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_TIMEOUT, $timeout);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_HEADER, false);
// FeedBurner requires a proper USER-AGENT...
curl_setopt($curl, CURL_HTTP_VERSION_1_1, true);
curl_setopt($curl, CURLOPT_ENCODING, "gzip, deflate");
curl_setopt($curl, CURLOPT_USERAGENT, $useragent);
$data = curl_exec($curl);
$httpcode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$httpcodeOK = isset($httpcode) and ($httpcode == 200 or $httpcode == 301);
curl_close($curl);
} else {
// create http context and add timeout and user-agent
$context = stream_context_create(array('http'=>array('timeout' => $timeout, // Timeout : time until we stop waiting for the response.
'header'=> "User-Agent: ".$useragent, // spoot Mozilla Firefox
'follow_location' => true
)));
// only download page lesser than 4MB
$data = @file_get_contents($url, false, $context, -1, 4000000); // We download at most 4 MB from source.
// echo "<pre>http_response_header : ".print_r($http_response_header);
if(isset($http_response_header) and isset($http_response_header[0])) {
$httpcodeOK = isset($http_response_header) and isset($http_response_header[0]) and ((strpos($http_response_header[0], '200 OK') !== FALSE) or (strpos($http_response_header[0], '301 Moved Permanently') !== FALSE));
}
}
// if response is not empty and response is OK
if (isset($data) and isset($httpcodeOK) and $httpcodeOK ) {
// take charset of page and get it
preg_match('#<meta .*charset=.*>#Usi', $data, $meta);
// if meta tag is found
if (!empty($meta[0])) {
// retrieve encoding in $enc
preg_match('#charset="?(.*)"#si', $meta[0], $enc);
// if charset is found set it otherwise, set it to utf-8
$html_charset = (!empty($enc[1])) ? strtolower($enc[1]) : 'utf-8';
} else {
$html_charset = 'utf-8';
$enc[1] = '';
}
// replace charset of url to charset of page
$data = str_replace('charset='.$enc[1], 'charset='.$html_charset, $data);
return $data;
}
else {
return FALSE;
}
}
function rel2abs($rel, $base)
{
/* return if already absolute URL */
if (parse_url($rel, PHP_URL_SCHEME) != '') return $rel;
/* queries and anchors */
if ($rel[0]=='#' || $rel[0]=='?') return $base.$rel;
/* parse base URL and convert to local variables:
$scheme, $host, $path */
extract(parse_url($base));
/* remove non-directory element from path */
$path = preg_replace('#/[^/]*$#', '', $path);
/* destroy path if relative url points to root */
if ($rel[0] == '/') $path = '';
/* dirty absolute URL */
$abs = "$host$path/$rel";
/* replace '//' or '/./' or '/foo/../' with '/' */
$re = array('#(/\.?/)#', '#/(?!\.\.)[^/]+/\.\./#');
for($n=1; $n>0; $abs=preg_replace($re, '/', $abs, -1, $n)) {}
/* absolute URL is ready! */
return $scheme.'://'.$abs;
}
// $str=preg_replace('#(href|src)="([^:"]*)("|(?:(?:%20|\s|\+)[^"]*"))#','$1="http://wintermute.com.au/$2$3',$str);
function absolutes_links($data, $base) {
// cherche les balises 'a' qui contiennent un href
$matches = array();
preg_match_all('#(href|src)="([^:"]*)("|(?:(?:%20|\s|\+)[^"]*"))#Si', $data, $matches, PREG_SET_ORDER);
// ne conserve que les liens ne commençant pas par un protocole « protocole:// » ni par une ancre « # »
foreach($matches as $i => $link) {
$link[1] = trim($link[1]);
if (!preg_match('#^(([a-z]+://)|(\#))#', $link[1]) ) {
$absolutePath=rel2abs($link[2],$base);
$data = str_replace($matches[$i][2], $absolutePath, $data);
}
}
return $data;
}
?>

View file

@ -22,6 +22,9 @@
* afficher liens mis en favoris et archivés
* tri des liens
*/
require_once dirname(__FILE__).'/inc/Readability.php';
require_once dirname(__FILE__).'/inc/Encoding.php';
include dirname(__FILE__).'/inc/functions.php';
try
{
@ -39,8 +42,21 @@ $id = (isset ($_GET['id'])) ? htmlspecialchars($_GET['id']) : '';
switch ($action) {
case 'add':
$url = (isset ($_GET['url'])) ? htmlspecialchars($_GET['url']) : '';
$url = (isset ($_GET['url'])) ? $_GET['url'] : '';
$url = html_entity_decode(trim($url));
$title = $url;
// if url use https protocol change it to http
if (!preg_match('!^https?://!i', $url)) $url = 'http://'.$url;
// convert page to utf-8
$html = Encoding::toUTF8(get_external_file($url,15));
if(isset($html) and strlen($html) > 0) {
// send result to readability library
$r = new Readability($html, $url);
if($r->init()) {
$title = $r->articleTitle->innerHTML;
}
}
$query = $db_handle->prepare('INSERT INTO entries ( url, title ) VALUES (?, ?)');
$query->execute(array($url, $title));
break;
@ -53,6 +69,8 @@ switch ($action) {
$params_action = array($id);
break;
case 'delete':
$sql_action = "DELETE FROM entries WHERE id=?";
$params_action = array($id);
break;
default:
break;
@ -98,16 +116,6 @@ catch (Exception $e)
die('query error : '.$e->getMessage());
}
function url() {
$protocol = "http";
if(isset($_SERVER['HTTPS'])) {
if($_SERVER['HTTPS'] != "off") {
$protocol = "https";
}
}
return $protocol . "://" . $_SERVER['HTTP_HOST'] . $_SERVER['REQUEST_URI'];
}
?>
<!DOCTYPE html>
<!--[if lte IE 6]> <html class="no-js ie6 ie67 ie678" lang="en"> <![endif]-->
@ -137,13 +145,13 @@ function url() {
<ul id="entries">
<?php
foreach ($entries as $entry) {
echo '<li><a href="readityourself.php?url='.urlencode($entry['url']).'">' . $entry['title'] . '</a> <a href="?action=toggle_archive&id='.$entry['id'].'" title="toggle mark as read" class="tool">&#10003;</a> <a href="?action=toggle_fav&id='.$entry['id'].'" title="toggle favorite" class="tool">'.(($entry['is_fav'] == 0) ? '&#9734;' : '&#9733;' ).'</a> <a href="#" title="toggle delete" class="tool">&#10799;</a></li>';
echo '<li><a href="readityourself.php?url='.urlencode($entry['url']).'">' . $entry['title'] . '</a> <a href="?action=toggle_archive&id='.$entry['id'].'" title="toggle mark as read" class="tool">&#10003;</a> <a href="?action=toggle_fav&id='.$entry['id'].'" title="toggle favorite" class="tool">'.(($entry['is_fav'] == 0) ? '&#9734;' : '&#9733;' ).'</a> <a href="?action=delete&id='.$entry['id'].'" title="toggle delete" class="tool">&#10799;</a></li>';
}
?>
</ul>
</div>
<footer class="mr2 mt3">
<p class="smaller"><a href="http://github.com/nicosomb/poche">poche</a> is a read it later open source system, based on <a href="http://www.memiks.fr/readityourself/">ReadItYourself</a>. poche is developed by <a href="http://nicolas.loeuillet.org">Nicolas Lœuillet</a> under the <a href="http://www.wtfpl.net/">Do What the Fuck You Want to Public License</a></p>
<p class="smaller"><a href="http://github.com/nicosomb/poche">poche</a> is a read it later open source system, based on <a href="http://www.memiks.fr/readityourself/">ReadItYourself</a>. poche is developed by <a href="http://nicolas.loeuillet.org">Nicolas Lœuillet</a> under the <a href="http://www.wtfpl.net/">WTFPL</a>.</p>
</footer>
</body>
</html>

View file

@ -21,162 +21,7 @@ require_once dirname(__FILE__).'/inc/Encoding.php';
// appel de la libraire RainTPL.
require_once dirname(__FILE__).'/inc/rain.tpl.class.php';
// FUNCTIONS BEGIN
function url(){
$protocol = "http";
if(isset($_SERVER['HTTPS']))
if($_SERVER['HTTPS'] != "off")
$protocol = "https";
return $protocol . "://" . $_SERVER['HTTP_HOST'] . $_SERVER['REQUEST_URI'];
}
function generate_page($url,$title,$content) {
raintpl::$tpl_dir = './tpl/'; // template directory
raintpl::$cache_dir = "./cache/"; // cache directory
raintpl::$base_url = url(); // base URL of blog
raintpl::configure( 'path_replace', false );
raintpl::configure('debug', false);
$tpl = new raintpl(); //include Rain TPL
$tpl->assign( "url", $url);
$tpl->assign( "title", $title);
$tpl->assign( "content", $content);
$tpl->assign( "version", VERSION);
$tpl->draw( "index"); // draw the template
}
// function define to retrieve url content
function get_external_file($url, $timeout) {
// spoofing FireFox 18.0
$useragent="Mozilla/5.0 (Windows NT 5.1; rv:18.0) Gecko/20100101 Firefox/18.0";
if (in_array ('curl', get_loaded_extensions())) {
// Fetch feed from URL
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_TIMEOUT, $timeout);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_HEADER, false);
// FeedBurner requires a proper USER-AGENT...
curl_setopt($curl, CURL_HTTP_VERSION_1_1, true);
curl_setopt($curl, CURLOPT_ENCODING, "gzip, deflate");
curl_setopt($curl, CURLOPT_USERAGENT, $useragent);
$data = curl_exec($curl);
$httpcode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$httpcodeOK = isset($httpcode) and ($httpcode == 200 or $httpcode == 301);
curl_close($curl);
} else {
// create http context and add timeout and user-agent
$context = stream_context_create(array('http'=>array('timeout' => $timeout, // Timeout : time until we stop waiting for the response.
'header'=> "User-Agent: ".$useragent, // spoot Mozilla Firefox
'follow_location' => true
)));
// only download page lesser than 4MB
$data = @file_get_contents($url, false, $context, -1, 4000000); // We download at most 4 MB from source.
// echo "<pre>http_response_header : ".print_r($http_response_header);
if(isset($http_response_header) and isset($http_response_header[0])) {
$httpcodeOK = isset($http_response_header) and isset($http_response_header[0]) and ((strpos($http_response_header[0], '200 OK') !== FALSE) or (strpos($http_response_header[0], '301 Moved Permanently') !== FALSE));
}
}
// if response is not empty and response is OK
if (isset($data) and isset($httpcodeOK) and $httpcodeOK ) {
// take charset of page and get it
preg_match('#<meta .*charset=.*>#Usi', $data, $meta);
// if meta tag is found
if (!empty($meta[0])) {
// retrieve encoding in $enc
preg_match('#charset="?(.*)"#si', $meta[0], $enc);
// if charset is found set it otherwise, set it to utf-8
$html_charset = (!empty($enc[1])) ? strtolower($enc[1]) : 'utf-8';
} else {
$html_charset = 'utf-8';
$enc[1] = '';
}
// replace charset of url to charset of page
$data = str_replace('charset='.$enc[1], 'charset='.$html_charset, $data);
return $data;
}
else {
return FALSE;
}
}
function rel2abs($rel, $base)
{
/* return if already absolute URL */
if (parse_url($rel, PHP_URL_SCHEME) != '') return $rel;
/* queries and anchors */
if ($rel[0]=='#' || $rel[0]=='?') return $base.$rel;
/* parse base URL and convert to local variables:
$scheme, $host, $path */
extract(parse_url($base));
/* remove non-directory element from path */
$path = preg_replace('#/[^/]*$#', '', $path);
/* destroy path if relative url points to root */
if ($rel[0] == '/') $path = '';
/* dirty absolute URL */
$abs = "$host$path/$rel";
/* replace '//' or '/./' or '/foo/../' with '/' */
$re = array('#(/\.?/)#', '#/(?!\.\.)[^/]+/\.\./#');
for($n=1; $n>0; $abs=preg_replace($re, '/', $abs, -1, $n)) {}
/* absolute URL is ready! */
return $scheme.'://'.$abs;
}
// $str=preg_replace('#(href|src)="([^:"]*)("|(?:(?:%20|\s|\+)[^"]*"))#','$1="http://wintermute.com.au/$2$3',$str);
function absolutes_links($data, $base) {
// cherche les balises 'a' qui contiennent un href
$matches = array();
preg_match_all('#(href|src)="([^:"]*)("|(?:(?:%20|\s|\+)[^"]*"))#Si', $data, $matches, PREG_SET_ORDER);
// ne conserve que les liens ne commençant pas par un protocole « protocole:// » ni par une ancre « # »
foreach($matches as $i => $link) {
$link[1] = trim($link[1]);
if (!preg_match('#^(([a-z]+://)|(\#))#', $link[1]) ) {
$absolutePath=rel2abs($link[2],$base);
$data = str_replace($matches[$i][2], $absolutePath, $data);
}
}
return $data;
}
// FUNCTIONS END
include dirname(__FILE__).'/inc/functions.php';
// EXUCUTION CODE
@ -190,15 +35,15 @@ if(isset($_GET['url']) && $_GET['url'] != null && trim($_GET['url']) != "") {
// decode it
$url = html_entity_decode($url);
// if url use https protocol change it to http
if (!preg_match('!^https?://!i', $url)) $url = 'http://'.$url;
// convert page to utf-8
$html = Encoding::toUTF8(get_external_file($url,15));
if(isset($html) and strlen($html) > 0) {
// send result to readability library
$r = new Readability($html, $url);
@ -213,4 +58,4 @@ if(isset($_GET['url']) && $_GET['url'] != null && trim($_GET['url']) != "") {
}
}
}
?>
?>