Merge branch 'memiks-gestion_erreur_readability' into dev

This commit is contained in:
nicosomb 2013-04-23 15:19:33 +02:00
commit 3e7188185d
2 changed files with 29 additions and 8 deletions

View file

@ -80,7 +80,7 @@ class Readability
public $debug = false;
protected $body = null; //
protected $bodyCache = null; // Cache the body HTML in case we need to re-use it later
protected $flags = self::FLAG_CLEAN_CONDITIONALLY; // 1 | 2 | 4; // Start with all flags set.
protected $flags = self::FLAG_CLEAN_CONDITIONALLY; // 1 | 2 | 4; // Start with all flags set.
protected $success = false; // indicates whether we were able to extract or not
/**
@ -90,7 +90,7 @@ class Readability
public $regexps = array(
'unlikelyCandidates' => '/combx|comment|comments|community|disqus|extra|foot|header|menu|remark|rss|shoutbox|sidebar|sponsor|ad-break|agegate|pagination|pager|popup|tweet|twitter/i',
'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i',
'positive' => '/article|body|content|entry|hentry|main|page|pagination|post|text|blog|story/i',
'positive' => '/article|body|content|entry|hentry|main|page|pagination|post|text|blog|story|attachment/i',
'negative' => '/combx|comment|comments|com-|contact|foot|footer|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget/i',
'divToPElements' => '/<(a|blockquote|dl|div|ol|p|pre|table|ul)/i',
'replaceBrs' => '/(<br[^>]*>[ \n\r\t]*){2,}/i',
@ -106,7 +106,7 @@ class Readability
* Create instance of Readability
* @param string UTF-8 encoded string
* @param string (optional) URL associated with HTML (used for footnotes)
*/
*/
function __construct($html, $url=null)
{
/* Turn all double br's into p's */
@ -185,6 +185,7 @@ class Readability
$articleContent = $this->dom->createElement('div');
$articleContent->setAttribute('id', 'readability-content');
$articleContent->innerHTML = '<p>Sorry, Readability was unable to parse this page for content.</p>';
return $this->success;
}
$overlay->setAttribute('id', 'readOverlay');

View file

@ -39,6 +39,10 @@ function get_external_file($url)
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_HEADER, false);
// FOR SSL do not verified certificate
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, FALSE);
curl_setopt($curl, CURLOPT_AUTOREFERER, TRUE );
// FeedBurner requires a proper USER-AGENT...
curl_setopt($curl, CURL_HTTP_VERSION_1_1, true);
curl_setopt($curl, CURLOPT_ENCODING, "gzip, deflate");
@ -54,7 +58,15 @@ function get_external_file($url)
} else {
// create http context and add timeout and user-agent
$context = stream_context_create(array('http'=>array('timeout' => $timeout,'header'=> "User-Agent: ".$useragent,/*spoot Mozilla Firefox*/'follow_location' => true)));
$context = stream_context_create(array(
'http'=>array('timeout' => $timeout,
'header'=> "User-Agent: ".$useragent, /*spoot Mozilla Firefox*/
'follow_location' => true),
// FOR SSL do not verified certificate
'ssl' => array('verify_peer' => false,
'allow_self_signed' => true)
)
);
// only download page lesser than 4MB
$data = @file_get_contents($url, false, $context, -1, 4000000); // We download at most 4 MB from source.
@ -98,6 +110,8 @@ function get_external_file($url)
*/
function prepare_url($url)
{
global $msg;
$parametres = array();
$url = html_entity_decode(trim($url));
@ -108,14 +122,20 @@ function prepare_url($url)
$i=strpos($url,'#xtor=RSS-'); if ($i!==false) $url=substr($url,0,$i);
$title = $url;
if (!preg_match('!^https?://!i', $url))
$url = 'http://' . $url;
$html = Encoding::toUTF8(get_external_file($url,15));
// If get_external_file if not able to retrieve HTTPS content try the same URL with HTTP protocol
if (!preg_match('!^https?://!i', $url) && (!isset($html) || strlen($html) <= 0)) {
$url = 'http://' . $url;
$html = Encoding::toUTF8(get_external_file($url,15));
}
$html = Encoding::toUTF8(get_external_file($url,15));
if (isset($html) and strlen($html) > 0)
{
$r = new Readability($html, $url);
$r->convertLinksToFootnotes = CONVERT_LINKS_FOOTNOTES;
$r->revertForcedParagraphElements = REVERT_FORCED_PARAGRAPH_ELEMENTS;
if($r->init())
{
$content = $r->articleContent->innerHTML;
@ -362,4 +382,4 @@ function logm($message)
{
$t = strval(date('Y/m/d_H:i:s')).' - '.$_SERVER["REMOTE_ADDR"].' - '.strval($message)."\n";
file_put_contents('./log.txt',$t,FILE_APPEND);
}
}