X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;ds=sidebyside;f=include%2FScrape.php;h=ff98992526314474b6dcc7aa20386a92f114c332;hb=b98b5645e6572a2ee4b00a1d7960b93160f1de7f;hp=0272dde129cd89c83d918ac2f9d6cbd5c3ceb86b;hpb=b8b227b32882fb511c8481a41c53637e7ce7707a;p=friendica.git

diff --git a/include/Scrape.php b/include/Scrape.php
index 0272dde129..ff98992526 100644
--- a/include/Scrape.php
+++ b/include/Scrape.php
@@ -2,24 +2,34 @@
 
 require_once('library/HTML5/Parser.php');
 
-if(! function_exists('attribute_contains')) {
-function attribute_contains($attr,$s) {
-	$a = explode(' ', $attr);
-	if(count($a) && in_array($s,$a))
-		return true;
-	return false;
-}}
-
-
 if(! function_exists('scrape_dfrn')) {
 function scrape_dfrn($url) {
 
+	$a = get_app();
+
 	$ret = array();
+
+	logger('scrape_dfrn: url=' . $url);
+
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	logger('scrape_dfrn: headers=' . $headers, LOGGER_DEBUG);
+
+
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			// don't try and run feeds through the html5 parser
+			if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
+				return ret;
+		}
+	}
+
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)
@@ -31,6 +41,8 @@ function scrape_dfrn($url) {
 
 	foreach($items as $item) {
 		$x = $item->getAttribute('rel');
+		if(($x === 'alternate') && ($item->getAttribute('type') === 'application/atom+xml'))
+			$ret['feed_atom'] = $item->getAttribute('href');
 		if(substr($x,0,5) == "dfrn-")
 			$ret[$x] = $item->getAttribute('href');
 		if($x === 'lrdd') {
@@ -53,7 +65,7 @@ function scrape_dfrn($url) {
 					$ret['photo'] = $x->getAttribute('src');
 				if(attribute_contains($x->getAttribute('class'),'key'))
 					$ret['key'] = $x->textContent;
-        		}
+			}
 		}
 	}
 
@@ -84,12 +96,31 @@ function validate_dfrn($a) {
 if(! function_exists('scrape_meta')) {
 function scrape_meta($url) {
 
+	$a = get_app();
+
 	$ret = array();
+
+	logger('scrape_meta: url=' . $url);
+
 	$s = fetch_url($url);
 
 	if(! $s) 
 		return $ret;
 
+	$headers = $a->get_curl_headers();
+	logger('scrape_meta: headers=' . $headers, LOGGER_DEBUG);
+
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			// don't try and run feeds through the html5 parser
+			if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
+				return ret;
+		}
+	}
+
+
+
 	$dom = HTML5_Parser::parse($s);
 
 	if(! $dom)
@@ -107,3 +138,106 @@ function scrape_meta($url) {
 
 	return $ret;
 }}
+
+
+if(! function_exists('scrape_vcard')) {
+function scrape_vcard($url) {
+
+	$a = get_app();
+
+	$ret = array();
+
+	logger('scrape_vcard: url=' . $url);
+
+	$s = fetch_url($url);
+
+	if(! $s) 
+		return $ret;
+
+	$headers = $a->get_curl_headers();
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			// don't try and run feeds through the html5 parser
+			if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
+				return ret;
+		}
+	}
+
+	$dom = HTML5_Parser::parse($s);
+
+	if(! $dom)
+		return $ret;
+
+	// Pull out hCard profile elements
+
+	$items = $dom->getElementsByTagName('*');
+	foreach($items as $item) {
+		if(attribute_contains($item->getAttribute('class'), 'vcard')) {
+			$level2 = $item->getElementsByTagName('*');
+			foreach($level2 as $x) {
+				if(attribute_contains($x->getAttribute('class'),'fn'))
+					$ret['fn'] = $x->textContent;
+				if((attribute_contains($x->getAttribute('class'),'photo'))
+					|| (attribute_contains($x->getAttribute('class'),'avatar')))
+					$ret['photo'] = $x->getAttribute('src');
+				if((attribute_contains($x->getAttribute('class'),'nickname'))
+					|| (attribute_contains($x->getAttribute('class'),'uid')))
+					$ret['nick'] = $x->textContent;
+			}
+		}
+	}
+
+	return $ret;
+}}
+
+
+if(! function_exists('scrape_feed')) {
+function scrape_feed($url) {
+
+	$a = get_app();
+
+	$ret = array();
+	$s = fetch_url($url);
+
+	if(! $s) 
+		return $ret;
+
+	$headers = $a->get_curl_headers();
+	logger('scrape_feed: headers=' . $headers, LOGGER_DEBUG);
+
+	$lines = explode("\n",$headers);
+	if(count($lines)) {
+		foreach($lines as $line) {				
+			if(stristr($line,'content-type:')) {
+				if(stristr($line,'application/atom+xml') || stristr($s,'<feed')) {
+					$ret['feed_atom'] = $url;
+					return $ret;
+				}
+ 				if(stristr($line,'application/rss+xml') || stristr($s,'<rss')) {
+					$ret['feed_rss'] = $url;
+					return ret;
+				}
+			}
+		}
+	}
+
+	$dom = HTML5_Parser::parse($s);
+
+	if(! $dom)
+		return $ret;
+
+	$items = $dom->getElementsByTagName('link');
+
+	// get Atom link elements
+
+	foreach($items as $item) {
+		$x = $item->getAttribute('rel');
+		if(($x === 'alternate') && ($item->getAttribute('type') === 'application/atom+xml'))
+			$ret['feed_atom'] = $item->getAttribute('href');
+		if(($x === 'alternate') && ($item->getAttribute('type') === 'application/rss+xml'))
+			$ret['feed_rss'] = $item->getAttribute('href');
+	}
+
+	return $ret;
+}}
\ No newline at end of file