X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=mod%2Fparse_url.php;h=7f4bd29a08b292728e2c07b3bb0f457c796420c3;hb=1a62a6ca921eb3388e18d6703a2c07f324d15d5d;hp=c8670d4d967fc67b69f66da129a71b60398d6bc0;hpb=1c55b0b3597379d4f319a390d9e16dce2f59faa3;p=friendica.git
diff --git a/mod/parse_url.php b/mod/parse_url.php
index c8670d4d96..7f4bd29a08 100644
--- a/mod/parse_url.php
+++ b/mod/parse_url.php
@@ -24,61 +24,120 @@ if(!function_exists('deletenode')) {
}
function completeurl($url, $scheme) {
- $urlarr = parse_url($url);
+ $urlarr = parse_url($url);
- if (isset($urlarr["scheme"]))
- return($url);
+ if (isset($urlarr["scheme"]))
+ return($url);
- $schemearr = parse_url($scheme);
+ $schemearr = parse_url($scheme);
- $complete = $schemearr["scheme"]."://".$schemearr["host"];
+ $complete = $schemearr["scheme"]."://".$schemearr["host"];
- if (@$schemearr["port"] != "")
- $complete .= ":".$schemearr["port"];
+ if (@$schemearr["port"] != "")
+ $complete .= ":".$schemearr["port"];
if(strpos($urlarr['path'],'/') !== 0)
$complete .= '/';
- $complete .= $urlarr["path"];
+ $complete .= $urlarr["path"];
- if (@$urlarr["query"] != "")
- $complete .= "?".$urlarr["query"];
+ if (@$urlarr["query"] != "")
+ $complete .= "?".$urlarr["query"];
- if (@$urlarr["fragment"] != "")
- $complete .= "#".$urlarr["fragment"];
+ if (@$urlarr["fragment"] != "")
+ $complete .= "#".$urlarr["fragment"];
- return($complete);
+ return($complete);
}
-function parseurl_getsiteinfo($url) {
+function parseurl_getsiteinfo($url, $no_guessing = false, $do_oembed = true, $count = 1) {
+ require_once("include/network.php");
+
+ $a = get_app();
+
$siteinfo = array();
+
+ if ($count > 10) {
+ logger("parseurl_getsiteinfo: Endless loop detected for ".$url, LOGGER_DEBUG);
+ return($siteinfo);
+ }
+
+ $url = trim($url, "'");
+ $url = trim($url, '"');
+
+ $url = original_url($url);
+
+ $siteinfo["url"] = $url;
+ $siteinfo["type"] = "link";
+
+ $stamp1 = microtime(true);
+
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_HEADER, 1);
- curl_setopt($ch, CURLOPT_NOBODY, 0);
+ curl_setopt($ch, CURLOPT_NOBODY, 1);
curl_setopt($ch, CURLOPT_TIMEOUT, 3);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
//curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
- curl_setopt($ch,CURLOPT_USERAGENT,'Opera/9.64(Windows NT 5.1; U; de) Presto/2.1.1');
+ curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
$header = curl_exec($ch);
$curl_info = @curl_getinfo($ch);
- $http_code = $curl_info['http_code'];
+ $http_code = $curl_info['http_code'];
curl_close($ch);
- if ((($curl_info['http_code'] == "301") OR ($curl_info['http_code'] == "302"))
+ $a->save_timestamp($stamp1, "network");
+
+ if ((($curl_info['http_code'] == "301") OR ($curl_info['http_code'] == "302") OR ($curl_info['http_code'] == "303") OR ($curl_info['http_code'] == "307"))
AND (($curl_info['redirect_url'] != "") OR ($curl_info['location'] != ""))) {
if ($curl_info['redirect_url'] != "")
- $siteinfo = parseurl_getsiteinfo($curl_info['redirect_url']);
+ $siteinfo = parseurl_getsiteinfo($curl_info['redirect_url'], $no_guessing, $do_oembed, ++$count);
else
- $siteinfo = parseurl_getsiteinfo($curl_info['location']);
+ $siteinfo = parseurl_getsiteinfo($curl_info['location'], $no_guessing, $do_oembed, ++$count);
return($siteinfo);
}
+ if ($do_oembed) {
+ require_once("include/oembed.php");
+
+ $oembed_data = oembed_fetch_url($url);
+
+ if ($oembed_data->type != "error")
+ $siteinfo["type"] = $oembed_data->type;
+ }
+
+ // if the file is too large then exit
+ if ($curl_info["download_content_length"] > 1000000)
+ return($siteinfo);
+
+ // if it isn't a HTML file then exit
+ if (($curl_info["content_type"] != "") AND !strstr(strtolower($curl_info["content_type"]),"html"))
+ return($siteinfo);
+
+ $stamp1 = microtime(true);
+
+ // Now fetch the body as well
+ $ch = curl_init();
+ curl_setopt($ch, CURLOPT_URL, $url);
+ curl_setopt($ch, CURLOPT_HEADER, 1);
+ curl_setopt($ch, CURLOPT_NOBODY, 0);
+ curl_setopt($ch, CURLOPT_TIMEOUT, 10);
+ curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
+ curl_setopt($ch, CURLOPT_USERAGENT, $a->get_useragent());
+
+ $header = curl_exec($ch);
+ $curl_info = @curl_getinfo($ch);
+ $http_code = $curl_info['http_code'];
+ curl_close($ch);
+
+ $a->save_timestamp($stamp1, "network");
+
// Fetch the first mentioned charset. Can be in body or header
+ $charset = "";
if (preg_match('/charset=(.*?)['."'".'"\s\n]/', $header, $matches))
- $charset = trim(array_pop($matches));
- else
+ $charset = trim(trim(trim(array_pop($matches)), ';,'));
+
+ if ($charset == "")
$charset = "utf-8";
$pos = strpos($header, "\r\n\r\n");
@@ -88,7 +147,12 @@ function parseurl_getsiteinfo($url) {
else
$body = $header;
- $body = mb_convert_encoding($body, "UTF-8", $charset);
+ if (($charset != '') AND (strtoupper($charset) != "UTF-8")) {
+ logger("parseurl_getsiteinfo: detected charset ".$charset, LOGGER_DEBUG);
+ //$body = mb_convert_encoding($body, "UTF-8", $charset);
+ $body = iconv($charset, "UTF-8//TRANSLIT", $body);
+ }
+
$body = mb_convert_encoding($body, 'HTML-ENTITIES', "UTF-8");
$doc = new DOMDocument();
@@ -109,25 +173,25 @@ function parseurl_getsiteinfo($url) {
$xpath = new DomXPath($doc);
$list = $xpath->query("//meta[@content]");
- foreach ($list as $node) {
- $attr = array();
- if ($node->attributes->length)
- foreach ($node->attributes as $attribute)
- $attr[$attribute->name] = $attribute->value;
-
- if (@$attr["http-equiv"] == 'refresh') {
- $path = $attr["content"];
- $pathinfo = explode(";", $path);
- $content = "";
- foreach ($pathinfo AS $value) {
- if (substr(strtolower($value), 0, 4) == "url=")
- $content = substr($value, 4);
- }
- if ($content != "") {
- $siteinfo = parseurl_getsiteinfo($content);
- return($siteinfo);
- }
- }
+ foreach ($list as $node) {
+ $attr = array();
+ if ($node->attributes->length)
+ foreach ($node->attributes as $attribute)
+ $attr[$attribute->name] = $attribute->value;
+
+ if (@$attr["http-equiv"] == 'refresh') {
+ $path = $attr["content"];
+ $pathinfo = explode(";", $path);
+ $content = "";
+ foreach ($pathinfo AS $value) {
+ if (substr(strtolower($value), 0, 4) == "url=")
+ $content = substr($value, 4);
+ }
+ if ($content != "") {
+ $siteinfo = parseurl_getsiteinfo($content, $no_guessing, $do_oembed, ++$count);
+ return($siteinfo);
+ }
+ }
}
//$list = $xpath->query("head/title");
@@ -140,25 +204,59 @@ function parseurl_getsiteinfo($url) {
foreach ($list as $node) {
$attr = array();
if ($node->attributes->length)
- foreach ($node->attributes as $attribute)
- $attr[$attribute->name] = $attribute->value;
-
- $attr["content"] = html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8");
+ foreach ($node->attributes as $attribute)
+ $attr[$attribute->name] = $attribute->value;
+
+ $attr["content"] = trim(html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8"));
+
+ if ($attr["content"] != "")
+ switch (strtolower($attr["name"])) {
+ case "fulltitle":
+ $siteinfo["title"] = $attr["content"];
+ break;
+ case "description":
+ $siteinfo["text"] = $attr["content"];
+ break;
+ case "thumbnail":
+ $siteinfo["image"] = $attr["content"];
+ break;
+ case "twitter:image":
+ $siteinfo["image"] = $attr["content"];
+ break;
+ case "twitter:image:src":
+ $siteinfo["image"] = $attr["content"];
+ break;
+ case "twitter:card":
+ if (($siteinfo["type"] == "") OR ($attr["content"] == "photo"))
+ $siteinfo["type"] = $attr["content"];
+ break;
+ case "twitter:description":
+ $siteinfo["text"] = $attr["content"];
+ break;
+ case "twitter:title":
+ $siteinfo["title"] = $attr["content"];
+ break;
+ case "dc.title":
+ $siteinfo["title"] = $attr["content"];
+ break;
+ case "dc.description":
+ $siteinfo["text"] = $attr["content"];
+ break;
+ case "keywords":
+ $keywords = explode(",", $attr["content"]);
+ break;
+ case "news_keywords":
+ $keywords = explode(",", $attr["content"]);
+ break;
+ }
+ if ($siteinfo["type"] == "summary")
+ $siteinfo["type"] = "link";
+ }
- switch (strtolower($attr["name"])) {
- case "fulltitle":
- $siteinfo["title"] = $attr["content"];
- break;
- case "description":
- $siteinfo["text"] = $attr["content"];
- break;
- case "dc.title":
- $siteinfo["title"] = $attr["content"];
- break;
- case "dc.description":
- $siteinfo["text"] = $attr["content"];
- break;
- }
+ if (isset($keywords)) {
+ $siteinfo["keywords"] = array();
+ foreach ($keywords as $keyword)
+ $siteinfo["keywords"][] = trim($keyword);
}
//$list = $xpath->query("head/meta[@property]");
@@ -166,31 +264,41 @@ function parseurl_getsiteinfo($url) {
foreach ($list as $node) {
$attr = array();
if ($node->attributes->length)
- foreach ($node->attributes as $attribute)
- $attr[$attribute->name] = $attribute->value;
-
- $attr["content"] = html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8");
+ foreach ($node->attributes as $attribute)
+ $attr[$attribute->name] = $attribute->value;
+
+ $attr["content"] = trim(html_entity_decode($attr["content"], ENT_QUOTES, "UTF-8"));
+
+ if ($attr["content"] != "")
+ switch (strtolower($attr["property"])) {
+ case "og:image":
+ $siteinfo["image"] = $attr["content"];
+ break;
+ case "og:title":
+ $siteinfo["title"] = $attr["content"];
+ break;
+ case "og:description":
+ $siteinfo["text"] = $attr["content"];
+ break;
+ }
+ }
- switch (strtolower($attr["property"])) {
- case "og:image":
- $siteinfo["image"] = $attr["content"];
- break;
- case "og:title":
- $siteinfo["title"] = $attr["content"];
- break;
- case "og:description":
- $siteinfo["text"] = $attr["content"];
- break;
- }
+ if (isset($oembed_data) AND ($oembed_data->type == "link") AND ($siteinfo["type"] != "photo")) {
+ if (isset($oembed_data->title) AND (trim($oembed_data->title) != ""))
+ $siteinfo["title"] = $oembed_data->title;
+ if (isset($oembed_data->description) AND (trim($oembed_data->description) != ""))
+ $siteinfo["text"] = trim($oembed_data->description);
+ if (isset($oembed_data->thumbnail_url) AND (trim($oembed_data->thumbnail_url) != ""))
+ $siteinfo["image"] = $oembed_data->thumbnail_url;
}
- if (@$siteinfo["image"] == "") {
- $list = $xpath->query("//img[@src]");
- foreach ($list as $node) {
- $attr = array();
- if ($node->attributes->length)
- foreach ($node->attributes as $attribute)
- $attr[$attribute->name] = $attribute->value;
+ if ((@$siteinfo["image"] == "") AND !$no_guessing) {
+ $list = $xpath->query("//img[@src]");
+ foreach ($list as $node) {
+ $attr = array();
+ if ($node->attributes->length)
+ foreach ($node->attributes as $attribute)
+ $attr[$attribute->name] = $attribute->value;
$src = completeurl($attr["src"], $url);
$photodata = @getimagesize($src);
@@ -209,7 +317,7 @@ function parseurl_getsiteinfo($url) {
"height"=>$photodata[1]);
}
- }
+ }
} else {
$src = completeurl($siteinfo["image"], $url);
@@ -223,7 +331,7 @@ function parseurl_getsiteinfo($url) {
"height"=>$photodata[1]);
}
- if (@$siteinfo["text"] == "") {
+ if ((@$siteinfo["text"] == "") AND (@$siteinfo["title"] != "") AND !$no_guessing) {
$text = "";
$list = $xpath->query("//div[@class='article']");
@@ -252,10 +360,14 @@ function parseurl_getsiteinfo($url) {
while (strpos($text, " "))
$text = trim(str_replace(" ", " ", $text));
- $siteinfo["text"] = html_entity_decode(substr($text,0,350), ENT_QUOTES, "UTF-8").'...';
+ $siteinfo["text"] = trim(html_entity_decode(substr($text,0,350), ENT_QUOTES, "UTF-8").'...');
}
}
+ logger("parseurl_getsiteinfo: Siteinfo for ".$url." ".print_r($siteinfo, true), LOGGER_DEBUG);
+
+ call_hooks('getsiteinfo', $siteinfo);
+
return($siteinfo);
}
@@ -295,12 +407,21 @@ function parse_url_content(&$a) {
}
}
+ // add url scheme if missing
+ $arrurl = parse_url($url);
+ if (!x($arrurl, 'scheme')) {
+ if (x($arrurl, 'host'))
+ $url = "http:".$url;
+ else
+ $url = "http://".$url;
+ }
+
logger('parse_url: ' . $url);
if($textmode)
- $template = $br . '[bookmark=%s]%s[/bookmark]%s' . $br;
+ $template = '[bookmark=%s]%s[/bookmark]%s';
else
- $template = "
%s%s
";
+ $template = "%s%s";
$arr = array('url' => $url, 'text' => '');
@@ -314,13 +435,15 @@ function parse_url_content(&$a) {
if($url && $title && $text) {
- if($textmode)
- $text = $br . '[quote]' . trim($text) . '[/quote]' . $br;
- else
- $text = '
' . trim($text) . '
' . htmlspecialchars(trim($text)) . '
'.trim($text).'
'.htmlspecialchars(trim($text)).''; } - if($image) { + if($image) $text = $br.$br.$image.$text; - } + else + $text = $br.$text; + $title = str_replace(array("\r","\n"),array('',''),$title); $result = sprintf($template,$url,($title) ? $title : $url,$text) . $str_tags; logger('parse_url: returns: ' . $result); - echo trim($result); + $sitedata .= trim($result); + + if (($siteinfo["type"] == "video") AND ($url != "")) + echo "[class=type-video]".$sitedata."[/class]"; + elseif (($siteinfo["type"] != "photo")) + echo "[class=type-link]".$sitedata."[/class]"; + else + echo "[class=type-photo]".$title.$br.$image."[/class]"; + killme(); } +?>