// curl wrapper. If binary flag is true, return binary
// results.
+// Set the cookiejar argument to a string (e.g. "/tmp/friendica-cookies.txt")
+// to preserve cookies from one request to the next.
if(! function_exists('fetch_url')) {
-function fetch_url($url,$binary = false, &$redirects = 0, $timeout = 0, $accept_content=Null) {
+function fetch_url($url,$binary = false, &$redirects = 0, $timeout = 0, $accept_content=Null, $cookiejar = 0) {
+
+ $stamp1 = microtime(true);
$a = get_app();
$ch = @curl_init($url);
- if(($redirects > 8) || (! $ch))
+ if(($redirects > 8) || (! $ch))
return false;
@curl_setopt($ch, CURLOPT_HEADER, true);
-
+
+ if($cookiejar) {
+ curl_setopt($ch, CURLOPT_COOKIEJAR, $cookiejar);
+ curl_setopt($ch, CURLOPT_COOKIEFILE, $cookiejar);
+ }
+
+// These settings aren't needed. We're following the location already.
+// @curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
+// @curl_setopt($ch, CURLOPT_MAXREDIRS, 5);
+
if (!is_null($accept_content)){
curl_setopt($ch,CURLOPT_HTTPHEADER, array (
"Accept: " . $accept_content
));
}
-
+
@curl_setopt($ch, CURLOPT_RETURNTRANSFER,true);
- @curl_setopt($ch, CURLOPT_USERAGENT, "Friendica");
+ //@curl_setopt($ch, CURLOPT_USERAGENT, "Friendica");
+ @curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (compatible; Friendica)");
if(intval($timeout)) {
$base = $s;
$curl_info = @curl_getinfo($ch);
$http_code = $curl_info['http_code'];
-
// logger('fetch_url:' . $http_code . ' data: ' . $s);
$header = '';
}
if($http_code == 301 || $http_code == 302 || $http_code == 303 || $http_code == 307) {
- $matches = array();
- preg_match('/(Location:|URI:)(.*?)\n/', $header, $matches);
- $newurl = trim(array_pop($matches));
+ $new_location_info = @parse_url($curl_info["redirect_url"]);
+ $old_location_info = @parse_url($curl_info["url"]);
+
+ $newurl = $curl_info["redirect_url"];
+
+ if (($new_location_info["path"] == "") AND ($new_location_info["host"] != ""))
+ $newurl = $new_location_info["scheme"]."://".$new_location_info["host"].$old_location_info["path"];
+
+ $matches = array();
+ if (preg_match('/(Location:|URI:)(.*?)\n/', $header, $matches)) {
+ $newurl = trim(array_pop($matches));
+ }
if(strpos($newurl,'/') === 0)
- $newurl = $url . $newurl;
- $url_parsed = @parse_url($newurl);
- if (isset($url_parsed)) {
- $redirects++;
- return fetch_url($newurl,$binary,$redirects,$timeout);
- }
- }
+ $newurl = $old_location_info["scheme"]."://".$old_location_info["host"].$newurl;
+ if (filter_var($newurl, FILTER_VALIDATE_URL)) {
+ $redirects++;
+ return fetch_url($newurl,$binary,$redirects,$timeout,$accept_content,$cookiejar);
+ }
+ }
$a->set_curl_code($http_code);
+ $a->set_curl_content_type($curl_info['content_type']);
$body = substr($s,strlen($header));
-
$a->set_curl_headers($header);
-
@curl_close($ch);
+
+ $a->save_timestamp($stamp1, "network");
+
return($body);
}}
if(! function_exists('post_url')) {
function post_url($url,$params, $headers = null, &$redirects = 0, $timeout = 0) {
+
+ $stamp1 = microtime(true);
+
$a = get_app();
$ch = curl_init($url);
- if(($redirects > 8) || (! $ch))
+ if(($redirects > 8) || (! $ch))
return false;
curl_setopt($ch, CURLOPT_HEADER, true);
preg_match('/(Location:|URI:)(.*?)\n/', $header, $matches);
$newurl = trim(array_pop($matches));
if(strpos($newurl,'/') === 0)
- $newurl = $url . $newurl;
- $url_parsed = @parse_url($newurl);
- if (isset($url_parsed)) {
+ $newurl = $old_location_info["scheme"] . "://" . $old_location_info["host"] . $newurl;
+ if (filter_var($newurl, FILTER_VALIDATE_URL)) {
$redirects++;
return fetch_url($newurl,false,$redirects,$timeout);
}
$a->set_curl_headers($header);
curl_close($ch);
+
+ $a->save_timestamp($stamp1, "network");
+
return($body);
}}
if($link['@attributes']['rel'] === NAMESPACE_DFRN)
$profile_link = $link['@attributes']['href'];
if($link['@attributes']['rel'] === NAMESPACE_OSTATUSSUB)
- $profile_link = 'stat:' . $link['@attributes']['template'];
+ $profile_link = 'stat:' . $link['@attributes']['template'];
if($link['@attributes']['rel'] === 'http://microformats.org/profile/hcard')
- $hcard = $link['@attributes']['href'];
+ $hcard = $link['@attributes']['href'];
}
}
return $profile_link;
logger('lrdd: constructed url: ' . $url);
$xml = fetch_url($url);
+
$headers = $a->get_curl_headers();
if (! $xml)
elseif(x($link['@attributes'],'href'))
$href = $link['@attributes']['href'];
}
- }
+ }
}
if((! isset($tpl)) || (! strpos($tpl,'{uri}')))
$lines = explode("\n",$headers);
if(count($lines)) {
- foreach($lines as $line) {
+ foreach($lines as $line) {
if((stristr($line,'link:')) && preg_match('/<([^>].*)>.*rel\=[\'\"]lrdd[\'\"]/',$line,$matches)) {
return(fetch_xrd_links($matches[1]));
break;
$lines = explode("\n",$headers);
if(count($lines)) {
- foreach($lines as $line) {
+ foreach($lines as $line) {
// TODO alter the following regex to support multiple relations (space separated)
if((stristr($line,'link:')) && preg_match('/<([^>].*)>.*rel\=[\'\"]lrdd[\'\"]/',$line,$matches)) {
$pagelink = $matches[1];
if(! function_exists('validate_url')) {
function validate_url(&$url) {
-
+
// no naked subdomains (allow localhost for tests)
if(strpos($url,'.') === false && strpos($url,'/localhost/') === false)
return false;
if(substr($url,0,4) != 'http')
$url = 'http://' . $url;
$h = @parse_url($url);
-
+
if(($h) && (dns_get_record($h['host'], DNS_A + DNS_CNAME + DNS_PTR) || filter_var($h['host'], FILTER_VALIDATE_IP) )) {
return true;
}
if(! function_exists('validate_email')) {
function validate_email($addr) {
+ if(get_config('system','disable_email_validation'))
+ return true;
+
if(! strpos($addr,'@'))
return false;
$h = substr($addr,strpos($addr,'@') + 1);
`alias` = '%s',
`pubkey` = '%s',
`updated` = '%s'
- WHERE `url` = '%s' AND `network` = '%s' LIMIT 1",
+ WHERE `url` = '%s' AND `network` = '%s'",
dbesc($arr['name']),
dbesc($arr['photo']),
dbesc($arr['request']),
}
-function scale_external_images($s,$include_link = true) {
+function scale_external_images($srctext, $include_link = true, $scale_replace = false) {
$a = get_app();
+ // Picture addresses can contain special characters
+ $s = htmlspecialchars_decode($srctext);
+
$matches = null;
- $c = preg_match_all('/\[img\](.*?)\[\/img\]/ism',$s,$matches,PREG_SET_ORDER);
+ $c = preg_match_all('/\[img.*?\](.*?)\[\/img\]/ism',$s,$matches,PREG_SET_ORDER);
if($c) {
require_once('include/Photo.php');
foreach($matches as $mtch) {
logger('scale_external_image: ' . $mtch[1]);
+
$hostname = str_replace('www.','',substr($a->get_baseurl(),strpos($a->get_baseurl(),'://')+3));
if(stristr($mtch[1],$hostname))
continue;
- $i = fetch_url($mtch[1]);
+
+ // $scale_replace, if passed, is an array of two elements. The
+ // first is the name of the full-size image. The second is the
+ // name of a remote, scaled-down version of the full size image.
+ // This allows Friendica to display the smaller remote image if
+ // one exists, while still linking to the full-size image
+ if($scale_replace)
+ $scaled = str_replace($scale_replace[0], $scale_replace[1], $mtch[1]);
+ else
+ $scaled = $mtch[1];
+ $i = @fetch_url($scaled);
+ if(! $i)
+ return $srctext;
+
+ $cachefile = get_cachefile(hash("md5", $scaled));
+ if ($cachefile != '') {
+ $stamp1 = microtime(true);
+ file_put_contents($cachefile, $i);
+ $a->save_timestamp($stamp1, "file");
+ }
+
+ // guess mimetype from headers or filename
+ $type = guess_image_type($mtch[1],true);
+
if($i) {
- $ph = new Photo($i);
+ $ph = new Photo($i, $type);
if($ph->is_valid()) {
$orig_width = $ph->getWidth();
$orig_height = $ph->getHeight();
$new_width = $ph->getWidth();
$new_height = $ph->getHeight();
logger('scale_external_images: ' . $orig_width . '->' . $new_width . 'w ' . $orig_height . '->' . $new_height . 'h' . ' match: ' . $mtch[0], LOGGER_DEBUG);
- $s = str_replace($mtch[0],'[img=' . $new_width . 'x' . $new_height. ']' . $mtch[1] . '[/img]'
+ $s = str_replace($mtch[0],'[img=' . $new_width . 'x' . $new_height. ']' . $scaled . '[/img]'
. "\n" . (($include_link)
? '[url=' . $mtch[1] . ']' . t('view full size') . '[/url]' . "\n"
: ''),$s);
}
}
}
+
+ // replace the special char encoding
+ $s = htmlspecialchars($s,ENT_NOQUOTES,'UTF-8');
return $s;
}
}
}
+
+
+/**
+ * xml2array() will convert the given XML text to an array in the XML structure.
+ * Link: http://www.bin-co.com/php/scripts/xml2array/
+ * Portions significantly re-written by mike@macgirvin.com for Friendica (namespaces, lowercase tags, get_attribute default changed, more...)
+ * Arguments : $contents - The XML text
+ * $namespaces - true or false include namespace information in the returned array as array elements.
+ * $get_attributes - 1 or 0. If this is 1 the function will get the attributes as well as the tag values - this results in a different array structure in the return value.
+ * $priority - Can be 'tag' or 'attribute'. This will change the way the resulting array sturcture. For 'tag', the tags are given more importance.
+ * Return: The parsed XML in an array form. Use print_r() to see the resulting array structure.
+ * Examples: $array = xml2array(file_get_contents('feed.xml'));
+ * $array = xml2array(file_get_contents('feed.xml', true, 1, 'attribute'));
+ */
+
+function xml2array($contents, $namespaces = true, $get_attributes=1, $priority = 'attribute') {
+ if(!$contents) return array();
+
+ if(!function_exists('xml_parser_create')) {
+ logger('xml2array: parser function missing');
+ return array();
+ }
+
+
+ libxml_use_internal_errors(true);
+ libxml_clear_errors();
+
+ if($namespaces)
+ $parser = @xml_parser_create_ns("UTF-8",':');
+ else
+ $parser = @xml_parser_create();
+
+ if(! $parser) {
+ logger('xml2array: xml_parser_create: no resource');
+ return array();
+ }
+
+ xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, "UTF-8");
+ // http://minutillo.com/steve/weblog/2004/6/17/php-xml-and-character-encodings-a-tale-of-sadness-rage-and-data-loss
+ xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
+ xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, 1);
+ @xml_parse_into_struct($parser, trim($contents), $xml_values);
+ @xml_parser_free($parser);
+
+ if(! $xml_values) {
+ logger('xml2array: libxml: parse error: ' . $contents, LOGGER_DATA);
+ foreach(libxml_get_errors() as $err)
+ logger('libxml: parse: ' . $err->code . " at " . $err->line . ":" . $err->column . " : " . $err->message, LOGGER_DATA);
+ libxml_clear_errors();
+ return;
+ }
+
+ //Initializations
+ $xml_array = array();
+ $parents = array();
+ $opened_tags = array();
+ $arr = array();
+
+ $current = &$xml_array; // Reference
+
+ // Go through the tags.
+ $repeated_tag_index = array(); // Multiple tags with same name will be turned into an array
+ foreach($xml_values as $data) {
+ unset($attributes,$value); // Remove existing values, or there will be trouble
+
+ // This command will extract these variables into the foreach scope
+ // tag(string), type(string), level(int), attributes(array).
+ extract($data); // We could use the array by itself, but this cooler.
+
+ $result = array();
+ $attributes_data = array();
+
+ if(isset($value)) {
+ if($priority == 'tag') $result = $value;
+ else $result['value'] = $value; // Put the value in a assoc array if we are in the 'Attribute' mode
+ }
+
+ //Set the attributes too.
+ if(isset($attributes) and $get_attributes) {
+ foreach($attributes as $attr => $val) {
+ if($priority == 'tag') $attributes_data[$attr] = $val;
+ else $result['@attributes'][$attr] = $val; // Set all the attributes in a array called 'attr'
+ }
+ }
+
+ // See tag status and do the needed.
+ if($namespaces && strpos($tag,':')) {
+ $namespc = substr($tag,0,strrpos($tag,':'));
+ $tag = strtolower(substr($tag,strlen($namespc)+1));
+ $result['@namespace'] = $namespc;
+ }
+ $tag = strtolower($tag);
+
+ if($type == "open") { // The starting of the tag '<tag>'
+ $parent[$level-1] = &$current;
+ if(!is_array($current) or (!in_array($tag, array_keys($current)))) { // Insert New tag
+ $current[$tag] = $result;
+ if($attributes_data) $current[$tag. '_attr'] = $attributes_data;
+ $repeated_tag_index[$tag.'_'.$level] = 1;
+
+ $current = &$current[$tag];
+
+ } else { // There was another element with the same tag name
+
+ if(isset($current[$tag][0])) { // If there is a 0th element it is already an array
+ $current[$tag][$repeated_tag_index[$tag.'_'.$level]] = $result;
+ $repeated_tag_index[$tag.'_'.$level]++;
+ } else { // This section will make the value an array if multiple tags with the same name appear together
+ $current[$tag] = array($current[$tag],$result); // This will combine the existing item and the new item together to make an array
+ $repeated_tag_index[$tag.'_'.$level] = 2;
+
+ if(isset($current[$tag.'_attr'])) { // The attribute of the last(0th) tag must be moved as well
+ $current[$tag]['0_attr'] = $current[$tag.'_attr'];
+ unset($current[$tag.'_attr']);
+ }
+
+ }
+ $last_item_index = $repeated_tag_index[$tag.'_'.$level]-1;
+ $current = &$current[$tag][$last_item_index];
+ }
+
+ } elseif($type == "complete") { // Tags that ends in 1 line '<tag />'
+ //See if the key is already taken.
+ if(!isset($current[$tag])) { //New Key
+ $current[$tag] = $result;
+ $repeated_tag_index[$tag.'_'.$level] = 1;
+ if($priority == 'tag' and $attributes_data) $current[$tag. '_attr'] = $attributes_data;
+
+ } else { // If taken, put all things inside a list(array)
+ if(isset($current[$tag][0]) and is_array($current[$tag])) { // If it is already an array...
+
+ // ...push the new element into that array.
+ $current[$tag][$repeated_tag_index[$tag.'_'.$level]] = $result;
+
+ if($priority == 'tag' and $get_attributes and $attributes_data) {
+ $current[$tag][$repeated_tag_index[$tag.'_'.$level] . '_attr'] = $attributes_data;
+ }
+ $repeated_tag_index[$tag.'_'.$level]++;
+
+ } else { // If it is not an array...
+ $current[$tag] = array($current[$tag],$result); //...Make it an array using using the existing value and the new value
+ $repeated_tag_index[$tag.'_'.$level] = 1;
+ if($priority == 'tag' and $get_attributes) {
+ if(isset($current[$tag.'_attr'])) { // The attribute of the last(0th) tag must be moved as well
+
+ $current[$tag]['0_attr'] = $current[$tag.'_attr'];
+ unset($current[$tag.'_attr']);
+ }
+
+ if($attributes_data) {
+ $current[$tag][$repeated_tag_index[$tag.'_'.$level] . '_attr'] = $attributes_data;
+ }
+ }
+ $repeated_tag_index[$tag.'_'.$level]++; // 0 and 1 indexes are already taken
+ }
+ }
+
+ } elseif($type == 'close') { // End of tag '</tag>'
+ $current = &$parent[$level-1];
+ }
+ }
+
+ return($xml_array);
+}