moonvader
Reputation: 21091
Parsing XML with PHP. Duplicate node names
I am parsing xml file with simplexml_load_file() function. I have problem when i meet two nodes with same name. My XML file structure is:
<company>
<name>Test Co</name>
<link href="link1" rel="self"/>
<link href="link2" rel="www"/>
</company>
And here is the code:
$parametrs = simplexml_load_file("my.xml");
foreach ($parametrs->company as $param ) {
echo $param->name;
}
How can i echo link2 from each company?
Upvotes: 4
Views: 3165
Answers (4)
mineichen
Reputation: 500
You can use xPath:
<?php
$sxml = simplexml_load_string('<company>
<name>Test Co</name>
<link href="link1" rel="self"/>
<link href="link2" rel="www"/>
</company>');
$link = $sxml->xPath('//link[@rel="www"]');
var_dump($link);
http://codepad.viper-7.com/C4VU9q
Greetings
Upvotes: 0
Mona Abdelmajeed
Reputation: 686
You can try my class It uses simple xml
Here's Code
<?php
class xml_grabber
{
private $xml_file = '' ;
private $xml_link = '' ;
private $xml_dom = '' ;
private $xml_type = '' ;
private $xml_content = '' ;
private $xml_errors = array() ;
public $xml_stack = 0 ;
public $only_text = 0 ;
private $xml_connect_count = 0 ;
public function __construct($link_file_com = '')
{
if(!$link_file_com)
{
$this->xml_errors['construct'] = 'No Xml In Construct' ;
return false;
}
elseif(!function_exists('simplexml_load_file') || !function_exists('simplexml_load_string') || !function_exists('simplexml_import_dom'))
{
$this->xml_errors['functions'] = 'simple xml function not exists' ;
return false;
}
else
{
$this->set_xml(trim($link_file_com)) ;
}
}
public function only_text( $val = 0 )
{
$this->only_text = $val ;
}
public function set_xml($xml)
{
if(isset($xml{3}))
{
if(file_exists($xml))
{
$this->xml_type = 1 ;
$this->xml_file = $xml ;
}
elseif(filter_var($xml, FILTER_VALIDATE_URL))
{
$this->xml_type = 2 ;
$this->xml_link = $xml ;
}
else
{
$this->xml_type = 3 ;
$this->xml_dom = $xml ;
}
}
else
{
$this->xml_type = '' ;
}
}
public function get_xml()
{
if($this->xml_type == '')
{
return false ;
}
elseif($this->xml_type == 1)
{
return $this->xml_file ;
}
elseif($this->xml_type == 2)
{
return $this->xml_link ;
}
elseif($this->xml_type == 3)
{
return $this->xml_dom ;
}
}
public function set_columns($new_columns= array())
{
return $this->xml_columns = $new_columns ;
}
public function get_columns()
{
return $this->xml_columns ;
}
public function load()
{
if($this->xml_type == '')
{
$this->xml_errors['loader'] = 'Unknown XML type' ;
return false;
}
elseif($this->xml_type == 1)
{
$xml = simplexml_load_file($this->xml_file,null, LIBXML_NOCDATA) ;
$this->xml_content = $xml ;
}
elseif($this->xml_type == 2)
{
$con = $this->connect($this->xml_link);
$this->xml_content = simplexml_load_string(trim($con),null, LIBXML_NOCDATA) ;
}
elseif($this->xml_type == 3)
{
return $this->xml_dom ;
}
}
public function fetch($return = 'array')
{
$xml = array() ;
if($this->xml_content)
{
print_r ( $this->get_attribute($this->xml_content)) ;
}
}
public function get_attribute($object)
{
if( (is_array( $object ) || is_object( $object )) && count( $object ) > 0 )
{
foreach( $object as $k => $val )
{
$count = count( $val ) ;
$cou = count( $object->$k ) ;
if( $count > 0 and is_array( $val ) || is_object( $val ) )
{
if( $cou > 1 )
{
$result['item'][] = $this->get_attribute( $val ) ;
}
else
{
$result[$k] = $this->get_attribute( $val ) ;
}
}
else
{
$attr = $val->attributes() ;
if( count( $attr ) > 0 )
{
$var ;
foreach( $attr as $kk => $vv )
{
$var[$kk] = (string) $vv ;
}
if( $cou > 1 )
{
$result[$k][] = $var ;
}
else
{
$result[$k] = $var ;
}
}
else
{
$result[$k] = (string) $val ;
}
}
}
}
else
{
$result[] = $object ;
}
return $result ;
}
/*
public function fetch($return = 'array')
{
if($this->xml_content)
{
$rss_feed = $this->xml_content ;
$rss_title = (string) $rss_feed->channel->title ;
$rss_link = (string) $rss_feed->channel->link ;
$rss_cat = (string) $rss_feed->channel->category ;
$rss_image = (string) $rss_feed->channel->image->url ;
$rss_summary =
array
(
'info' =>
array(
'title'=>$rss_title ,
'link'=>$rss_link ,
'cat'=>$rss_cat ,
'image'=>$rss_image
) ,
'item' => array()
) ;
if(is_array($rss_feed->channel) or is_object($rss_feed->channel))
{
if(is_array($rss_feed->channel->item) or is_object($rss_feed->channel->item))
{
foreach($rss_feed->channel->item as $item)
{
if($item->enclosure && $item->enclosure->attributes())
{
$image0 = $item->enclosure->attributes() ;
$image_url = $image0 ['url'] ;
}
$result = array() ;
foreach($item as $k=>$v)
{
$result[strtolower($k)] = strip_tags((string) $v) ;
}
if(isset($image_url{1}))
{
$result['image0'] = $image_url ;
}
$rss_summary['item'][] = $result ;
}
}
elseif(is_array($rss_feed->channel->entry) or is_object($rss_feed->channel->entry))
{
foreach($rss_feed->channel->entry as $item)
{
if($item->enclosure && $item->enclosure->attributes())
{
$image0 = $item->enclosure->attributes() ;
$image_url = $image0 ['url'] ;
}
$result = array() ;
foreach($item as $k=>$v)
{
$result[strtolower($k)] = (string) $v ;
}
if(isset($image_url{1}))
{
$result['image0'] = $image_url ;
}
$rss_summary['item'][] = $result ;
}
}
}
else
{
if(is_array($rss_feed->item) or is_object($rss_feed->item))
{
foreach($rss_feed->item as $item)
{
if($item->enclosure && $item->enclosure->attributes())
{
$image0 = $item->enclosure->attributes() ;
$image_url = $image0 ['url'] ;
}
$result = array() ;
foreach($item as $k=>$v)
{
$result[strtolower($k)] = (string) $v ;
}
if(isset($image_url{1}))
{
$result['image0'] = $image_url ;
}
$rss_summary['item'][] = $result ;
}
}
elseif(is_array($rss_feed->entry) or is_object($rss_feed->entry))
{
foreach($rss_feed->entry as $item)
{
if($item->enclosure && $item->enclosure->attributes())
{
$image0 = $item->enclosure->attributes() ;
$image_url = $image0 ['url'] ;
}
$result = array() ;
foreach($item as $k=>$v)
{
$result[strtolower($k)] = (string) $v ;
}
if(isset($image_url{1}))
{
$result['image0'] = $image_url ;
}
$rss_summary['item'][] = $result ;
}
}
}
if($return == 'json')
{
return json_encode($rss_summary) ;
}
elseif($return == 'serialize')
{
return serialize($rss_summary) ;
}
elseif($return == 'xml')
{
return xml_encode($rss_summary) ;
}
else
{
return $rss_summary ;
}
}
else
{
$this->xml_errors['fetch'] = 'No Xml Content' ;
}
}
*/
protected function connect($link,$post='')
{
if(!filter_var($link, FILTER_VALIDATE_URL))
{
$this->xml_errors['connect'] = 'Not Vaild Link To Get data' ;
return false ;
}
if(function_exists('curl_init'))
{
$cu = curl_init();
curl_setopt($cu,CURLOPT_URL,$link);
curl_setopt($cu,CURLOPT_AUTOREFERER,true);
if($post != '')
{
curl_setopt($cu,CURLOPT_HEADER, 1);
curl_setopt($cu,CURLOPT_POST,3);
curl_setopt($cu,CURLOPT_POSTFIELDS,$post);
}
curl_setopt($cu,CURLOPT_USERAGENT,$_SERVER['HTTP_USER_AGENT']);
curl_setopt($cu,CURLOPT_SSL_VERIFYPEER,false);
curl_setopt($cu,CURLOPT_SSL_VERIFYHOST,false);
curl_setopt($cu,CURLOPT_RETURNTRANSFER,true);
$co = curl_exec($cu) ;
if($co)
{
$con = $co ;
}
else
{
$this->xml_errors['connect'] = 'No Result From Curl' ;
$this->xml_errors['curl'] = curl_error($cu);
}
curl_close($cu) ;
}
if(!$con and function_exists('ini_get'))
{
$url_fopen = ini_get('allow_url_fopen') ;
if($url_fopen == 0)
{
if(function_exists('ini_set'))
{
ini_set('allow_url_fopen', 1) ;
}
$check_fopen = 1 ;
}
else
{
$check_fopen = 0 ;
}
if($check_fopen == 1)
{
$url_fopen = ini_get('allow_url_fopen') ;
}
if($url_fopen == 1)
{
if(function_exists('file_get_contents') and !$con)
{
$con = @file_get_contents($link) ;
if($con)
{
$con ;
}
else
{
$this->xml_errors['connect'] = 'No Result From file_get_contents' ;
}
}
elseif(function_exists('readfile') and !$con)
{
$con = @readfile($link);
if($con)
{
$con ;
}
else
{
$this->xml_errors['connect'] = 'No Result From readfile' ;
}
}
elseif(function_exists('file') and !$con)
{
$con = @file($link) ;
if($con)
{
$con ;
}
else
{
$this->xml_errors['connect'] = 'No Result From file' ;
}
}
}
}
if(!$con)
{
$this->xml_errors['connect'] = 'Curl And Allow Url Fopen Disabled On Server' ;
return false ;
}
elseif(stripos($con,'DDoS protection by CloudFlare') and $this->xml_connect_count < 1)
{
echo '<h2> Curl Answer No : '.$this->xml_connect_count.' </h2>'.$con.'<br />';
preg_match('/'.preg_quote('.val(').'(.*?)'.preg_quote(');').'/is', $con, $match);
$matc = str_replace('+', " + ", $match[1]) ;
$matc = str_replace('*', " * ", $matc) ;
$post = eval ("return $matc ;") ;
$html=new DOMDocument();
$html->loadHTML($con) ;
$xpath = new DOMXPath($html);
$tags = $xpath->query('//input[@type="hidden"]');
$fields = array();
foreach ($tags as $tag) {
$fields[trim($tag->getAttribute('name'))] = trim($tag->getAttribute('value')) ;
}
$post_data = 'act=jschl&jschl_vc='.$fields['jschl_vc'].'&jschl_answer='.$post ;
echo '<h2> I will post this info to curl </h2>'.$post_data.'<br /> ' ;
$this->xml_connect_count = $this->xml_connect_count + 1 ;
sleep(5) ;
$con = $this->connect($link , $post_data) ;
echo '<h2> Curl Answer No : 1 </h2>'. $con.'<br />' ;
preg_match('/^Set-Cookie: (.*?);/m', $con, $m);
echo '<h2> Cookie from Result </h2>' ;var_dump(parse_url($m[1]));
}
else
{
return $con ;
}
}
public function get_error()
{
return $this->xml_errors ;
}
}
?>
Here's How to use it
<?php
$rss = new xml_grabber('xml.xml') ;
$rss -> load() ;
$x = $rss -> fetch() ;
print_r ( $x ) ;
?>
Example
<?xml version="1.0" encoding="Windows-1256"?>
<rss version="2.0">
<channel>
<info name="xml_reader" vesrion="1.0" author="sec.php"></info>
<title> Xml By sec.php </title>
<company>
<name>Test Co</name>
<link href="link1" rel="self"/>
<link href="link2" rel="www"/>
</company>
<company>
<name>Test Co</name>
<link href="link1" rel="self"/>
<link href="link2" rel="www"/>
</company>
<company>
<name>Test Co</name>
<link href="link1" rel="self"/>
<link href="link2" rel="www"/>
</company>
</channel>
</rss>
Result Array ( [channel] => Array ( [info] => Array ( [name] => xml_reader [vesrion] => 1.0 [author] => sec.php )
[title] => Xml By sec.php
[item] => Array
(
[0] => Array
(
[name] => Test Co
[link] => Array
(
[0] => Array
(
[href] => link1
[rel] => self
)
[1] => Array
(
[href] => link2
[rel] => www
)
)
)
[1] => Array
(
[name] => Test Co
[link] => Array
(
[0] => Array
(
[href] => link1
[rel] => self
)
[1] => Array
(
[href] => link2
[rel] => www
)
)
)
[2] => Array
(
[name] => Test Co
[link] => Array
(
[0] => Array
(
[href] => link1
[rel] => self
)
[1] => Array
(
[href] => link2
[rel] => www
)
)
)
)
)
)
Upvotes: -1
gen_Eric
Reputation: 227240
When you load an XML file into SimpleXML, the returned object represents the XML root node, <company> in your case.
So, you just simply need to get the 2nd link tag, and get its href.
$parametrs = simplexml_load_file("my.xml");
// you need to case here, as this is actually a SimpleXML element, not a string
echo (string)$parametrs->link[1]['href'];
Upvotes: 0
quickshiftin
Reputation: 69581
<?php
$xml = '<?xml version="1.0" ?>
<company>
<name>Test Co</name>
<link href="link1" rel="self"/>
<link href="link2" rel="www"/>
</company>';
$parameters = new SimpleXmlElement($xml);
echo (string)$parameters->link[1]['href']; // note you must cast here!
This will output 'link2' (without quotes around it).
Also, you may want to do some checking up front that these elements exist, but I'll leave that up to you as it's outside the scope of the question ;)
Upvotes: 3
Related Questions
- XML duplicate values - PHP
- Getting XML node names without duplicating in simplexml_load_file
- Why i getting duplicates when i import XML?
- Using PHP to remove xml duplicates
- PHP - Two same nodes in xml
- PHP XML and nodes with same name
- Repeating XML parsing with PHP
- Parsing data from XML file with multiple of same name attributes in PHP
- Trouble using PHP to parse an XML document with identical tags
- Parse only some of xml elements with same name