note 97518 added to book.dom
| From: | ben_demott at hotmail dot com | Date: | Fri, 23 Apr 2010 20:36:47 +0000 |
| Subject: | note 97518 added to book.dom | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-168574@lists.php.net to get a copy of this message | ||
A function among several others to parse a google results page, I wrote this some time ago - google
has probably changed their site since then, but I thought this might be helpful to someone.
I'm moving servers, but I will probably throw this up on my blog when I get it back up.
<?php
function googleResult($listItem) {
// given a LIST ITEM element, this will validate, and return an array for that LI entry as an
inline result from google.
/*
* <li class='g w0'>
* <h3 class='r'>
* <a href='the URL' class='l'>
* Description <em>description</em>
* </a>
* </h3>
* </li>
*
UPDATE:
This function will now look for any subcontainer that has an href, it doesn't have to be an
H3
this will make it work with a few more formatted search results.
*/
$listItem = $listItem->childNodes;
// Yes I don't use instanceof - I guess you'll have to deal.
foreach($listItem as $element) {
if(is_object($element) && get_class($element) == 'DOMElement' &&
$element->hasChildNodes()) {
$hrefContainer = $element->childNodes;
foreach($hrefContainer as $element2) {
if(is_object($element2) && get_class($element2) == 'DOMElement' &&
$element2->nodeName == 'a' && $element2->hasAttribute('href')) {
$anchor = $element2;
unset($h3);
unset($element2);
break;
} else {
//print __LINE__ ." :: Breaking out of loop (normal result) element is not an annchor
Element='".$element2->nodeName."'\n";
}
}
unset($element);
unset($listItem);
break;
}
}
if(empty($anchor) || !is_object($anchor) || get_class($anchor) != 'DOMElement') {
//print __LINE__ ." :: Returning false, did not locate anchor through iteration...";
return false;
}
$href = $anchor->getAttribute('href');
if(empty($href)) {
//print __LINE__ ." :: Found anchor object, could not read href attribute / href is empty?
href='$href'\n";
return false;
}
$description = $anchor->childNodes;
$urlDescription = '';
foreach($description as $words) {
$name = trim($words->nodeName);
if($name == 'em' || $name == '#text' || $name == 'b') {
if(!empty($words->nodeValue)) {
$text = trim($words->nodeValue);
$urlDescription = $urlDescription . $text . ' ';
}
}
}
$urlDescription = htmlspecialchars_decode($urlDescription, ENT_QUOTES);
$urlDescription = trim($urlDescription);
return array('description' => $urlDescription, 'href' => $href);
}
----
Server IP: 208.69.120.55
Probable Submitter: 69.129.20.250
----
Manual Page -- http://www.php.net/manual/en/book.dom.php
Edit -- https://master.php.net/note/edit/97518
Del: integrated -- https://master.php.net/note/delete/97518/integrated
Del: useless -- https://master.php.net/note/delete/97518/useless
Del: bad code -- https://master.php.net/note/delete/97518/bad+code
Del: spam -- https://master.php.net/note/delete/97518/spam
Del: non-english -- https://master.php.net/note/delete/97518/non-english
Del: in docs -- https://master.php.net/note/delete/97518/in+docs
Del: other reasons-- https://master.php.net/note/delete/97518
Reject -- https://master.php.net/note/reject/97518
Search -- https://master.php.net/manage/user-notes.php