function testData_Text_HTMLParser()
{
$content = "<a href='#'>Go Daddy</a><attr name='attr'>ATTR</attr>\r\n\t\t\t\t\t\t<p align=\"center\"><a href=\"http://www.myspace.com/declareyourself\" target=\"_blank\">\r\n\t\t\t\t\t\t<img src=\"http://creative.myspace.com/groups/_jc/declareyourself/dy_badge.jpg\" border=\"0\" />\r\n\t\t\t\t\t\t</a></p>";
$res = HTMLParser::StripTags($content);
$this->assertEqual($res, strip_tags($content), "Error while stripping all tags");
$res = HTMLParser::StripTags($content, 'attr');
$this->assertFalse(stristr($res, '<attr'), "Error while stripping [attr] tag");
$nolinks = HTMLParser::StripTags($content, 'a');
$this->assertFalse(stristr($nolinks, 'href'), "Error while stripping [a] tag");
$nolinks = HTMLParser::StripLinks($content);
$this->assertFalse(stristr($nolinks, 'href'), "Error while stripping links");
$res = HTMLParser::StripScripts($content);
$this->assertEqual($res, $content, "Error while stripping scripts");
$res = HTMLParser::StripTags($content, 'img');
$this->assertFalse(stristr($res, 'img'), "Error while stripping [img] tag");
}
/**
* Parse personal details from content
*
* @return array profile details
* sample
* [userpic] => http://www.livejournal.com/userpic/38353247/8981002
* [name] => Natalie
* [website] => http://www.myspace.com/aggressiva
* [city] => La Verne
* [state] => California
* [country] => United States
* [birthday] => 1971-12-15
* [aboutme] => party ... I just believe in parties!
*/
function GetPersonalDetails()
{
$details = array();
$pattern = '/><[0-9]*b>(user|name|website|location|birthdate|gizmo\/lj talk|bio|e\-mail)\:<[0-9]*\/b><[0-9]*\/td><([0-9]*)td[^>]*>(.*?)<\\2\/td>/msi';
$this->Result = HTMLParser::AddTagDepth($this->Result);
preg_match_all($pattern, $this->Result, $matches, PREG_SET_ORDER);
$this->Result = HTMLParser::RemoveTagDepth($this->Result);
foreach($matches as $match)
{
$match[2] = HTMLParser::RemoveTagDepth(trim($match[3]));
switch ($match[1])
{
case 'Name':
$details['name'] = $match[2];
break;
case 'Website':
if (preg_match("/href=(\'|\")(.*?)\\1/", $match[2], $match2))
{
$details['website'] = $match2[2];
}
break;
case 'Location':
preg_match_all("/loc\_(ci|st|cn)\=[^>\&]+>(.*?)</msi", $match[2], $match2, PREG_SET_ORDER);
foreach($match2 as $res)
{
if ($res[1] == 'ci')
$details['city'] = $res[2];
elseif ($res[1] == 'st')
$details['state'] = $res[2];
elseif ($res[1] == 'cn')
$details['country'] = $res[2];
}
break;
case 'Bio':
$details['aboutme'] = $match[2];
break;
case 'Birthdate':
$details['birthday'] = $match[2];
break;
case 'E-mail':
$details['email'] = HTMLParser::StripTags($match[2]);
break;
}
}
if (preg_match("/http\:\/\/([a-z0-9\-]+\.)+[a-z0-9]{2,6}\/userpic\/[0-9]+\/[0-9]+/msi", $this->Result, $matches))
{
$details['userpic'] = $matches[0];
}
//echo '<xmp>'; print_r($details); echo '</xmp>'; exit;
return $details;
}
/**
* Find differences between multiline strings and return formatted new
* string
*
* @param string $string_old Old string
* @param string $string_new New string
* @return string New formatted string
* @uses HTMLParser HTML Parser method StripTags
* @access public
*/
public function GetHighlitedDiff($string_old, $string_new)
{
$string_new = HTMLParser::StripTags($string_new);
$string_old = HTMLParser::StripTags($string_old);
$patch = $this->Diff($string_old, $string_new);
if ($patch)
{
$patch = preg_replace($this->Statements, $this->Replacements, $patch);
$string_new = $this->Patch($string_old, $patch);
}
return $string_new;
}
/**
* Parse personal details from content
*
* @return array profile details
*/
function GetPersonalDetails()
{
if (!$this->Result) return;
$details = array();
$pattern = '/<li>[\s\t\r\n]*<strong>[\s\t\r\n]*(age|gender|industry|occupation|location)\:[\s\t\r\n]*<\/strong>[\s\t\r\n]*(.*?)[\s\t\r\n]*<\/li>/msi';
preg_match_all($pattern, $this->Result, $matches, PREG_SET_ORDER);
foreach($matches as $match)
{
switch ($match[1])
{
case 'Age':
$details['age'] = $match[2];
break;
case 'Gender':
$details['gender'] = $match[2];
break;
case 'Location':
$locations = explode(":", $match[2]);
$locations = array_map('trim', $locations);
$details['city'] = HTMLParser::StripLinks($locations[0]);
$details['state'] = HTMLParser::StripLinks($locations[1]);
$details['country'] = HTMLParser::StripLinks($locations[2]);
break;
case 'Industry':
$details['industry'] = $match[2];
break;
case 'Occupation':
$details['occupation'] = $match[2];
break;
}
}
$pattern = '/<h2>(About\sMe|Interests)<\/h2>[\s\t\r\n]*<([a-z]+)\b[^>]*>(.*?)<\/\\2>/msi';
preg_match_all($pattern, $this->Result, $matches, PREG_SET_ORDER);
foreach($matches as $match)
{
switch ($match[1])
{
case 'About Me':
$details['aboutme'] = $match[3];
break;
// #todo - separators needed
case 'Interests':
$details['interests'] = HTMLParser::StripTags($match[3]);
break;
}
}
return $details;
}
