/usr/share/php/PicoFeed/Scraper/RuleParser.php is in php-picofeed 0.1.18-1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | <?php
namespace PicoFeed\Scraper;
use DOMXPath;
use PicoFeed\Parser\XmlParser;
/**
* Rule Parser.
*
* @author Frederic Guillot
*/
class RuleParser implements ParserInterface
{
private $dom;
private $xpath;
private $rules = array();
/**
* Constructor.
*
* @param string $html
* @param array $rules
*/
public function __construct($html, array $rules)
{
$this->rules = $rules;
$this->dom = XmlParser::getHtmlDocument('<?xml version="1.0" encoding="UTF-8">'.$html);
$this->xpath = new DOMXPath($this->dom);
}
/**
* Get the relevant content with predefined rules.
*
* @return string
*/
public function execute()
{
$this->stripTags();
return $this->findContent();
}
/**
* Remove HTML tags.
*/
public function stripTags()
{
if (isset($this->rules['strip']) && is_array($this->rules['strip'])) {
foreach ($this->rules['strip'] as $pattern) {
$nodes = $this->xpath->query($pattern);
if ($nodes !== false && $nodes->length > 0) {
foreach ($nodes as $node) {
$node->parentNode->removeChild($node);
}
}
}
}
}
/**
* Fetch content based on Xpath rules.
*/
public function findContent()
{
$content = '';
if (isset($this->rules['body']) && is_array($this->rules['body'])) {
foreach ($this->rules['body'] as $pattern) {
$nodes = $this->xpath->query($pattern);
if ($nodes !== false && $nodes->length > 0) {
foreach ($nodes as $node) {
$content .= $this->dom->saveXML($node);
}
}
}
}
return $content;
}
}
|