Created
November 16, 2015 23:05
-
-
Save JaviPedrera/ebc29de9947c10ba37c1 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
class yahooScraper { | |
/** | |
* Properties | |
*/ | |
private $html; | |
private $resultsContainer; | |
private $resultsCount; | |
private $titles; | |
private $links; | |
private $cache; | |
private $bodies; | |
/** | |
* [scrapUrl] | |
* This function will scrap an URL by saving the desired tags into properties | |
*/ | |
public function scrapUrl($url) | |
{ | |
$this->html = file_get_contents($url); | |
// Extract the results ordered list | |
preg_match('/\<ol class\=\" reg searchCenterMiddle\">(.*?)\<\/ol\>/i', $this->html, $result); | |
$this->resultsContainer = $result[0]; | |
// Extract one of each elements to display | |
preg_match_all('/\<h3(.*?)\<\/h3\>/i', $this->resultsContainer, $this->titles); | |
preg_match_all('/\<p(.*?)\<\/p\>/i', $this->resultsContainer, $this->bodies); | |
preg_match_all('/\<span(.*?)\<\/span\>/i', $this->resultsContainer, $this->links); | |
preg_match_all('/\<a(.*?)\<\/a\>/i', $this->resultsContainer, $this->cache); | |
// Get the total results number for the subsequent iteration | |
$this->resultsCount = count($this->titles[0]); | |
} | |
/** | |
* [printScrap] | |
* This function will print the scraped content automatically | |
*/ | |
public function printScrap() | |
{ | |
for ($i=0; $i < $this->resultsCount; $i++) { | |
echo strip_tags($this->titles[0][$i]); | |
echo "<br/>"; | |
echo strip_tags($this->links[0][$i]) . " - " . strip_tags($this->cache[0][$i]); | |
echo "<br/>"; | |
echo strip_tags($this->bodies[0][$i]); | |
echo "<br/>"; | |
echo "<br/>"; | |
} | |
} | |
} | |
$scraper = new yahooScraper(); | |
$scraper->scrapUrl('https://es.search.yahoo.com/search?p=madrid&fr=yfp-t-777'); | |
$scraper->printScrap(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment