Created
June 18, 2012 08:08
-
-
Save maxcal/2947417 to your computer and use it in GitHub Desktop.
Simple Curl web scraper
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 | |
/** | |
* @param string $url - the url you wish to fetch. | |
* @return string - the raw html respose. | |
*/ | |
function web_scrape($url) { | |
$ch = curl_init($url); | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE); | |
$response = curl_exec($ch); | |
curl_close($ch); | |
return $response; | |
} | |
/** | |
* | |
* @param string $url - the url you wish to fetch. | |
* @return array - the http headers returned | |
*/ | |
function fetch_headers($url) { | |
$ch = curl_init($url); | |
curl_setopt($ch, CURLOPT_HEADER, 1); | |
$response = curl_exec($ch); | |
curl_close($ch); | |
return $response; | |
} | |
//var_dump(get_headers("https://www.google.se/")); | |
// echo web_scrape('https://www.google.se/'); | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment