Created
December 4, 2020 15:59
-
-
Save javedbaloch4/0269047ebba2bc1d53429573cf371124 to your computer and use it in GitHub Desktop.
Simple Web Scrapping in PHP.
This file contains hidden or 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 | |
// Using the library https://simplehtmldom.sourceforge.io | |
include("simple_html_dom.php"); | |
# Example 1 - Get the title of webpage. | |
$html = file_get_html("https://www.google.com"); | |
// Returns title of web page. | |
$html->find('title' ,0)->plaintext; | |
# Example 2 - Get Navigation / & Other examples | |
$list = $html->find('div[class="w3-bar w3-left"]', 0); | |
/* | |
$list_array = $list->find('a'); | |
echo sizeof($list_array); | |
for ($i = 0; $i < sizeof($list_array); $i++) { | |
echo $list_array[$i]; | |
echo "<br>"; | |
} | |
*/ | |
/* | |
foreach ($list->find('a') as $key => $element) { | |
echo $key . " " .$element->plaintext; | |
echo "<br>"; | |
} | |
*/ | |
/* | |
foreach ($html->find('div') as $element) { | |
echo $element; | |
echo "<br>"; | |
} | |
*/ | |
/* | |
foreach ($html->find('a') as $element) { | |
// echo $element; | |
if ($element->plaintext == 'HTML' || $element->plaintext == 'CSS') { | |
echo $element; | |
} | |
} | |
*/ | |
/* | |
foreach ($html->find('p') as $element) { | |
echo $element; | |
echo "<br>"; | |
} | |
*/ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment