| 1 |
<?php |
| 2 |
include_once('simple_html_dom.php'); |
| 3 |
|
| 4 |
function scraping_generic($url, $search) { |
| 5 |
// Didn't find it yet. |
| 6 |
$return = false; |
| 7 |
|
| 8 |
echo "reading the url: " . $url . "<br/>"; |
| 9 |
// create HTML DOM |
| 10 |
$html = file_get_html($url); |
| 11 |
echo "url has been read.<br/>"; |
| 12 |
|
| 13 |
// get article block |
| 14 |
foreach($html->find($search) as $found) { |
| 15 |
// Found at least one. |
| 16 |
$return - true; |
| 17 |
echo "found a: " . $search . "<br/><pre>"; |
| 18 |
$found->dump(); |
| 19 |
echo "</pre><br/>"; |
| 20 |
} |
| 21 |
|
| 22 |
// clean up memory |
| 23 |
$html->clear(); |
| 24 |
unset($html); |
| 25 |
|
| 26 |
return $return; |
| 27 |
} |
| 28 |
|
| 29 |
|
| 30 |
// ------------------------------------------ |
| 31 |
error_log ("post:" . print_r($_POST, true)); |
| 32 |
$url = ""; |
| 33 |
if (isset($_POST['url'])) |
| 34 |
{ |
| 35 |
$url = $_POST['url']; |
| 36 |
} |
| 37 |
$search = ""; |
| 38 |
if (isset($_POST['search'])) |
| 39 |
{ |
| 40 |
$search = $_POST['search']; |
| 41 |
} |
| 42 |
?> |
| 43 |
<form method="post"> |
| 44 |
URL: <input name="url" type="text" value="<?=$url;?>"/><br/> |
| 45 |
Search: <input name="search" type="text" value="<?=$search;?>"/> |
| 46 |
<input name="submit" type="submit" value="Submit"/> |
| 47 |
</form> |
| 48 |
<?php |
| 49 |
// ----------------------------------------------------------------------------- |
| 50 |
// test it! |
| 51 |
if (isset ($_POST['submit'])) |
| 52 |
{ |
| 53 |
$response = scraping_generic($_POST['url'], $_POST['search']); |
| 54 |
if (!$response) |
| 55 |
{ |
| 56 |
echo "Did not find any: " . $_POST['search'] . "<br />"; |
| 57 |
} |
| 58 |
} |
| 59 |
?> |