Created
March 25, 2014 14:33
-
-
Save kiang/9763078 to your computer and use it in GitHub Desktop.
A small script to collect links and extract titles
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 | |
$path = dirname(__FILE__); | |
$urlText = ''; | |
$urls = file_get_contents($path . '/tmp/list'); | |
$urls = explode("\n", $urls); | |
$urls = array_unique($urls); | |
natcasesort($urls); | |
if (!isset($_GET['op'])) { | |
$_GET['op'] = 'default'; | |
} | |
switch ($_GET['op']) { | |
case 'all': | |
foreach ($urls AS $url) { | |
$cache = $path . '/tmp/' . md5($url); | |
if (!file_exists($cache) || filesize($cache) < 10) { | |
file_put_contents($cache, file_get_contents($url)); | |
} | |
$news = file_get_contents($cache); | |
$titlePos = stripos($news, '<title'); | |
$titlePos = stripos($news, '>', $titlePos) + 1; | |
$title = ''; | |
if (false !== $titlePos) { | |
$titleEnd = stripos($news, '</title>', $titlePos); | |
$title = substr($news, $titlePos, $titleEnd - $titlePos); | |
$title = trim(str_replace(array("\n"), array(' '), $title)); | |
} | |
if(empty($news)) continue; | |
$charsetPos = stripos($news, 'charset='); | |
if(false !== $charsetPos) { | |
$charsetPos += 8; | |
$charsetEnd = stripos($news, '>', $charsetPos) + 1; | |
$fromEncoding = substr($news, $charsetPos, $charsetEnd - $charsetPos); | |
$fromEncoding = str_replace(array(' ', '/' , '>', '"', '\''), '', $fromEncoding); | |
} | |
$title = mb_convert_encoding($title, 'utf-8', $fromEncoding); | |
$urlText .= implode("\t", array( | |
$url, | |
$title, | |
)) . "\n"; | |
} | |
file_put_contents($path . '/tmp/list', implode("\n", $urls)); | |
break; | |
default: | |
if (!empty($_POST['urls'])) { | |
$newUrls = explode("\n", $_POST['urls']); | |
$fh = fopen($path . '/tmp/list', 'a'); | |
foreach ($newUrls AS $newUrl) { | |
$newUrl = trim($newUrl); | |
if (false === array_search($newUrl, $urls)) { | |
fputs($fh, $newUrl . "\n"); | |
$cache = $path . '/tmp/' . md5($newUrl); | |
if (!file_exists($cache) || filesize($cache) < 10) { | |
file_put_contents($cache, file_get_contents($newUrl)); | |
} | |
$news = file_get_contents($cache); | |
$titlePos = stripos($news, '<title'); | |
$titlePos = stripos($news, '>', $titlePos) + 1; | |
$title = ''; | |
if (false !== $titlePos) { | |
$titleEnd = stripos($news, '</title>', $titlePos); | |
$title = substr($news, $titlePos, $titleEnd - $titlePos); | |
$title = trim(str_replace(array("\n"), array(' '), $title)); | |
} | |
$urlText .= implode("\t", array( | |
$newUrl, | |
$title, | |
)) . "\n"; | |
} | |
} | |
fclose($fh); | |
} | |
} | |
?> | |
<form method="post" action="index.php?op=default"> | |
<textarea name="urls" cols="120" rows="30"><?php echo $urlText; ?></textarea> | |
<br /><br /><input type="submit" /> | |
<br /><br /><a href="index.php?op=all">show all</a> | |
</form> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment