Created
December 17, 2012 14:27
-
-
Save joshuabaker/4318654 to your computer and use it in GitHub Desktop.
Incomplete PHP script to scrape twitter.com for a specific user’s timeline. It’s incomplete because the email functionality has not been completed. The idea here was to email it to IFTTT, Evernote or similar for archiving.
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 | |
// Enter your Twitter screen name | |
$screen_name = 'joshuabaker'; | |
// Optionally enter your email address | |
$from_email = ''; | |
// ------------------------------------------------------------------- | |
// DON’T EDIT BELOW THIS LINE UNLESS YOU KNOW WHAT YOU’RE DOING! | |
$html = file_get_contents('http://twitter.com/'.$screen_name); | |
$html = mb_convert_encoding($html, 'utf-8', mb_detect_encoding($html)); | |
$html = mb_convert_encoding($html, 'html-entities', 'utf-8'); | |
$doc = new DOMDocument(); | |
$doc->loadHTML($html); | |
$nodes = $doc->getElementsByTagName('p'); | |
$tweets = array(); | |
foreach ($nodes as $node) | |
{ | |
if ($node->hasAttributes() && $class = $node->attributes->getNamedItem('class')) | |
{ | |
if (in_array('js-tweet-text', explode(' ', $class->nodeValue))) | |
{ | |
$tweet = $doc->saveXML($node, LIBXML_NOEMPTYTAG); | |
$tweet = strip_tags($tweet); | |
$tweet = str_replace(' ', '', $tweet); | |
$tweet = trim($tweet, '…'); | |
$tweet = trim($tweet); | |
$tweets[] = trim($node->nodeValue); | |
} | |
} | |
} | |
print_r($tweets); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment