Created
December 6, 2016 05:13
-
-
Save jongacnik/1dae2c9852b12e2b9a029fba4caab6ad to your computer and use it in GitHub Desktop.
Tumblr image scrape
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 | |
$offset = 0; | |
$count = 50; | |
$domain = $argv[1]; | |
$tagged = isset($argv[2]) ? $argv[2] : false; | |
$api = 'http://' . $domain . '.tumblr.com/api/read/json?debug=1&num=' . $count . ($tagged ? '&tagged=' . $tagged : ''); | |
function scrape ($api, $count, $offset) { | |
$endpoint = $api . '&start=' . ($count * $offset); | |
$json = json_decode(file_get_contents($endpoint)); | |
if (count($json->posts)) { | |
foreach($json->posts as $post) { | |
$post = (array) $post; | |
if (isset($post['photos']) { | |
foreach ($post['photos'] as $image) { | |
$image = (array) $image; | |
$url = $image['photo-url-1280']; | |
$filename = basename($url); | |
$img = file_get_contents($url); // get the image from the url | |
file_put_contents($filename, $img); // create a file | |
} | |
} | |
} | |
scrape($api, $count, $offset + 1); | |
} | |
} | |
scrape($api, $count, $offset); |
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
# from command line, will scrape tumblr-name.tumblr.com for all images: | |
$ php scrape.php tumblr-name | |
# optionally pass a tag to filter by: | |
$ php scrape.php tumblr-name tag |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment