Flickr photoset downloader. Simple and stupid.

flickr-downloader.php

<?php

# Config.

/*

Requires:

- Array of photo-ids, you can get them via the included js. Just run it in the console a bunch of times on the photo-set page. Crude but works.
- Public subdirectory from this script's location named 'photos'.
- The url pattern for the original-photo pages. 

Sample urls:

http://www.flickr.com/photos/themuseumofmodernart/4479621448/sizes/o - Pages.
http://farm3.staticflickr.com/2779/4479621448_nnnnnnnnnn_o.jpg - Images.
http://farm5.staticflickr.com/4060/4479434490_nnnnnnnnnn_o.jpg

*/

$file = 'flickr-photo-ids.php';
$page_url_format = 'http://www.flickr.com/photos/themuseumofmodernart/%d/sizes/o';
$image_url_pattern = '/<img src="(.*\.jpg)">/';
$image_dir = __DIR__.'/photos';

# Script.

function d_log($str, $is_section=false){
  if ($is_section) echo PHP_EOL;
  echo $str.PHP_EOL;
  if ($is_section) echo PHP_EOL;
  return;
}
function d_log_thru(){
  call_user_func_array('d_log', func_get_args());
  return func_get_arg(0);
}

function make_handle($url){
  $handle = curl_init();
  curl_setopt_array($handle, array(
    CURLOPT_URL => $url,
    CURLOPT_RETURNTRANSFER => 1,
    CURLOPT_CONNECTTIMEOUT => 10,
    CURLOPT_USERAGENT => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/537.22 (KHTML, like Gecko) Chrome/25.0.1364.36 Safari/537.22',
  ));
  return $handle;
}

function get_html($url){
  $html = curl_exec(make_handle($url));
  return $html;
}

function get_image($html, $pattern){
  if ($html === false) return d_log('No html!');
  $matches = array();
  if (preg_match($pattern, $html, $matches) === 0) return false;
  return $matches[1];
}

function save_image($url, $name){
  if (!isset($url)) return;
  file_put_contents(d_log_thru("$image_dir/$name.jpg"), curl_exec(make_handle($url)));
}

include $file;

if (!isset($ids)) {
  d_log("No photo ids; '$file' not found!", true);
  die;
}

d_log('Starting in '.__DIR__.'...', true);

$total = count($ids);
$chunks = array_chunk($ids, 10);
$from_chunk = 1;
$until_chunk = $total + 1;
$image_ordl = 0;

foreach ($chunks as $i => $ids) {

  $chunk_ordl = $i + 1;
  if ($chunk_ordl >= $until_chunk || $chunk_ordl < $from_chunk) continue;

  foreach ($ids as $j => $id) {
    $image_ordl++;
    save_image(
      get_image(
        get_html(sprintf($page_url_format, $id))
      , $image_url_pattern)
    , "{$image_ordl}_{$id}");
  }

  d_log('Taking a break...', true);

  sleep(5);
}

d_log('Done!', true);

flickr-id-reaper.js

var d = document, A = Array.prototype;
setTimeout(function(){ d.querySelector('[data-track=next]').click(); }, 10000); // Click next for us.
A.slice.call(d.querySelectorAll('[data-photo-id]')).map(function(el){ return el.getAttribute('data-photo-id'); }); // Copy the output from the console.