function main()
{
$html = get_page(encode_cjk_url($_GET['url']));
$img_urls = parse_img_urls($html);
switch (count($img_urls)) {
case 0:
exit_with_msg('Images not found');
break;
case 1:
redirect_location(array_pop($img_urls));
break;
default:
output_zip(make_zip(fetch_and_store_images($img_urls)));
break;
}
}
/**
* Read short urls text file tumblr_likes.txt
* deal with every short url:
* 1 read the unwanted_files.txt for name of files that we don't need
* 2 fetch out long url of short url, if failed write the short url to invalid_urls.txt
* 3 fetch out resource uris inside html content of long url, filter this uris by the content of unwanted_files.txt
* 4 write out the resource uris to resource_urls.txt
* @param null $direct_url if specific deal with this single url instead of reading tumblr_likes.txt
*/
function main($direct_url = null)
{
$txt = $direct_url ? $direct_url : file_get_contents('tumblr_likes.txt');
if (preg_match_all('#http://ift.tt/.*#', $txt, $matches)) {
$unwanted = file_get_contents('unwanted_files.txt');
#deal with each short url
foreach ($matches[0] as $ori_url) {
try {
echo str_repeat('-', 30), "\n";
echo "Start: {$ori_url}\n";
#get long url
$redirect_url = get_redirect_target($ori_url);
if (!$redirect_url) {
file_put_contents('invalid_urls.txt', "{$ori_url}\n", FILE_APPEND);
throw new exception("invalid original URL {$ori_url}");
} else {
#file_put_contents('real_post_urls.txt', "$redirect_url\n", FILE_APPEND);
}
echo "Location fetched: {$redirect_url}\n";
#get html page content
$page_src = get_page_src($redirect_url);
if (!$page_src) {
throw new exception("zero length page_src");
}
printf("Page fetched: length(%d)\n", strlen($page_src));
#fetch out resource urls
$resource_urls = array();
$post_type = get_post_type($page_src);
switch ($post_type) {
case 'photo':
case 'photoset':
$resource_urls = parse_img_urls($page_src);
break;
case 'audio':
echo "fetching audio\n";
$resource_urls = parse_audio_url($page_src);
break;
case 'video':
echo "fetching video\n";
$resource_urls = parse_video_url($page_src);
break;
default:
echo 'unknown resource, trying images', "\n";
$resource_urls = parse_img_urls($page_src);
}
if (is_array($resource_urls)) {
foreach ($resource_urls as $index => $url) {
if (strpos($unwanted, basename($url)) !== false) {
unset($resource_urls[$index]);
}
}
$resource_urls = implode("\n", $resource_urls);
}
echo $resource_urls .= "\n";
file_put_contents('resource_urls.txt', $resource_urls, FILE_APPEND);
} catch (exception $e) {
echo 'Exception: ', $e->getMessage(), "\n";
}
}
}
}
