[17225] | 1 | <?php |
---|
| 2 | if (!defined('PBASE_PATH')) die('Hacking attempt!'); |
---|
| 3 | |
---|
| 4 | /** |
---|
| 5 | * get the content of web-page, with cache management |
---|
| 6 | * @param: string url |
---|
| 7 | * @return: string |
---|
| 8 | */ |
---|
| 9 | function get_file_cached($url) |
---|
| 10 | { |
---|
| 11 | // html files are cached 10000 seconds |
---|
| 12 | $cache_id_prefix = str_replace('http://www.pbase.com/', null, $url); |
---|
[17434] | 13 | $cache_id_prefix = preg_replace('#([^a-z0-9-_]+)#i', null, $cache_id_prefix); |
---|
[17225] | 14 | $cache_id = $cache_id_prefix.'-'.substr(time(), 0, -4); |
---|
| 15 | |
---|
| 16 | if (!file_exists(PBASE_FS_CACHE.$cache_id)) |
---|
| 17 | { |
---|
| 18 | $files = glob(PBASE_FS_CACHE.$cache_id_prefix.'-*'); |
---|
| 19 | foreach ($files as $file) unlink($file); |
---|
| 20 | |
---|
| 21 | if (($result = download_remote_file($url, PBASE_FS_CACHE.$cache_id)) !== true) |
---|
| 22 | { |
---|
| 23 | return $result; |
---|
| 24 | } |
---|
| 25 | } |
---|
| 26 | |
---|
| 27 | $html = file_get_contents(PBASE_FS_CACHE.$cache_id); |
---|
| 28 | |
---|
| 29 | return utf8_encode($html); |
---|
| 30 | } |
---|
| 31 | |
---|
| 32 | /** |
---|
| 33 | * helper to navigate throught the tree |
---|
| 34 | * @param: &array tree |
---|
| 35 | * @param: string path |
---|
| 36 | * @return: reference to a branch of the tree |
---|
| 37 | */ |
---|
| 38 | function &get_current_cat(&$tree, $path) |
---|
| 39 | { |
---|
| 40 | if (empty($path)) return $tree; |
---|
| 41 | |
---|
| 42 | $path = ltrim($path, '/'); |
---|
| 43 | $path = explode('/', $path); |
---|
| 44 | $current = &$tree[ $path[0] ]; |
---|
| 45 | array_shift($path); |
---|
| 46 | |
---|
| 47 | foreach ($path as $folder) |
---|
| 48 | { |
---|
| 49 | $current = &$current['categories'][$folder]; |
---|
| 50 | } |
---|
| 51 | |
---|
| 52 | return $current; |
---|
| 53 | } |
---|
| 54 | |
---|
| 55 | /** |
---|
| 56 | * check if give account (http://pbase.com/login/root) exists |
---|
| 57 | * @param: string url |
---|
| 58 | * @return: bool |
---|
| 59 | */ |
---|
| 60 | function check_account($url) |
---|
| 61 | { |
---|
| 62 | $html = get_file_cached($url); |
---|
| 63 | return !(bool)preg_match('#<h2>Unknown Account</h2>#i', $html); |
---|
| 64 | } |
---|
| 65 | |
---|
| 66 | /** |
---|
| 67 | * parse a category page |
---|
| 68 | * @param: string category url |
---|
| 69 | * @param: bool parse only sub-categories |
---|
| 70 | * @param: bool parse only one level |
---|
| 71 | * @return: array category |
---|
| 72 | */ |
---|
| 73 | function parse_category($url, $path, $cats_only=false, $one_level=false) |
---|
| 74 | { |
---|
| 75 | $url = str_replace('&page=all', null, $url); |
---|
| 76 | |
---|
| 77 | $current = array( |
---|
| 78 | 'url' => $url, |
---|
| 79 | 'path' => null, |
---|
| 80 | 'id' => null, |
---|
| 81 | ); |
---|
| 82 | |
---|
| 83 | // id |
---|
| 84 | $temp = parse_url($url); |
---|
| 85 | $temp = explode('/', $temp['path']); |
---|
| 86 | $current['id'] = $temp[ count($temp)-1 ]; |
---|
| 87 | $current['path'] = $path.'/'.$current['id']; |
---|
| 88 | |
---|
| 89 | if ($one_level === 'stop') |
---|
| 90 | { |
---|
| 91 | return $current; |
---|
| 92 | } |
---|
| 93 | |
---|
| 94 | $current = array_merge($current, array( |
---|
| 95 | 'title' => null, |
---|
| 96 | 'description' => null, |
---|
| 97 | 'pictures' => array(), |
---|
| 98 | 'categories' => array(), |
---|
| 99 | 'nb_pictures' => 0, |
---|
| 100 | 'nb_categories' => 0, |
---|
| 101 | )); |
---|
| 102 | |
---|
| 103 | |
---|
| 104 | $url.= '&page=all'; // seriously... (should be ? not &) |
---|
| 105 | |
---|
| 106 | |
---|
| 107 | $html = get_file_cached($url); |
---|
| 108 | if ($html == 'file_error') |
---|
| 109 | { |
---|
| 110 | return $current; |
---|
| 111 | } |
---|
| 112 | |
---|
| 113 | preg_match('#<body>(.*)</body>#is', $html, $matches); |
---|
| 114 | $body = $matches[1]; |
---|
| 115 | |
---|
| 116 | // content |
---|
| 117 | // if (preg_match('#<CENTER>(.*)</CENTER>#is', $body, $matches) === 0) return 'null1'; |
---|
| 118 | if (preg_match_all('#<A HREF="([^">]*)" class="thumbnail">#i', $body, $matches) === 0) return $current; |
---|
| 119 | $links = $matches[1]; |
---|
| 120 | |
---|
| 121 | // title |
---|
| 122 | if (preg_match('#<h2>(.*?)</h2>#i', $body, $matches)) |
---|
| 123 | { |
---|
| 124 | $current['title'] = trim($matches[1]); |
---|
| 125 | } |
---|
| 126 | else |
---|
| 127 | { |
---|
| 128 | $current['title'] = $current['id']; |
---|
| 129 | } |
---|
| 130 | |
---|
| 131 | // description |
---|
| 132 | if (preg_match('#<!-- BEGIN user desc -->(.*?)<!-- END user desc -->#s', $body, $matches)) |
---|
| 133 | { |
---|
| 134 | $current['description'] = trim($matches[1]); |
---|
| 135 | } |
---|
| 136 | |
---|
| 137 | // sub-cats and pictures |
---|
| 138 | foreach ($links as $link) |
---|
| 139 | { |
---|
| 140 | if (strpos($link, '/image/') !== false) |
---|
| 141 | { |
---|
| 142 | if (($image = parse_image($link, $cats_only)) !== null) |
---|
| 143 | { |
---|
| 144 | $current['pictures'][ $image['id'] ] = $image; |
---|
| 145 | } |
---|
| 146 | $current['nb_pictures']++; |
---|
| 147 | } |
---|
| 148 | else |
---|
| 149 | { |
---|
| 150 | $next_level = ($one_level === true) ? 'stop' : false; |
---|
| 151 | if (($category = parse_category($link, $current['path'], $cats_only, $next_level)) !== null) |
---|
| 152 | { |
---|
| 153 | $current['categories'][ $category['id'] ] = $category; |
---|
| 154 | } |
---|
| 155 | $current['nb_categories']++; |
---|
| 156 | } |
---|
| 157 | } |
---|
| 158 | |
---|
| 159 | return $current; |
---|
| 160 | } |
---|
| 161 | |
---|
| 162 | /** |
---|
| 163 | * parse a picture page |
---|
| 164 | * @param: string picture url |
---|
| 165 | * @param: bool return only url and id |
---|
| 166 | * @return: array picture |
---|
| 167 | */ |
---|
| 168 | function parse_image($url, $light=false) |
---|
| 169 | { |
---|
| 170 | $url = preg_replace('#/(small|medium|large|original)$#', null, $url); |
---|
| 171 | |
---|
| 172 | $current = array( |
---|
| 173 | 'url' => $url, |
---|
| 174 | 'id' => null, |
---|
| 175 | ); |
---|
| 176 | |
---|
| 177 | // id |
---|
| 178 | $temp = parse_url($url); |
---|
| 179 | $temp = explode('/', $temp['path']); |
---|
| 180 | $current['id'] = $temp[ count($temp)-1 ]; |
---|
| 181 | |
---|
| 182 | if ($light) |
---|
| 183 | { |
---|
| 184 | return $current; |
---|
| 185 | } |
---|
| 186 | |
---|
| 187 | $current = array_merge($current, array( |
---|
| 188 | 'title' => null, |
---|
| 189 | 'path' => null, |
---|
| 190 | 'description' => null, |
---|
| 191 | 'date' => null, |
---|
| 192 | 'author' => null, |
---|
| 193 | 'keywords' => array(), |
---|
| 194 | )); |
---|
| 195 | |
---|
| 196 | $url.= '/original'; |
---|
| 197 | |
---|
| 198 | |
---|
| 199 | $html = get_file_cached($url); |
---|
| 200 | if ($html == 'file_error') |
---|
| 201 | { |
---|
| 202 | return $current; |
---|
| 203 | } |
---|
| 204 | |
---|
| 205 | preg_match('#<body>(.*)</body>#is', $html, $matches); |
---|
| 206 | $body = $matches[1]; |
---|
| 207 | |
---|
| 208 | // path |
---|
| 209 | if (preg_match('#<IMG ([^>]*)class="display" src="([^">]*)"#i', $body, $matches) ===0) return null; |
---|
| 210 | $current['path'] = $matches[2]; |
---|
| 211 | |
---|
| 212 | // title |
---|
| 213 | preg_match('#<span class="title">(.*?)</span>#i', $body, $matches); |
---|
| 214 | if (!empty($matches[1])) |
---|
| 215 | { |
---|
| 216 | $current['title'] = trim($matches[1]); |
---|
| 217 | $current['title'] = get_filename_wo_extension($current['title']); |
---|
| 218 | } |
---|
| 219 | else |
---|
| 220 | { |
---|
| 221 | $current['title'] = $current['id']; |
---|
| 222 | } |
---|
| 223 | |
---|
| 224 | // description |
---|
| 225 | if (preg_match('#<p class="caption">(.*?)</p>#is', $body, $matches)) |
---|
| 226 | { |
---|
| 227 | $current['description'] = trim($matches[1]); |
---|
| 228 | } |
---|
| 229 | |
---|
| 230 | // date |
---|
| 231 | if (preg_match('#<span class=date>(.*?)</span>#i', $body, $matches)) |
---|
| 232 | { |
---|
| 233 | $current['date'] = trim($matches[1]); |
---|
| 234 | } |
---|
| 235 | |
---|
| 236 | // author |
---|
| 237 | if (preg_match('#<span class=artist>(.*?)</span>#i', $body, $matches)) |
---|
| 238 | { |
---|
| 239 | $current['author'] = trim($matches[1]); |
---|
| 240 | } |
---|
| 241 | |
---|
| 242 | |
---|
| 243 | preg_match('#<head>(.*)</head>#is', $html, $matches); |
---|
| 244 | $head = $matches[1]; |
---|
| 245 | |
---|
| 246 | // keywords |
---|
| 247 | if (preg_match('#<meta name="keywords" content="([^">]*)">#i', $head, $matches)) |
---|
| 248 | { |
---|
| 249 | $words = explode(',', $matches[1]); |
---|
| 250 | foreach ($words as $word) |
---|
| 251 | { |
---|
| 252 | if (!empty($word)) $current['keywords'][] = trim($word); |
---|
| 253 | } |
---|
| 254 | } |
---|
| 255 | |
---|
| 256 | return $current; |
---|
| 257 | } |
---|
| 258 | |
---|
| 259 | /** |
---|
| 260 | * print categories tree (list or select) |
---|
| 261 | * @param: array tree |
---|
| 262 | * @param: int level |
---|
| 263 | * @param: string tree type (list|select) |
---|
| 264 | * @return: string |
---|
| 265 | */ |
---|
| 266 | function print_tree(&$tree, $level=0, $type='list') |
---|
| 267 | { |
---|
| 268 | $out = ''; |
---|
| 269 | |
---|
| 270 | if ($type == 'list') |
---|
| 271 | { |
---|
| 272 | $out.= '<ul>'; |
---|
| 273 | foreach ($tree as $item) |
---|
| 274 | { |
---|
| 275 | $out.= '<li>'; |
---|
| 276 | $out.= '<a href="'.$item['url'].'">'.$item['title'].'</a> ['.$item['nb_pictures'].']'; |
---|
| 277 | if (!empty($item['categories'])) |
---|
| 278 | $out.= print_tree($item['categories'], $level+1, 'list'); |
---|
| 279 | $out.= '</li>'; |
---|
| 280 | } |
---|
| 281 | $out.= '</ul>'; |
---|
| 282 | } |
---|
| 283 | else if ($type == 'select') |
---|
| 284 | { |
---|
| 285 | $i=0; |
---|
| 286 | foreach ($tree as $item) |
---|
| 287 | { |
---|
| 288 | $out.= '<option value="'.$item['path'].'"'; |
---|
| 289 | if ($level==0 and $i==0) $out.= ' selected="selected"'; |
---|
| 290 | $out.= '>'; |
---|
| 291 | |
---|
| 292 | $out.= str_repeat(' ', $level*4); |
---|
| 293 | $out.= '- '.$item['title'].' ['.$item['nb_pictures'].']'; |
---|
| 294 | |
---|
| 295 | $out.= '</option>'; |
---|
| 296 | |
---|
| 297 | if (!empty($item['categories'])) |
---|
| 298 | $out.= print_tree($item['categories'], $level+1, 'select'); |
---|
| 299 | |
---|
| 300 | $i++; |
---|
| 301 | } |
---|
| 302 | } |
---|
| 303 | |
---|
| 304 | return $out; |
---|
| 305 | } |
---|
| 306 | |
---|
| 307 | /** |
---|
| 308 | * test if a download method is available |
---|
| 309 | * @return: bool |
---|
| 310 | */ |
---|
[17314] | 311 | if (!function_exists('test_remote_download')) |
---|
[17225] | 312 | { |
---|
[17314] | 313 | function test_remote_download() |
---|
| 314 | { |
---|
| 315 | return function_exists('curl_init') || ini_get('allow_url_fopen'); |
---|
| 316 | } |
---|
[17225] | 317 | } |
---|
| 318 | |
---|
| 319 | /** |
---|
| 320 | * download a remote file |
---|
[17314] | 321 | * - needs cURL or allow_url_fopen |
---|
| 322 | * - take care of SSL urls |
---|
| 323 | * |
---|
| 324 | * @param: string source url |
---|
| 325 | * @param: mixed destination file (if true, file content is returned) |
---|
[17225] | 326 | */ |
---|
[17314] | 327 | if (!function_exists('download_remote_file')) |
---|
[17225] | 328 | { |
---|
[17314] | 329 | function download_remote_file($src, $dest) |
---|
[17225] | 330 | { |
---|
[17314] | 331 | if (empty($src)) |
---|
[17225] | 332 | { |
---|
[17314] | 333 | return false; |
---|
[17225] | 334 | } |
---|
| 335 | |
---|
[17314] | 336 | $return = ($dest === true) ? true : false; |
---|
[17225] | 337 | |
---|
[17314] | 338 | /* curl */ |
---|
| 339 | if (function_exists('curl_init')) |
---|
[17225] | 340 | { |
---|
[17314] | 341 | if (!$return) |
---|
| 342 | { |
---|
| 343 | $newf = fopen($dest, "wb"); |
---|
| 344 | } |
---|
| 345 | $ch = curl_init(); |
---|
| 346 | |
---|
| 347 | curl_setopt($ch, CURLOPT_URL, $src); |
---|
[19832] | 348 | curl_setopt($ch, CURLOPT_HEADER, false); |
---|
[17314] | 349 | curl_setopt($ch, CURLOPT_HTTPHEADER, array("Accept-language: en")); |
---|
| 350 | curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)'); |
---|
[21291] | 351 | curl_setopt($ch, CURLOPT_TIMEOUT, 30); |
---|
| 352 | if (!ini_get('safe_mode')) |
---|
| 353 | { |
---|
| 354 | curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); |
---|
| 355 | curl_setopt($ch, CURLOPT_MAXREDIRS, 1); |
---|
| 356 | } |
---|
[17314] | 357 | if (strpos($src, 'https://') !== false) |
---|
| 358 | { |
---|
| 359 | curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0); |
---|
| 360 | curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0); |
---|
| 361 | } |
---|
| 362 | if (!$return) |
---|
| 363 | { |
---|
| 364 | curl_setopt($ch, CURLOPT_FILE, $newf); |
---|
| 365 | } |
---|
| 366 | else |
---|
| 367 | { |
---|
| 368 | curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); |
---|
| 369 | } |
---|
| 370 | |
---|
[19832] | 371 | $out = curl_exec($ch); |
---|
| 372 | curl_close($ch); |
---|
| 373 | |
---|
| 374 | if ($out === false) |
---|
[17314] | 375 | { |
---|
| 376 | return 'file_error'; |
---|
| 377 | } |
---|
[19832] | 378 | else if (!$return) |
---|
[17314] | 379 | { |
---|
| 380 | fclose($newf); |
---|
| 381 | return true; |
---|
| 382 | } |
---|
| 383 | else |
---|
| 384 | { |
---|
| 385 | return $out; |
---|
| 386 | } |
---|
[17225] | 387 | } |
---|
[17314] | 388 | /* file get content */ |
---|
| 389 | else if (ini_get('allow_url_fopen')) |
---|
| 390 | { |
---|
| 391 | if (strpos($src, 'https://') !== false and !extension_loaded('openssl')) |
---|
| 392 | { |
---|
| 393 | return false; |
---|
| 394 | } |
---|
| 395 | |
---|
| 396 | $opts = array( |
---|
| 397 | 'http' => array( |
---|
| 398 | 'method' => "GET", |
---|
| 399 | 'user_agent' => 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)', |
---|
| 400 | 'header' => "Accept-language: en", |
---|
| 401 | ) |
---|
| 402 | ); |
---|
| 403 | |
---|
| 404 | $context = stream_context_create($opts); |
---|
| 405 | |
---|
| 406 | if (($file = file_get_contents($src, false, $context)) === false) |
---|
| 407 | { |
---|
| 408 | return 'file_error'; |
---|
| 409 | } |
---|
| 410 | |
---|
| 411 | if (!$return) |
---|
| 412 | { |
---|
| 413 | file_put_contents($dest, $file); |
---|
| 414 | return true; |
---|
| 415 | } |
---|
| 416 | else |
---|
| 417 | { |
---|
| 418 | return $file; |
---|
| 419 | } |
---|
| 420 | } |
---|
[17225] | 421 | |
---|
[17314] | 422 | return false; |
---|
[17225] | 423 | } |
---|
| 424 | } |
---|
| 425 | |
---|
| 426 | /** |
---|
| 427 | * count pictures and cats in the selected cat |
---|
| 428 | * @param: &array tree |
---|
| 429 | * @param: string $path |
---|
| 430 | * @param: &int nb pictures |
---|
| 431 | * @param: &int nb categories |
---|
| 432 | * @param: bool recursive |
---|
| 433 | * @return: void |
---|
| 434 | */ |
---|
| 435 | function count_pictures_cats(&$tree, $path, &$nb_pictures, &$nb_categories, $recursive=true) |
---|
| 436 | { |
---|
| 437 | $current = &get_current_cat($tree, $path); |
---|
| 438 | $nb_pictures+= $current['nb_pictures']; |
---|
| 439 | $nb_categories++; |
---|
| 440 | |
---|
| 441 | if ( $recursive and !empty($current['categories']) ) |
---|
| 442 | { |
---|
| 443 | foreach ($current['categories'] as $cat) |
---|
| 444 | { |
---|
| 445 | count_pictures_cats($tree, $cat['path'], $nb_pictures, $nb_categories, $recursive); |
---|
| 446 | } |
---|
| 447 | } |
---|
| 448 | } |
---|
| 449 | |
---|
| 450 | /** |
---|
| 451 | * extract unique values of the specified key in a two dimensional array |
---|
| 452 | * @param: array |
---|
| 453 | * @param: mixed key name |
---|
| 454 | * @return: array |
---|
| 455 | */ |
---|
[17314] | 456 | if (!function_exists('array_unique_deep')) |
---|
[17225] | 457 | { |
---|
[17314] | 458 | function array_unique_deep(&$array, $key) |
---|
[17225] | 459 | { |
---|
[17314] | 460 | $values = array(); |
---|
| 461 | foreach ($array as $k1 => $row) |
---|
[17225] | 462 | { |
---|
[17314] | 463 | foreach ($row as $k2 => $v) |
---|
[17225] | 464 | { |
---|
[17314] | 465 | if ($k2 == $key) |
---|
| 466 | { |
---|
| 467 | $values[ $k1 ] = $v; |
---|
| 468 | continue; |
---|
| 469 | } |
---|
[17225] | 470 | } |
---|
| 471 | } |
---|
[17314] | 472 | return array_unique($values); |
---|
[17225] | 473 | } |
---|
| 474 | } |
---|
| 475 | |
---|
| 476 | /** |
---|
| 477 | * search a string in array values |
---|
| 478 | * // http://www.strangeplanet.fr/blog/dev/php-une-fonction-pour-rechercher-dans-un-tableau |
---|
| 479 | * @param string needle |
---|
| 480 | * @param array haystack |
---|
| 481 | * @param bool return all instances |
---|
| 482 | * @param bool search in PCRE mode |
---|
| 483 | * @return key or array of keys |
---|
| 484 | */ |
---|
[17314] | 485 | if (!function_exists('array_pos')) |
---|
[17225] | 486 | { |
---|
[17314] | 487 | function array_pos($needle, &$haystack, $match_all=false, $preg_mode=false) |
---|
[17225] | 488 | { |
---|
[17314] | 489 | if ($match_all) $matches = array(); |
---|
| 490 | |
---|
| 491 | foreach ($haystack as $i => $row) |
---|
[17225] | 492 | { |
---|
[17314] | 493 | if (!is_array($row)) |
---|
[17225] | 494 | { |
---|
[17314] | 495 | if (!$preg_mode) |
---|
[17225] | 496 | { |
---|
[17314] | 497 | if (strpos($row, $needle) !== false) |
---|
| 498 | { |
---|
| 499 | if (!$match_all) return $i; |
---|
| 500 | else array_push($matches, $i); |
---|
| 501 | } |
---|
[17225] | 502 | } |
---|
[17314] | 503 | else |
---|
[17225] | 504 | { |
---|
[17314] | 505 | if (preg_match($needle, $row) === 1) |
---|
| 506 | { |
---|
| 507 | if (!$match_all) return $i; |
---|
| 508 | else array_push($matches, $i); |
---|
| 509 | } |
---|
[17225] | 510 | } |
---|
| 511 | } |
---|
| 512 | } |
---|
[17314] | 513 | |
---|
| 514 | if ( !$match_all or !count($matches) ) return false; |
---|
| 515 | return $matches; |
---|
[17225] | 516 | } |
---|
| 517 | } |
---|
| 518 | |
---|
| 519 | ?> |
---|