NNTmux /
newznab-tmux
| Total Complexity | 124 |
| Total Lines | 845 |
| Duplicated Lines | 0 % |
| Changes | 1 | ||
| Bugs | 0 | Features | 0 |
Complex classes like AbstractAdultProviderPipe often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use AbstractAdultProviderPipe, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 32 | abstract class AbstractAdultProviderPipe |
||
| 33 | { |
||
| 34 | protected int $priority = 50; |
||
| 35 | protected bool $echoOutput = true; |
||
| 36 | protected ?ColorCLI $colorCli = null; |
||
| 37 | protected ?HtmlDomParser $html = null; |
||
| 38 | protected ?string $cookie = null; |
||
| 39 | |||
| 40 | /** |
||
| 41 | * Minimum similarity threshold for matching (percentage). |
||
| 42 | */ |
||
| 43 | protected float $minimumSimilarity = 90.0; |
||
| 44 | |||
| 45 | /** |
||
| 46 | * HTTP client for making requests. |
||
| 47 | */ |
||
| 48 | protected ?Client $httpClient = null; |
||
| 49 | |||
| 50 | /** |
||
| 51 | * Cookie jar for maintaining session cookies. |
||
| 52 | */ |
||
| 53 | protected CookieJar|FileCookieJar|null $cookieJar = null; |
||
| 54 | |||
| 55 | /** |
||
| 56 | * Age verification manager for handling site-specific cookies. |
||
| 57 | */ |
||
| 58 | protected ?AgeVerificationManager $ageVerificationManager = null; |
||
| 59 | |||
| 60 | /** |
||
| 61 | * Maximum number of retry attempts for failed requests. |
||
| 62 | */ |
||
| 63 | protected int $maxRetries = 3; |
||
| 64 | |||
| 65 | /** |
||
| 66 | * Delay between retries in milliseconds. |
||
| 67 | */ |
||
| 68 | protected int $retryDelay = 1000; |
||
| 69 | |||
| 70 | /** |
||
| 71 | * Rate limit delay between requests in milliseconds. |
||
| 72 | */ |
||
| 73 | protected int $rateLimitDelay = 500; |
||
| 74 | |||
| 75 | /** |
||
| 76 | * Last request timestamp for rate limiting. |
||
| 77 | */ |
||
| 78 | protected static array $lastRequestTime = []; |
||
| 79 | |||
| 80 | /** |
||
| 81 | * Cache duration for search results in minutes. |
||
| 82 | */ |
||
| 83 | protected int $cacheDuration = 60; |
||
| 84 | |||
| 85 | /** |
||
| 86 | * Whether to use caching for this provider. |
||
| 87 | */ |
||
| 88 | protected bool $useCache = true; |
||
| 89 | |||
| 90 | public function __construct() |
||
| 91 | { |
||
| 92 | // Lazy load ColorCLI and HtmlDomParser to avoid serialization issues |
||
| 93 | } |
||
| 94 | |||
| 95 | /** |
||
| 96 | * Get the ColorCLI instance (lazy loaded). |
||
| 97 | */ |
||
| 98 | protected function getColorCli(): ColorCLI |
||
| 99 | { |
||
| 100 | if ($this->colorCli === null) { |
||
| 101 | $this->colorCli = new ColorCLI(); |
||
| 102 | } |
||
| 103 | return $this->colorCli; |
||
| 104 | } |
||
| 105 | |||
| 106 | /** |
||
| 107 | * Get the HtmlDomParser instance (lazy loaded). |
||
| 108 | */ |
||
| 109 | protected function getHtmlParser(): HtmlDomParser |
||
| 110 | { |
||
| 111 | if ($this->html === null) { |
||
| 112 | $this->html = new HtmlDomParser(); |
||
| 113 | } |
||
| 114 | return $this->html; |
||
| 115 | } |
||
| 116 | |||
| 117 | /** |
||
| 118 | * Handle the adult movie processing request. |
||
| 119 | */ |
||
| 120 | public function handle(AdultProcessingPassable $passable, Closure $next): AdultProcessingPassable |
||
| 121 | { |
||
| 122 | // If we already have a match, skip processing |
||
| 123 | if ($passable->shouldStopProcessing()) { |
||
| 124 | return $next($passable); |
||
| 125 | } |
||
| 126 | |||
| 127 | // Set the cookie from passable |
||
| 128 | $this->cookie = $passable->getCookie(); |
||
| 129 | |||
| 130 | // Skip if this provider shouldn't process |
||
| 131 | if ($this->shouldSkip($passable)) { |
||
| 132 | $passable->updateResult( |
||
| 133 | AdultProcessingResult::skipped('Provider skipped', $this->getName()), |
||
| 134 | $this->getName() |
||
| 135 | ); |
||
| 136 | return $next($passable); |
||
| 137 | } |
||
| 138 | |||
| 139 | // Output processing message |
||
| 140 | if ($this->echoOutput) { |
||
| 141 | $this->getColorCli()->info('Checking '.$this->getDisplayName().' for movie info'); |
||
| 142 | } |
||
| 143 | |||
| 144 | try { |
||
| 145 | // Apply rate limiting |
||
| 146 | $this->applyRateLimit(); |
||
| 147 | |||
| 148 | // Attempt to process with this provider |
||
| 149 | $result = $this->process($passable); |
||
| 150 | |||
| 151 | // Update the result |
||
| 152 | $passable->updateResult($result, $this->getName()); |
||
| 153 | } catch (\Exception $e) { |
||
| 154 | Log::error('Adult provider '.$this->getName().' failed: '.$e->getMessage(), [ |
||
| 155 | 'provider' => $this->getName(), |
||
| 156 | 'title' => $passable->getCleanTitle(), |
||
| 157 | 'exception' => get_class($e), |
||
| 158 | ]); |
||
| 159 | |||
| 160 | $passable->updateResult( |
||
| 161 | AdultProcessingResult::failed($e->getMessage(), $this->getName()), |
||
| 162 | $this->getName() |
||
| 163 | ); |
||
| 164 | } |
||
| 165 | |||
| 166 | return $next($passable); |
||
| 167 | } |
||
| 168 | |||
| 169 | /** |
||
| 170 | * Apply rate limiting between requests to the same provider. |
||
| 171 | */ |
||
| 172 | protected function applyRateLimit(): void |
||
| 173 | { |
||
| 174 | $providerName = $this->getName(); |
||
| 175 | $now = microtime(true) * 1000; |
||
| 176 | |||
| 177 | if (isset(self::$lastRequestTime[$providerName])) { |
||
| 178 | $elapsed = $now - self::$lastRequestTime[$providerName]; |
||
| 179 | if ($elapsed < $this->rateLimitDelay) { |
||
| 180 | usleep((int)(($this->rateLimitDelay - $elapsed) * 1000)); |
||
| 181 | } |
||
| 182 | } |
||
| 183 | |||
| 184 | self::$lastRequestTime[$providerName] = microtime(true) * 1000; |
||
| 185 | } |
||
| 186 | |||
| 187 | /** |
||
| 188 | * Get the priority of this provider (lower = higher priority). |
||
| 189 | */ |
||
| 190 | public function getPriority(): int |
||
| 191 | { |
||
| 192 | return $this->priority; |
||
| 193 | } |
||
| 194 | |||
| 195 | /** |
||
| 196 | * Get the internal name of this provider. |
||
| 197 | */ |
||
| 198 | abstract public function getName(): string; |
||
| 199 | |||
| 200 | /** |
||
| 201 | * Get the display name for user-facing output. |
||
| 202 | */ |
||
| 203 | abstract public function getDisplayName(): string; |
||
| 204 | |||
| 205 | /** |
||
| 206 | * Get the base URL for the provider. |
||
| 207 | */ |
||
| 208 | abstract protected function getBaseUrl(): string; |
||
| 209 | |||
| 210 | /** |
||
| 211 | * Attempt to process the movie through this provider. |
||
| 212 | */ |
||
| 213 | abstract protected function process(AdultProcessingPassable $passable): AdultProcessingResult; |
||
| 214 | |||
| 215 | /** |
||
| 216 | * Search for a movie on this provider. |
||
| 217 | * |
||
| 218 | * @return array|false Returns array with 'title' and 'url' keys on success, false on failure |
||
| 219 | */ |
||
| 220 | abstract protected function search(string $movie): array|false; |
||
| 221 | |||
| 222 | /** |
||
| 223 | * Get all movie information from the provider. |
||
| 224 | */ |
||
| 225 | abstract protected function getMovieInfo(): array|false; |
||
| 226 | |||
| 227 | /** |
||
| 228 | * Check if this provider should be skipped for the given passable. |
||
| 229 | */ |
||
| 230 | protected function shouldSkip(AdultProcessingPassable $passable): bool |
||
| 231 | { |
||
| 232 | return empty($passable->getCleanTitle()); |
||
| 233 | } |
||
| 234 | |||
| 235 | /** |
||
| 236 | * Set echo output flag. |
||
| 237 | */ |
||
| 238 | public function setEchoOutput(bool $echo): self |
||
| 239 | { |
||
| 240 | $this->echoOutput = $echo; |
||
| 241 | return $this; |
||
| 242 | } |
||
| 243 | |||
| 244 | /** |
||
| 245 | * Get cached search result if available. |
||
| 246 | */ |
||
| 247 | protected function getCachedSearch(string $movie): array|false|null |
||
| 248 | { |
||
| 249 | if (!$this->useCache) { |
||
| 250 | return null; |
||
| 251 | } |
||
| 252 | |||
| 253 | $cacheKey = 'adult_search_' . $this->getName() . '_' . md5(strtolower($movie)); |
||
| 254 | $cached = Cache::get($cacheKey); |
||
| 255 | |||
| 256 | if ($cached !== null) { |
||
| 257 | if ($this->echoOutput) { |
||
| 258 | $this->getColorCli()->info('Using cached result for: ' . $movie); |
||
| 259 | } |
||
| 260 | return $cached; |
||
| 261 | } |
||
| 262 | |||
| 263 | return null; |
||
| 264 | } |
||
| 265 | |||
| 266 | /** |
||
| 267 | * Cache a search result. |
||
| 268 | */ |
||
| 269 | protected function cacheSearchResult(string $movie, array|false $result): void |
||
| 270 | { |
||
| 271 | if (!$this->useCache) { |
||
| 272 | return; |
||
| 273 | } |
||
| 274 | |||
| 275 | $cacheKey = 'adult_search_' . $this->getName() . '_' . md5(strtolower($movie)); |
||
| 276 | Cache::put($cacheKey, $result, now()->addMinutes($this->cacheDuration)); |
||
| 277 | } |
||
| 278 | |||
| 279 | /** |
||
| 280 | * Fetch raw HTML from a URL with retry support. |
||
| 281 | */ |
||
| 282 | protected function fetchHtml(string $url, ?string $cookie = null, ?array $postData = null): string|false |
||
| 283 | { |
||
| 284 | $attempt = 0; |
||
| 285 | $lastException = null; |
||
| 286 | $ageVerificationAttempted = false; |
||
| 287 | |||
| 288 | while ($attempt < $this->maxRetries) { |
||
| 289 | try { |
||
| 290 | $attempt++; |
||
| 291 | $client = $this->getHttpClient(); |
||
| 292 | |||
| 293 | $options = [ |
||
| 294 | 'headers' => $this->getDefaultHeaders(), |
||
| 295 | ]; |
||
| 296 | |||
| 297 | // Add custom cookie if provided |
||
| 298 | if ($cookie) { |
||
| 299 | $options['headers']['Cookie'] = $cookie; |
||
| 300 | } |
||
| 301 | |||
| 302 | // Handle POST data |
||
| 303 | if ($postData !== null) { |
||
| 304 | $options['form_params'] = $postData; |
||
| 305 | $response = $client->post($url, $options); |
||
| 306 | } else { |
||
| 307 | $response = $client->get($url, $options); |
||
| 308 | } |
||
| 309 | |||
| 310 | $body = $response->getBody()->getContents(); |
||
| 311 | |||
| 312 | // Check if we were redirected to an age verification page |
||
| 313 | $finalUrl = $response->getHeaderLine('X-Guzzle-Redirect-History'); |
||
| 314 | if (empty($finalUrl)) { |
||
| 315 | // Use the effective URI if available |
||
| 316 | $effectiveUri = $response->getHeader('X-Guzzle-Redirect-History'); |
||
| 317 | if (!empty($effectiveUri)) { |
||
| 318 | $finalUrl = end($effectiveUri); |
||
| 319 | } |
||
| 320 | } |
||
| 321 | |||
| 322 | // Check for common error pages |
||
| 323 | if ($this->isErrorPage($body)) { |
||
| 324 | Log::warning('Received error page from ' . $this->getName() . ': ' . $url); |
||
| 325 | if ($attempt < $this->maxRetries) { |
||
| 326 | usleep($this->retryDelay * 1000); |
||
| 327 | continue; |
||
| 328 | } |
||
| 329 | return false; |
||
| 330 | } |
||
| 331 | |||
| 332 | // Check for age verification requirement |
||
| 333 | if ($this->requiresAgeVerification($body)) { |
||
| 334 | // If we haven't tried age verification yet, refresh cookies and retry |
||
| 335 | if (!$ageVerificationAttempted) { |
||
| 336 | $ageVerificationAttempted = true; |
||
| 337 | |||
| 338 | // Refresh cookies using the manager |
||
| 339 | $this->getAgeVerificationManager()->refreshCookies($this->getBaseUrl()); |
||
| 340 | |||
| 341 | // Reset HTTP client to pick up new cookies |
||
| 342 | $this->httpClient = null; |
||
| 343 | $this->cookieJar = null; |
||
| 344 | |||
| 345 | Log::info('Refreshed age verification cookies for ' . $this->getName() . ', retrying...'); |
||
| 346 | continue; |
||
| 347 | } |
||
| 348 | |||
| 349 | $body = $this->handleAgeVerification($url, $body); |
||
| 350 | if ($body === false) { |
||
| 351 | return false; |
||
| 352 | } |
||
| 353 | } |
||
| 354 | |||
| 355 | return $body; |
||
| 356 | |||
| 357 | } catch (ConnectException $e) { |
||
| 358 | $lastException = $e; |
||
| 359 | Log::warning('Connection failed for ' . $this->getName() . ' (attempt ' . $attempt . '): ' . $e->getMessage()); |
||
| 360 | |||
| 361 | if ($attempt < $this->maxRetries) { |
||
| 362 | usleep($this->retryDelay * 1000 * $attempt); // Exponential backoff |
||
| 363 | } |
||
| 364 | } catch (RequestException $e) { |
||
| 365 | $lastException = $e; |
||
| 366 | $statusCode = $e->hasResponse() ? $e->getResponse()->getStatusCode() : 0; |
||
| 367 | |||
| 368 | // Don't retry on 4xx client errors (except 429 rate limit) |
||
| 369 | if ($statusCode >= 400 && $statusCode < 500 && $statusCode !== 429) { |
||
| 370 | Log::error('HTTP ' . $statusCode . ' for ' . $this->getName() . ': ' . $url); |
||
| 371 | return false; |
||
| 372 | } |
||
| 373 | |||
| 374 | Log::warning('Request failed for ' . $this->getName() . ' (attempt ' . $attempt . '): ' . $e->getMessage()); |
||
| 375 | |||
| 376 | if ($attempt < $this->maxRetries) { |
||
| 377 | // Longer delay for rate limit errors |
||
| 378 | $delay = $statusCode === 429 ? $this->retryDelay * 5 : $this->retryDelay * $attempt; |
||
| 379 | usleep($delay * 1000); |
||
| 380 | } |
||
| 381 | } catch (\Exception $e) { |
||
| 382 | $lastException = $e; |
||
| 383 | Log::error('Unexpected error for ' . $this->getName() . ': ' . $e->getMessage()); |
||
| 384 | |||
| 385 | if ($attempt < $this->maxRetries) { |
||
| 386 | usleep($this->retryDelay * 1000); |
||
| 387 | } |
||
| 388 | } |
||
| 389 | } |
||
| 390 | |||
| 391 | if ($lastException) { |
||
| 392 | Log::error('All retry attempts failed for ' . $this->getName() . ': ' . $lastException->getMessage()); |
||
| 393 | } |
||
| 394 | |||
| 395 | return false; |
||
| 396 | } |
||
| 397 | |||
| 398 | /** |
||
| 399 | * Get default HTTP headers. |
||
| 400 | */ |
||
| 401 | protected function getDefaultHeaders(): array |
||
| 402 | { |
||
| 403 | return [ |
||
| 404 | 'User-Agent' => $this->getRandomUserAgent(), |
||
| 405 | 'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8', |
||
| 406 | 'Accept-Language' => 'en-US,en;q=0.9', |
||
| 407 | 'Accept-Encoding' => 'gzip, deflate, br', |
||
| 408 | 'Cache-Control' => 'no-cache', |
||
| 409 | 'Pragma' => 'no-cache', |
||
| 410 | 'Sec-Fetch-Dest' => 'document', |
||
| 411 | 'Sec-Fetch-Mode' => 'navigate', |
||
| 412 | 'Sec-Fetch-Site' => 'none', |
||
| 413 | 'Sec-Fetch-User' => '?1', |
||
| 414 | 'Upgrade-Insecure-Requests' => '1', |
||
| 415 | ]; |
||
| 416 | } |
||
| 417 | |||
| 418 | /** |
||
| 419 | * Get a random user agent string. |
||
| 420 | */ |
||
| 421 | protected function getRandomUserAgent(): string |
||
| 422 | { |
||
| 423 | $userAgents = [ |
||
| 424 | 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', |
||
| 425 | 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36', |
||
| 426 | 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', |
||
| 427 | 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0', |
||
| 428 | 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.2 Safari/605.1.15', |
||
| 429 | 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0', |
||
| 430 | ]; |
||
| 431 | |||
| 432 | return $userAgents[array_rand($userAgents)]; |
||
| 433 | } |
||
| 434 | |||
| 435 | /** |
||
| 436 | * Check if the response is an error page. |
||
| 437 | */ |
||
| 438 | protected function isErrorPage(string $html): bool |
||
| 439 | { |
||
| 440 | $errorPatterns = [ |
||
| 441 | 'Access Denied', |
||
| 442 | 'Service Unavailable', |
||
| 443 | '503 Service', |
||
| 444 | '502 Bad Gateway', |
||
| 445 | 'temporarily unavailable', |
||
| 446 | 'maintenance mode', |
||
| 447 | 'rate limit exceeded', |
||
| 448 | ]; |
||
| 449 | |||
| 450 | foreach ($errorPatterns as $pattern) { |
||
| 451 | if (stripos($html, $pattern) !== false) { |
||
| 452 | return true; |
||
| 453 | } |
||
| 454 | } |
||
| 455 | |||
| 456 | return false; |
||
| 457 | } |
||
| 458 | |||
| 459 | /** |
||
| 460 | * Check if the page requires age verification. |
||
| 461 | */ |
||
| 462 | protected function requiresAgeVerification(string $html): bool |
||
| 463 | { |
||
| 464 | // First check if this looks like a proper content page |
||
| 465 | // Content pages have actual movie info, cast, etc. |
||
| 466 | $contentIndicators = [ |
||
| 467 | '<title>.*?DVD.*?</title>', |
||
| 468 | 'product-info', |
||
| 469 | 'movie-details', |
||
| 470 | 'cast-list', |
||
| 471 | 'genre-list', |
||
| 472 | '"@type":\s*"Movie"', |
||
| 473 | '"@type":\s*"Product"', |
||
| 474 | ]; |
||
| 475 | |||
| 476 | foreach ($contentIndicators as $pattern) { |
||
| 477 | if (preg_match('/' . $pattern . '/is', $html)) { |
||
| 478 | return false; // This is a content page, not an age verification page |
||
| 479 | } |
||
| 480 | } |
||
| 481 | |||
| 482 | // Check for short page that might just be a redirect/age gate |
||
| 483 | if (strlen($html) < 500) { |
||
| 484 | return true; // Very short response likely means we got redirected |
||
| 485 | } |
||
| 486 | |||
| 487 | // Now check for explicit age verification indicators |
||
| 488 | $agePatterns = [ |
||
| 489 | 'age verification', |
||
| 490 | 'are you 18', |
||
| 491 | 'are you over 18', |
||
| 492 | 'confirm your age', |
||
| 493 | 'enter your age', |
||
| 494 | 'must be 18', |
||
| 495 | 'age-gate', |
||
| 496 | 'ageGate', |
||
| 497 | 'AgeConfirmation', // PopPorn specific |
||
| 498 | 'ageConfirmationButton', // ADE specific |
||
| 499 | 'age-confirmation', // Generic |
||
| 500 | 'verify your age', |
||
| 501 | 'adult content warning', |
||
| 502 | 'I am 18 or older', |
||
| 503 | 'I am over 18', |
||
| 504 | 'this site contains adult', |
||
| 505 | ]; |
||
| 506 | |||
| 507 | // Count how many patterns match - if multiple match on a short page, it's likely age verification |
||
| 508 | $matchCount = 0; |
||
| 509 | foreach ($agePatterns as $pattern) { |
||
| 510 | if (stripos($html, $pattern) !== false) { |
||
| 511 | $matchCount++; |
||
| 512 | // If the page is relatively short and has an age pattern, it's probably an age gate |
||
| 513 | if (strlen($html) < 10000) { |
||
| 514 | return true; |
||
| 515 | } |
||
| 516 | } |
||
| 517 | } |
||
| 518 | |||
| 519 | // If multiple patterns match, it's likely an age verification page |
||
| 520 | return $matchCount >= 2; |
||
| 521 | } |
||
| 522 | |||
| 523 | /** |
||
| 524 | * Handle age verification requirement. |
||
| 525 | */ |
||
| 526 | protected function handleAgeVerification(string $url, string $html): string|false |
||
| 527 | { |
||
| 528 | // First, try to use site-specific cookies from the AgeVerificationManager |
||
| 529 | $manager = $this->getAgeVerificationManager(); |
||
| 530 | $domain = parse_url($this->getBaseUrl(), PHP_URL_HOST); |
||
| 531 | $domain = preg_replace('/^www\./', '', $domain); |
||
| 532 | |||
| 533 | // Re-initialize cookies from the manager and retry |
||
| 534 | if ($this->cookieJar) { |
||
| 535 | // The manager already handles setting cookies, but let's ensure they're fresh |
||
| 536 | Log::info('Attempting to handle age verification for ' . $this->getName() . ' with domain: ' . $domain); |
||
| 537 | } |
||
| 538 | |||
| 539 | // Try to find and submit age verification form |
||
| 540 | $this->getHtmlParser()->loadHtml($html); |
||
| 541 | |||
| 542 | // Look for common age verification form patterns |
||
| 543 | $forms = $this->getHtmlParser()->find('form'); |
||
| 544 | foreach ($forms as $form) { |
||
| 545 | $action = $form->action ?? ''; |
||
| 546 | $method = strtoupper($form->method ?? 'GET'); |
||
| 547 | |||
| 548 | // Check if this looks like an age verification form |
||
| 549 | $formHtml = $form->innerHtml ?? ''; |
||
| 550 | if (stripos($formHtml, 'age') !== false || stripos($formHtml, '18') !== false || |
||
| 551 | stripos($formHtml, 'adult') !== false || stripos($formHtml, 'enter') !== false || |
||
| 552 | stripos($formHtml, 'confirm') !== false) { |
||
| 553 | // Try to submit the form with age confirmation |
||
| 554 | $postData = $this->extractAgeVerificationFormData($form); |
||
| 555 | |||
| 556 | if (!empty($postData)) { |
||
| 557 | $submitUrl = $action; |
||
| 558 | if (!str_starts_with($submitUrl, 'http')) { |
||
| 559 | $submitUrl = $this->getBaseUrl() . '/' . ltrim($submitUrl, '/'); |
||
| 560 | } |
||
| 561 | |||
| 562 | // Submit the age verification |
||
| 563 | try { |
||
| 564 | $response = $this->getHttpClient()->request($method, $submitUrl, [ |
||
| 565 | 'form_params' => $postData, |
||
| 566 | 'headers' => $this->getDefaultHeaders(), |
||
| 567 | ]); |
||
| 568 | |||
| 569 | $body = $response->getBody()->getContents(); |
||
| 570 | |||
| 571 | // Check if we still get age verification after submit |
||
| 572 | if (!$this->requiresAgeVerification($body)) { |
||
| 573 | return $body; |
||
| 574 | } |
||
| 575 | } catch (\Exception $e) { |
||
| 576 | Log::warning('Age verification submission failed for ' . $this->getName() . ': ' . $e->getMessage()); |
||
| 577 | } |
||
| 578 | } |
||
| 579 | } |
||
| 580 | } |
||
| 581 | |||
| 582 | // Look for JavaScript-based age verification (click to enter) |
||
| 583 | if (preg_match('/onclick\s*=\s*["\'].*?(enter|agree|confirm|over18|adult).*?["\']/i', $html) || |
||
| 584 | preg_match('/<a[^>]*href\s*=\s*["\']([^"\']*)["\'][^>]*>(Enter|I am over 18|Agree|Enter Site|I Agree)/i', $html, $matches)) { |
||
| 585 | // Try to follow the link or simulate the click |
||
| 586 | if (!empty($matches[1])) { |
||
| 587 | $enterUrl = $matches[1]; |
||
| 588 | if (!str_starts_with($enterUrl, 'http')) { |
||
| 589 | $enterUrl = $this->getBaseUrl() . '/' . ltrim($enterUrl, '/'); |
||
| 590 | } |
||
| 591 | |||
| 592 | try { |
||
| 593 | $response = $this->getHttpClient()->get($enterUrl, [ |
||
| 594 | 'headers' => $this->getDefaultHeaders(), |
||
| 595 | ]); |
||
| 596 | $body = $response->getBody()->getContents(); |
||
| 597 | |||
| 598 | if (!$this->requiresAgeVerification($body)) { |
||
| 599 | return $body; |
||
| 600 | } |
||
| 601 | } catch (\Exception $e) { |
||
| 602 | Log::warning('Age verification link follow failed for ' . $this->getName() . ': ' . $e->getMessage()); |
||
| 603 | } |
||
| 604 | } |
||
| 605 | } |
||
| 606 | |||
| 607 | // If all else fails, try to just refetch the original URL |
||
| 608 | // (sometimes the cookies from previous attempts work) |
||
| 609 | try { |
||
| 610 | $response = $this->getHttpClient()->get($url, [ |
||
| 611 | 'headers' => $this->getDefaultHeaders(), |
||
| 612 | ]); |
||
| 613 | $body = $response->getBody()->getContents(); |
||
| 614 | |||
| 615 | if (!$this->requiresAgeVerification($body)) { |
||
| 616 | return $body; |
||
| 617 | } |
||
| 618 | } catch (\Exception $e) { |
||
| 619 | Log::warning('Age verification retry failed for ' . $this->getName() . ': ' . $e->getMessage()); |
||
| 620 | } |
||
| 621 | |||
| 622 | // If we couldn't handle age verification, log and return false |
||
| 623 | Log::warning('Could not handle age verification for ' . $this->getName() . ': ' . $url); |
||
| 624 | return false; |
||
| 625 | } |
||
| 626 | |||
| 627 | /** |
||
| 628 | * Extract form data for age verification submission. |
||
| 629 | */ |
||
| 630 | protected function extractAgeVerificationFormData($form): array |
||
| 631 | { |
||
| 632 | $data = []; |
||
| 633 | |||
| 634 | // Get all input fields |
||
| 635 | foreach ($form->find('input') as $input) { |
||
| 636 | $name = $input->name ?? ''; |
||
| 637 | $type = strtolower($input->type ?? 'text'); |
||
| 638 | $value = $input->value ?? ''; |
||
| 639 | |||
| 640 | if (empty($name)) { |
||
| 641 | continue; |
||
| 642 | } |
||
| 643 | |||
| 644 | // Handle different input types |
||
| 645 | switch ($type) { |
||
| 646 | case 'hidden': |
||
| 647 | $data[$name] = $value; |
||
| 648 | break; |
||
| 649 | case 'checkbox': |
||
| 650 | // Usually age verification checkboxes need to be checked |
||
| 651 | if (stripos($name, 'age') !== false || stripos($name, 'agree') !== false || stripos($name, 'confirm') !== false) { |
||
| 652 | $data[$name] = $value ?: '1'; |
||
| 653 | } |
||
| 654 | break; |
||
| 655 | case 'submit': |
||
| 656 | // Include submit button value if it has a name |
||
| 657 | if (!empty($value)) { |
||
| 658 | $data[$name] = $value; |
||
| 659 | } |
||
| 660 | break; |
||
| 661 | default: |
||
| 662 | // For text inputs that might be age/birthdate |
||
| 663 | if (stripos($name, 'age') !== false || stripos($name, 'year') !== false) { |
||
| 664 | $data[$name] = '1990'; // Default to a valid birth year |
||
| 665 | } |
||
| 666 | } |
||
| 667 | } |
||
| 668 | |||
| 669 | // Handle select elements (for birthdate selection) |
||
| 670 | foreach ($form->find('select') as $select) { |
||
| 671 | $name = $select->name ?? ''; |
||
| 672 | if (empty($name)) { |
||
| 673 | continue; |
||
| 674 | } |
||
| 675 | |||
| 676 | if (stripos($name, 'year') !== false) { |
||
| 677 | $data[$name] = '1990'; |
||
| 678 | } elseif (stripos($name, 'month') !== false) { |
||
| 679 | $data[$name] = '01'; |
||
| 680 | } elseif (stripos($name, 'day') !== false) { |
||
| 681 | $data[$name] = '01'; |
||
| 682 | } |
||
| 683 | } |
||
| 684 | |||
| 685 | return $data; |
||
| 686 | } |
||
| 687 | |||
| 688 | /** |
||
| 689 | * Get the age verification manager instance. |
||
| 690 | */ |
||
| 691 | protected function getAgeVerificationManager(): AgeVerificationManager |
||
| 692 | { |
||
| 693 | if ($this->ageVerificationManager === null) { |
||
| 694 | $this->ageVerificationManager = new AgeVerificationManager(); |
||
| 695 | } |
||
| 696 | return $this->ageVerificationManager; |
||
| 697 | } |
||
| 698 | |||
| 699 | /** |
||
| 700 | * Get or create HTTP client with retry middleware. |
||
| 701 | */ |
||
| 702 | protected function getHttpClient(): Client |
||
| 724 | } |
||
| 725 | |||
| 726 | /** |
||
| 727 | * Calculate similarity between two strings using multiple algorithms. |
||
| 728 | */ |
||
| 729 | protected function calculateSimilarity(string $searchTerm, string $resultTitle): float |
||
| 730 | { |
||
| 731 | // Clean up both strings for comparison |
||
| 732 | $cleanSearch = $this->cleanTitleForComparison($searchTerm); |
||
| 733 | $cleanResult = $this->cleanTitleForComparison($resultTitle); |
||
| 734 | |||
| 735 | // Calculate similarity using multiple methods |
||
| 736 | similar_text($cleanSearch, $cleanResult, $similarTextPercent); |
||
| 737 | |||
| 738 | // Also calculate Levenshtein distance based similarity |
||
| 739 | $maxLen = max(strlen($cleanSearch), strlen($cleanResult)); |
||
| 740 | if ($maxLen > 0) { |
||
| 741 | $levenshtein = levenshtein($cleanSearch, $cleanResult); |
||
| 742 | $levenshteinPercent = (1 - ($levenshtein / $maxLen)) * 100; |
||
| 743 | } else { |
||
| 744 | $levenshteinPercent = 0; |
||
| 745 | } |
||
| 746 | |||
| 747 | // Use the higher of the two similarity scores |
||
| 748 | return max($similarTextPercent, $levenshteinPercent); |
||
| 749 | } |
||
| 750 | |||
| 751 | /** |
||
| 752 | * Clean a title for comparison purposes. |
||
| 753 | */ |
||
| 754 | protected function cleanTitleForComparison(string $title): string |
||
| 755 | { |
||
| 756 | $title = strtolower($title); |
||
| 757 | $title = str_replace('/XXX/', '', $title); |
||
| 758 | |||
| 759 | // Remove common adult movie prefixes/suffixes |
||
| 760 | $removePatterns = [ |
||
| 761 | '/\b(xxx|adult|porn|erotic|hd|4k|1080p|720p|dvdrip|webrip|bluray)\b/i', |
||
| 762 | '/\(.*?\)/', |
||
| 763 | '/\[.*?\]/', |
||
| 764 | '/[._-]+/', |
||
| 765 | '/\s+/', |
||
| 766 | ]; |
||
| 767 | |||
| 768 | foreach ($removePatterns as $pattern) { |
||
| 769 | $title = preg_replace($pattern, ' ', $title); |
||
| 770 | } |
||
| 771 | |||
| 772 | return trim($title); |
||
| 773 | } |
||
| 774 | |||
| 775 | /** |
||
| 776 | * Extract movie information from the loaded HTML. |
||
| 777 | */ |
||
| 778 | protected function extractCovers(): array |
||
| 779 | { |
||
| 780 | return []; |
||
| 781 | } |
||
| 782 | |||
| 783 | protected function extractSynopsis(): array |
||
| 786 | } |
||
| 787 | |||
| 788 | protected function extractCast(): array |
||
| 789 | { |
||
| 791 | } |
||
| 792 | |||
| 793 | protected function extractGenres(): array |
||
| 794 | { |
||
| 795 | return []; |
||
| 796 | } |
||
| 797 | |||
| 798 | protected function extractProductInfo(bool $extras = false): array |
||
| 801 | } |
||
| 802 | |||
| 803 | protected function extractTrailers(): array |
||
| 804 | { |
||
| 805 | return []; |
||
| 806 | } |
||
| 807 | |||
| 808 | /** |
||
| 809 | * Output match success message. |
||
| 810 | */ |
||
| 811 | protected function outputMatch(string $title): void |
||
| 812 | { |
||
| 813 | if (! $this->echoOutput) { |
||
| 814 | return; |
||
| 815 | } |
||
| 816 | |||
| 817 | $this->getColorCli()->primary('Found match on '.$this->getDisplayName().': '.$title); |
||
| 818 | } |
||
| 819 | |||
| 820 | /** |
||
| 821 | * Output failure message. |
||
| 822 | */ |
||
| 823 | protected function outputNotFound(): void |
||
| 830 | } |
||
| 831 | |||
| 832 | /** |
||
| 833 | * Parse JSON-LD structured data from HTML. |
||
| 834 | */ |
||
| 835 | protected function extractJsonLd(string $html): ?array |
||
| 836 | { |
||
| 837 | if (preg_match_all('/<script[^>]*type=["\']application\/ld\+json["\'][^>]*>(.*?)<\/script>/si', $html, $matches)) { |
||
| 838 | foreach ($matches[1] as $json) { |
||
| 839 | $data = json_decode(trim($json), true); |
||
| 840 | if (json_last_error() === JSON_ERROR_NONE && is_array($data)) { |
||
| 841 | // Handle both single object and array of objects |
||
| 842 | if (isset($data['@type'])) { |
||
| 843 | return $data; |
||
| 844 | } elseif (isset($data[0]['@type'])) { |
||
| 845 | return $data[0]; |
||
| 846 | } |
||
| 847 | } |
||
| 848 | } |
||
| 849 | } |
||
| 850 | |||
| 851 | return null; |
||
| 852 | } |
||
| 853 | |||
| 854 | /** |
||
| 855 | * Extract Open Graph meta data from HTML. |
||
| 856 | */ |
||
| 857 | protected function extractOpenGraph(string $html): array |
||
| 877 | } |
||
| 878 | } |
||
| 879 | |||
| 880 |
Loading history...
The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g.
excluded_paths: ["lib/*"], you can move it to the dependency path list as follows:For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths