|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace App\Console\Commands; |
|
4
|
|
|
|
|
5
|
|
|
use App\Models\AnidbInfo; |
|
6
|
|
|
use App\Models\Category; |
|
7
|
|
|
use App\Models\Release; |
|
8
|
|
|
use Blacklight\PopulateAniList; |
|
9
|
|
|
use Illuminate\Console\Command; |
|
10
|
|
|
use Illuminate\Support\Facades\DB; |
|
11
|
|
|
|
|
12
|
|
|
class RefreshAnimeData extends Command |
|
13
|
|
|
{ |
|
14
|
|
|
/** |
|
15
|
|
|
* Conservative rate limit: 35 requests per minute (to stay well below AniList's 90/min limit). |
|
16
|
|
|
* This allows for multiple API calls per release (search + getById). |
|
17
|
|
|
*/ |
|
18
|
|
|
private const RATE_LIMIT_PER_MINUTE = 35; |
|
19
|
|
|
|
|
20
|
|
|
/** |
|
21
|
|
|
* Track API request timestamps for rate limiting. |
|
22
|
|
|
* |
|
23
|
|
|
* @var array<int> |
|
24
|
|
|
*/ |
|
25
|
|
|
private array $requestTimestamps = []; |
|
26
|
|
|
|
|
27
|
|
|
/** |
|
28
|
|
|
* The name and signature of the console command. |
|
29
|
|
|
* |
|
30
|
|
|
* @var string |
|
31
|
|
|
*/ |
|
32
|
|
|
protected $signature = 'anime:refresh |
|
33
|
|
|
{--limit=0 : Maximum number of releases to process (0 = all)} |
|
34
|
|
|
{--chunk=100 : Process releases in chunks of this size} |
|
35
|
|
|
{--missing-only : Only refresh releases missing AniList data (no anilist_id)} |
|
36
|
|
|
{--force : Force refresh even if data exists}'; |
|
37
|
|
|
|
|
38
|
|
|
/** |
|
39
|
|
|
* The console command description. |
|
40
|
|
|
* |
|
41
|
|
|
* @var string |
|
42
|
|
|
*/ |
|
43
|
|
|
protected $description = 'Fetch and refresh AniList data for existing anime releases in TV->Anime category by matching release searchname'; |
|
44
|
|
|
|
|
45
|
|
|
/** |
|
46
|
|
|
* Execute the console command. |
|
47
|
|
|
*/ |
|
48
|
|
|
public function handle(): int |
|
49
|
|
|
{ |
|
50
|
|
|
$limit = (int) $this->option('limit'); |
|
51
|
|
|
$chunkSize = (int) $this->option('chunk'); |
|
52
|
|
|
$missingOnly = $this->option('missing-only'); |
|
53
|
|
|
$force = $this->option('force'); |
|
54
|
|
|
|
|
55
|
|
|
$this->info('Starting AniList data refresh for anime releases...'); |
|
56
|
|
|
$this->info('Matching releases by searchname to AniList API...'); |
|
57
|
|
|
$this->newLine(); |
|
58
|
|
|
|
|
59
|
|
|
// Build query for releases in TV_ANIME category |
|
60
|
|
|
$query = Release::query() |
|
61
|
|
|
->select(['releases.id', 'releases.anidbid', 'releases.searchname']) |
|
62
|
|
|
->where('categories_id', Category::TV_ANIME); |
|
63
|
|
|
|
|
64
|
|
|
// If missing-only, only get releases without anilist_id |
|
65
|
|
|
if ($missingOnly) { |
|
66
|
|
|
$query->leftJoin('anidb_info as ai', 'ai.anidbid', '=', 'releases.anidbid') |
|
67
|
|
|
->whereNull('ai.anilist_id'); |
|
68
|
|
|
} |
|
69
|
|
|
|
|
70
|
|
|
// Get releases (not distinct anidbids, since we're matching by searchname) |
|
71
|
|
|
$releases = $query->orderBy('releases.id') |
|
|
|
|
|
|
72
|
|
|
->get(); |
|
73
|
|
|
|
|
74
|
|
|
$totalCount = $releases->count(); |
|
75
|
|
|
|
|
76
|
|
|
if ($totalCount === 0) { |
|
77
|
|
|
$this->warn('No anime releases found to process.'); |
|
78
|
|
|
return self::SUCCESS; |
|
79
|
|
|
} |
|
80
|
|
|
|
|
81
|
|
|
$this->info("Found {$totalCount} anime releases to process."); |
|
82
|
|
|
|
|
83
|
|
|
if ($limit > 0) { |
|
84
|
|
|
$releases = $releases->take($limit); |
|
85
|
|
|
$totalCount = $releases->count(); |
|
86
|
|
|
$this->info("Processing {$totalCount} releases (limited)."); |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
|
|
$this->newLine(); |
|
90
|
|
|
|
|
91
|
|
|
$populateAniList = new PopulateAniList; |
|
92
|
|
|
$processed = 0; |
|
93
|
|
|
$successful = 0; |
|
94
|
|
|
$failed = 0; |
|
95
|
|
|
$skipped = 0; |
|
96
|
|
|
$notFound = 0; |
|
97
|
|
|
|
|
98
|
|
|
// Process in chunks |
|
99
|
|
|
$chunks = $releases->chunk($chunkSize); |
|
100
|
|
|
$progressBar = $this->output->createProgressBar($totalCount); |
|
101
|
|
|
$progressBar->setFormat(' %current%/%max% [%bar%] %percent:3s%% %elapsed:6s%/%estimated:-6s% %memory:6s% -- %message%'); |
|
102
|
|
|
$progressBar->setMessage('Starting...'); |
|
103
|
|
|
$progressBar->start(); |
|
104
|
|
|
|
|
105
|
|
|
foreach ($chunks as $chunk) { |
|
106
|
|
|
foreach ($chunk as $release) { |
|
107
|
|
|
$searchname = $release->searchname ?? ''; |
|
108
|
|
|
$progressBar->setMessage("Processing: " . substr($searchname, 0, 50) . "..."); |
|
109
|
|
|
|
|
110
|
|
|
try { |
|
111
|
|
|
// Extract clean title from searchname |
|
112
|
|
|
$titleData = $this->extractTitleFromSearchname($searchname); |
|
113
|
|
|
|
|
114
|
|
|
if (empty($titleData) || empty($titleData['title'])) { |
|
115
|
|
|
$notFound++; |
|
116
|
|
|
$processed++; |
|
117
|
|
|
$progressBar->advance(); |
|
118
|
|
|
continue; |
|
119
|
|
|
} |
|
120
|
|
|
|
|
121
|
|
|
$cleanTitle = $titleData['title']; |
|
122
|
|
|
|
|
123
|
|
|
// Check if we should skip (if not forcing and data exists) |
|
124
|
|
|
if (! $force && ! $missingOnly) { |
|
125
|
|
|
// Check if release already has complete AniList data |
|
126
|
|
|
if ($release->anidbid > 0) { |
|
127
|
|
|
$anidbInfo = DB::table('anidb_info') |
|
128
|
|
|
->where('anidbid', $release->anidbid) |
|
129
|
|
|
->whereNotNull('anilist_id') |
|
130
|
|
|
->whereNotNull('country') |
|
131
|
|
|
->whereNotNull('media_type') |
|
132
|
|
|
->first(); |
|
133
|
|
|
|
|
134
|
|
|
if ($anidbInfo) { |
|
135
|
|
|
$skipped++; |
|
136
|
|
|
$processed++; |
|
137
|
|
|
$progressBar->advance(); |
|
138
|
|
|
continue; |
|
139
|
|
|
} |
|
140
|
|
|
} |
|
141
|
|
|
} |
|
142
|
|
|
|
|
143
|
|
|
// Search AniList for this title (with rate limiting) |
|
144
|
|
|
$this->enforceRateLimit(); |
|
145
|
|
|
$searchResults = $populateAniList->searchAnime($cleanTitle, 1); |
|
146
|
|
|
|
|
147
|
|
|
if (! $searchResults || empty($searchResults)) { |
|
148
|
|
|
// Try with spaces replaced for broader matching |
|
149
|
|
|
$altTitle = preg_replace('/\s+/', ' ', $cleanTitle); |
|
150
|
|
|
if ($altTitle !== $cleanTitle) { |
|
151
|
|
|
$this->enforceRateLimit(); |
|
152
|
|
|
$searchResults = $populateAniList->searchAnime($altTitle, 1); |
|
153
|
|
|
} |
|
154
|
|
|
} |
|
155
|
|
|
|
|
156
|
|
|
if (! $searchResults || empty($searchResults)) { |
|
157
|
|
|
$notFound++; |
|
158
|
|
|
$processed++; |
|
159
|
|
|
$progressBar->advance(); |
|
160
|
|
|
continue; |
|
161
|
|
|
} |
|
162
|
|
|
|
|
163
|
|
|
$anilistData = $searchResults[0]; |
|
164
|
|
|
$anilistId = $anilistData['id'] ?? null; |
|
165
|
|
|
|
|
166
|
|
|
if (! $anilistId) { |
|
167
|
|
|
$notFound++; |
|
168
|
|
|
$processed++; |
|
169
|
|
|
$progressBar->advance(); |
|
170
|
|
|
continue; |
|
171
|
|
|
} |
|
172
|
|
|
|
|
173
|
|
|
// Fetch full data from AniList and insert/update (with rate limiting) |
|
174
|
|
|
// This will create/update anidb_info entry using anilist_id as anidbid if needed |
|
175
|
|
|
$this->enforceRateLimit(); |
|
176
|
|
|
$populateAniList->populateTable('info', $anilistId); |
|
177
|
|
|
|
|
178
|
|
|
// Get the anidbid that was created/updated (it uses anilist_id as anidbid) |
|
179
|
|
|
$anidbid = AnidbInfo::query() |
|
180
|
|
|
->where('anilist_id', $anilistId) |
|
181
|
|
|
->value('anidbid'); |
|
182
|
|
|
|
|
183
|
|
|
if (! $anidbid) { |
|
184
|
|
|
// Fallback: use anilist_id as anidbid |
|
185
|
|
|
$anidbid = (int) $anilistId; |
|
186
|
|
|
} |
|
187
|
|
|
|
|
188
|
|
|
// Update release with the anidbid |
|
189
|
|
|
Release::query() |
|
190
|
|
|
->where('id', $release->id) |
|
191
|
|
|
->update(['anidbid' => $anidbid]); |
|
192
|
|
|
|
|
193
|
|
|
$successful++; |
|
194
|
|
|
} catch (\Exception $e) { |
|
195
|
|
|
// Check if this is a 429 rate limit error |
|
196
|
|
|
if (str_contains($e->getMessage(), '429') || str_contains($e->getMessage(), 'rate limit exceeded')) { |
|
197
|
|
|
$this->newLine(); |
|
198
|
|
|
$this->error('AniList API rate limit exceeded (429). Stopping processing for 15 minutes.'); |
|
199
|
|
|
$this->warn('Please wait 15 minutes before running this command again.'); |
|
200
|
|
|
$progressBar->finish(); |
|
201
|
|
|
$this->newLine(); |
|
202
|
|
|
|
|
203
|
|
|
// Show summary of what was processed before the error |
|
204
|
|
|
$this->info('Summary (before rate limit error):'); |
|
205
|
|
|
$this->table( |
|
206
|
|
|
['Status', 'Count'], |
|
207
|
|
|
[ |
|
208
|
|
|
['Total Processed', $processed], |
|
209
|
|
|
['Successful', $successful], |
|
210
|
|
|
['Failed', $failed], |
|
211
|
|
|
['Not Found', $notFound], |
|
212
|
|
|
['Skipped', $skipped], |
|
213
|
|
|
] |
|
214
|
|
|
); |
|
215
|
|
|
|
|
216
|
|
|
return self::FAILURE; |
|
217
|
|
|
} |
|
218
|
|
|
|
|
219
|
|
|
$failed++; |
|
220
|
|
|
if ($this->getOutput()->isVerbose()) { |
|
221
|
|
|
$this->newLine(); |
|
222
|
|
|
$this->error("Error processing release ID {$release->id}: " . $e->getMessage()); |
|
223
|
|
|
} |
|
224
|
|
|
} |
|
225
|
|
|
|
|
226
|
|
|
$processed++; |
|
227
|
|
|
$progressBar->advance(); |
|
228
|
|
|
} |
|
229
|
|
|
} |
|
230
|
|
|
|
|
231
|
|
|
$progressBar->setMessage('Complete!'); |
|
232
|
|
|
$progressBar->finish(); |
|
233
|
|
|
$this->newLine(2); |
|
234
|
|
|
|
|
235
|
|
|
// Summary |
|
236
|
|
|
$this->info('Summary:'); |
|
237
|
|
|
$this->table( |
|
238
|
|
|
['Status', 'Count'], |
|
239
|
|
|
[ |
|
240
|
|
|
['Total Processed', $processed], |
|
241
|
|
|
['Successful', $successful], |
|
242
|
|
|
['Failed', $failed], |
|
243
|
|
|
['Not Found', $notFound], |
|
244
|
|
|
['Skipped', $skipped], |
|
245
|
|
|
] |
|
246
|
|
|
); |
|
247
|
|
|
|
|
248
|
|
|
return self::SUCCESS; |
|
249
|
|
|
} |
|
250
|
|
|
|
|
251
|
|
|
/** |
|
252
|
|
|
* Extract clean anime title from release searchname. |
|
253
|
|
|
* Similar to extractTitleEpisode in AniDB.php but simplified. |
|
254
|
|
|
* |
|
255
|
|
|
* @return array{title: string}|array{} |
|
256
|
|
|
*/ |
|
257
|
|
|
private function extractTitleFromSearchname(string $searchname): array |
|
258
|
|
|
{ |
|
259
|
|
|
if (empty($searchname)) { |
|
260
|
|
|
return []; |
|
261
|
|
|
} |
|
262
|
|
|
|
|
263
|
|
|
// Normalize common separators |
|
264
|
|
|
$s = str_replace(['_', '.'], ' ', $searchname); |
|
265
|
|
|
$s = preg_replace('/\s+/', ' ', $s); |
|
266
|
|
|
$s = trim($s); |
|
267
|
|
|
|
|
268
|
|
|
// Strip leading group tags like [Group] |
|
269
|
|
|
$s = preg_replace('/^(?:\[[^\]]+\]\s*)+/', '', $s); |
|
270
|
|
|
$s = trim($s); |
|
271
|
|
|
|
|
272
|
|
|
// Remove language codes and tags |
|
273
|
|
|
$s = preg_replace('/\[(?:ENG|JAP|JPN|SUB|DUB|MULTI|RAW|HARDSUB|SOFTSUB|HARDDUB|SOFTDUB|ITA|SPA|FRE|GER|RUS|CHI|KOR)\]/i', ' ', $s); |
|
274
|
|
|
$s = preg_replace('/\((?:ENG|JAP|JPN|SUB|DUB|MULTI|RAW|HARDSUB|SOFTSUB|HARDDUB|SOFTDUB|ITA|SPA|FRE|GER|RUS|CHI|KOR)\)/i', ' ', $s); |
|
275
|
|
|
|
|
276
|
|
|
// Extract title by removing episode patterns |
|
277
|
|
|
$title = ''; |
|
278
|
|
|
|
|
279
|
|
|
// Try to extract title by removing episode patterns |
|
280
|
|
|
// 1) Look for " - NNN" and extract title before it |
|
281
|
|
|
if (preg_match('/\s-\s*(\d{1,3})\b/', $s, $m, PREG_OFFSET_CAPTURE)) { |
|
282
|
|
|
$title = substr($s, 0, (int) $m[0][1]); |
|
283
|
|
|
} |
|
284
|
|
|
// 2) If not found, look for " E0*NNN" or " Ep NNN" |
|
285
|
|
|
elseif (preg_match('/\sE(?:p(?:isode)?)?\s*0*(\d{1,3})\b/i', $s, $m, PREG_OFFSET_CAPTURE)) { |
|
286
|
|
|
$title = substr($s, 0, (int) $m[0][1]); |
|
287
|
|
|
} |
|
288
|
|
|
// 3) Look for " S01E01" or " S1E1" pattern |
|
289
|
|
|
elseif (preg_match('/\sS\d+E\d+/i', $s, $m, PREG_OFFSET_CAPTURE)) { |
|
290
|
|
|
$title = substr($s, 0, (int) $m[0][1]); |
|
291
|
|
|
} |
|
292
|
|
|
// 4) Keywords Movie/OVA/Complete Series |
|
293
|
|
|
elseif (preg_match('/\b(Movie|OVA|Complete Series|Complete|Full Series)\b/i', $s, $m, PREG_OFFSET_CAPTURE)) { |
|
294
|
|
|
$title = substr($s, 0, (int) $m[0][1]); |
|
295
|
|
|
} |
|
296
|
|
|
// 5) BD/resolution releases: pick title before next bracket token |
|
297
|
|
|
elseif (preg_match('/\[(?:BD|BDRip|BluRay|Blu-Ray|\d{3,4}[ipx]|HEVC|x264|x265|H264|H265)\]/i', $s, $m, PREG_OFFSET_CAPTURE)) { |
|
298
|
|
|
$title = substr($s, 0, (int) $m[0][1]); |
|
299
|
|
|
} else { |
|
300
|
|
|
// No episode pattern found, use the whole string as title |
|
301
|
|
|
$title = $s; |
|
302
|
|
|
} |
|
303
|
|
|
|
|
304
|
|
|
$title = $this->cleanTitle($title); |
|
305
|
|
|
|
|
306
|
|
|
if ($title === '') { |
|
307
|
|
|
return []; |
|
308
|
|
|
} |
|
309
|
|
|
|
|
310
|
|
|
return ['title' => $title]; |
|
311
|
|
|
} |
|
312
|
|
|
|
|
313
|
|
|
/** |
|
314
|
|
|
* Strip stray separators, language codes, episode numbers, and other release tags from title. |
|
315
|
|
|
*/ |
|
316
|
|
|
private function cleanTitle(string $title): string |
|
317
|
|
|
{ |
|
318
|
|
|
// Remove all bracketed tags (language, quality, etc.) |
|
319
|
|
|
$title = preg_replace('/\[[^\]]+\]/', ' ', $title); |
|
320
|
|
|
|
|
321
|
|
|
// Remove all parenthesized tags |
|
322
|
|
|
$title = preg_replace('/\([^)]+\)/', ' ', $title); |
|
323
|
|
|
|
|
324
|
|
|
// Remove language codes (standalone or with separators) |
|
325
|
|
|
$title = preg_replace('/\b(ENG|JAP|JPN|SUB|DUB|MULTI|RAW|HARDSUB|SOFTSUB|HARDDUB|SOFTDUB|ITA|SPA|FRE|GER|RUS|CHI|KOR)\b/i', ' ', $title); |
|
326
|
|
|
|
|
327
|
|
|
// Remove episode patterns |
|
328
|
|
|
$title = preg_replace('/\s*-\s*\d{1,4}\s*$/i', '', $title); |
|
329
|
|
|
$title = preg_replace('/\s*-\s*$/i', '', $title); |
|
330
|
|
|
$title = preg_replace('/\s+E(?:p(?:isode)?)?\s*0*\d{1,4}\s*$/i', '', $title); |
|
331
|
|
|
$title = preg_replace('/\s+S\d+E\d+\s*$/i', '', $title); |
|
332
|
|
|
|
|
333
|
|
|
// Remove quality/resolution tags |
|
334
|
|
|
$title = preg_replace('/\b(480p|720p|1080p|2160p|4K|BD|BDRip|BluRay|Blu-Ray|HEVC|x264|x265|H264|H265|WEB|WEBRip|DVDRip|TVRip)\b/i', ' ', $title); |
|
335
|
|
|
|
|
336
|
|
|
// Remove common release tags |
|
337
|
|
|
$title = preg_replace('/\b(PROPER|REPACK|RIP|ISO|CRACK|BETA|ALPHA|FINAL|COMPLETE|FULL)\b/i', ' ', $title); |
|
338
|
|
|
|
|
339
|
|
|
// Remove volume/chapter markers |
|
340
|
|
|
$title = preg_replace('/\s+Vol\.?\s*\d*\s*$/i', '', $title); |
|
341
|
|
|
$title = preg_replace('/\s+Ch\.?\s*\d*\s*$/i', '', $title); |
|
342
|
|
|
|
|
343
|
|
|
// Remove trailing dashes and separators |
|
344
|
|
|
$title = preg_replace('/\s*[-_]\s*$/', '', $title); |
|
345
|
|
|
|
|
346
|
|
|
// Normalize whitespace |
|
347
|
|
|
$title = preg_replace('/\s+/', ' ', $title); |
|
348
|
|
|
|
|
349
|
|
|
return trim($title); |
|
350
|
|
|
} |
|
351
|
|
|
|
|
352
|
|
|
/** |
|
353
|
|
|
* Enforce rate limiting: 35 requests per minute (conservative limit). |
|
354
|
|
|
* Adds delays between API calls to prevent hitting AniList's 90/min limit. |
|
355
|
|
|
*/ |
|
356
|
|
|
private function enforceRateLimit(): void |
|
357
|
|
|
{ |
|
358
|
|
|
$now = time(); |
|
359
|
|
|
|
|
360
|
|
|
// Clean old timestamps (older than 1 minute) |
|
361
|
|
|
$this->requestTimestamps = array_filter($this->requestTimestamps, function ($timestamp) use ($now) { |
|
362
|
|
|
return ($now - $timestamp) < 60; |
|
363
|
|
|
}); |
|
364
|
|
|
|
|
365
|
|
|
$requestCount = count($this->requestTimestamps); |
|
366
|
|
|
|
|
367
|
|
|
// If we're at or over the limit, wait |
|
368
|
|
|
if ($requestCount >= self::RATE_LIMIT_PER_MINUTE) { |
|
369
|
|
|
// Calculate wait time based on oldest request |
|
370
|
|
|
if (! empty($this->requestTimestamps)) { |
|
371
|
|
|
$oldestRequest = min($this->requestTimestamps); |
|
372
|
|
|
$waitTime = 60 - ($now - $oldestRequest) + 1; // +1 for safety margin |
|
373
|
|
|
|
|
374
|
|
|
if ($waitTime > 0 && $waitTime <= 60) { |
|
375
|
|
|
if ($this->getOutput()->isVerbose()) { |
|
376
|
|
|
$this->newLine(); |
|
377
|
|
|
$this->warn("Rate limit reached ({$requestCount}/" . self::RATE_LIMIT_PER_MINUTE . "). Waiting {$waitTime} seconds..."); |
|
378
|
|
|
} |
|
379
|
|
|
sleep($waitTime); |
|
380
|
|
|
|
|
381
|
|
|
// Clean timestamps again after waiting |
|
382
|
|
|
$now = time(); |
|
383
|
|
|
$this->requestTimestamps = array_filter($this->requestTimestamps, function ($timestamp) use ($now) { |
|
384
|
|
|
return ($now - $timestamp) < 60; |
|
385
|
|
|
}); |
|
386
|
|
|
} |
|
387
|
|
|
} |
|
388
|
|
|
} |
|
389
|
|
|
|
|
390
|
|
|
// Calculate minimum delay between requests (to maintain 35/min rate) |
|
391
|
|
|
// 60 seconds / 35 requests = ~1.71 seconds per request |
|
392
|
|
|
$minDelay = 60.0 / self::RATE_LIMIT_PER_MINUTE; |
|
393
|
|
|
|
|
394
|
|
|
// If we have recent requests, ensure we wait at least the minimum delay |
|
395
|
|
|
if (! empty($this->requestTimestamps)) { |
|
396
|
|
|
$lastRequest = max($this->requestTimestamps); |
|
397
|
|
|
$timeSinceLastRequest = $now - $lastRequest; |
|
398
|
|
|
|
|
399
|
|
|
if ($timeSinceLastRequest < $minDelay) { |
|
400
|
|
|
$waitTime = $minDelay - $timeSinceLastRequest; |
|
401
|
|
|
if ($waitTime > 0 && $waitTime < 2) { // Only wait if less than 2 seconds |
|
402
|
|
|
usleep((int) ($waitTime * 1000000)); // Convert to microseconds |
|
403
|
|
|
$now = time(); // Update now after waiting |
|
404
|
|
|
} |
|
405
|
|
|
} |
|
406
|
|
|
} |
|
407
|
|
|
|
|
408
|
|
|
// Record this request timestamp (after all delays) |
|
409
|
|
|
$this->requestTimestamps[] = $now; |
|
410
|
|
|
} |
|
411
|
|
|
} |
|
412
|
|
|
|
|
413
|
|
|
|