@crawlith/core 0.1.1 → 0.1.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (237) hide show
  1. package/LICENSE +201 -0
  2. package/README.md +70 -0
  3. package/dist/analysis/analyze.d.ts +29 -8
  4. package/dist/analysis/analyze.js +325 -221
  5. package/dist/analysis/clustering.d.ts +23 -0
  6. package/dist/analysis/clustering.js +206 -0
  7. package/dist/analysis/content.d.ts +1 -1
  8. package/dist/analysis/content.js +11 -5
  9. package/dist/analysis/duplicate.d.ts +34 -0
  10. package/dist/analysis/duplicate.js +305 -0
  11. package/dist/analysis/heading.d.ts +116 -0
  12. package/dist/analysis/heading.js +356 -0
  13. package/dist/analysis/images.d.ts +1 -1
  14. package/dist/analysis/images.js +6 -5
  15. package/dist/analysis/links.d.ts +1 -1
  16. package/dist/analysis/links.js +8 -8
  17. package/dist/{scoring/orphanSeverity.d.ts → analysis/orphan.d.ts} +12 -23
  18. package/dist/{scoring/orphanSeverity.js → analysis/orphan.js} +9 -3
  19. package/dist/analysis/scoring.js +4 -1
  20. package/dist/analysis/seo.d.ts +8 -4
  21. package/dist/analysis/seo.js +41 -30
  22. package/dist/analysis/soft404.d.ts +17 -0
  23. package/dist/analysis/soft404.js +62 -0
  24. package/dist/analysis/structuredData.d.ts +1 -1
  25. package/dist/analysis/structuredData.js +5 -4
  26. package/dist/application/index.d.ts +2 -0
  27. package/dist/application/index.js +2 -0
  28. package/dist/application/usecase.d.ts +3 -0
  29. package/dist/application/usecase.js +1 -0
  30. package/dist/application/usecases.d.ts +114 -0
  31. package/dist/application/usecases.js +201 -0
  32. package/dist/audit/index.js +1 -1
  33. package/dist/audit/transport.d.ts +1 -1
  34. package/dist/audit/transport.js +5 -4
  35. package/dist/audit/types.d.ts +1 -0
  36. package/dist/constants.d.ts +17 -0
  37. package/dist/constants.js +23 -0
  38. package/dist/core/scope/scopeManager.js +3 -0
  39. package/dist/crawler/crawl.d.ts +2 -2
  40. package/dist/crawler/crawler.d.ts +17 -5
  41. package/dist/crawler/crawler.js +259 -94
  42. package/dist/crawler/fetcher.d.ts +1 -1
  43. package/dist/crawler/fetcher.js +6 -6
  44. package/dist/crawler/metricsRunner.d.ts +21 -1
  45. package/dist/crawler/metricsRunner.js +181 -60
  46. package/dist/crawler/normalize.d.ts +41 -0
  47. package/dist/crawler/normalize.js +119 -3
  48. package/dist/crawler/parser.d.ts +1 -3
  49. package/dist/crawler/parser.js +2 -49
  50. package/dist/crawler/resolver.d.ts +11 -0
  51. package/dist/crawler/resolver.js +67 -0
  52. package/dist/crawler/sitemap.d.ts +4 -1
  53. package/dist/crawler/sitemap.js +24 -18
  54. package/dist/crawler/trap.d.ts +5 -1
  55. package/dist/crawler/trap.js +23 -2
  56. package/dist/db/CrawlithDB.d.ts +110 -0
  57. package/dist/db/CrawlithDB.js +500 -0
  58. package/dist/db/graphLoader.js +15 -32
  59. package/dist/db/index.d.ts +9 -1
  60. package/dist/db/index.js +39 -31
  61. package/dist/db/migrations.d.ts +2 -0
  62. package/dist/db/{schema.js → migrations.js} +90 -43
  63. package/dist/db/pluginRegistry.d.ts +9 -0
  64. package/dist/db/pluginRegistry.js +19 -0
  65. package/dist/db/repositories/EdgeRepository.d.ts +5 -0
  66. package/dist/db/repositories/EdgeRepository.js +7 -0
  67. package/dist/db/repositories/MetricsRepository.d.ts +13 -8
  68. package/dist/db/repositories/MetricsRepository.js +14 -6
  69. package/dist/db/repositories/PageRepository.d.ts +5 -3
  70. package/dist/db/repositories/PageRepository.js +68 -17
  71. package/dist/db/repositories/SiteRepository.d.ts +6 -0
  72. package/dist/db/repositories/SiteRepository.js +4 -0
  73. package/dist/db/repositories/SnapshotRepository.d.ts +12 -5
  74. package/dist/db/repositories/SnapshotRepository.js +48 -10
  75. package/dist/db/reset.d.ts +9 -0
  76. package/dist/db/reset.js +32 -0
  77. package/dist/db/statements.d.ts +12 -0
  78. package/dist/db/statements.js +40 -0
  79. package/dist/diff/compare.d.ts +0 -5
  80. package/dist/diff/compare.js +0 -12
  81. package/dist/diff/service.d.ts +16 -0
  82. package/dist/diff/service.js +41 -0
  83. package/dist/domain/index.d.ts +4 -0
  84. package/dist/domain/index.js +4 -0
  85. package/dist/events.d.ts +8 -0
  86. package/dist/graph/graph.d.ts +20 -42
  87. package/dist/graph/graph.js +12 -16
  88. package/dist/graph/hits.d.ts +23 -0
  89. package/dist/graph/hits.js +111 -0
  90. package/dist/graph/metrics.d.ts +0 -4
  91. package/dist/graph/metrics.js +19 -15
  92. package/dist/graph/pagerank.d.ts +17 -4
  93. package/dist/graph/pagerank.js +126 -93
  94. package/dist/index.d.ts +27 -9
  95. package/dist/index.js +27 -9
  96. package/dist/lock/lockManager.d.ts +1 -0
  97. package/dist/lock/lockManager.js +15 -0
  98. package/dist/plugin-system/plugin-cli.d.ts +10 -0
  99. package/dist/plugin-system/plugin-cli.js +31 -0
  100. package/dist/plugin-system/plugin-config.d.ts +16 -0
  101. package/dist/plugin-system/plugin-config.js +36 -0
  102. package/dist/plugin-system/plugin-loader.d.ts +17 -0
  103. package/dist/plugin-system/plugin-loader.js +122 -0
  104. package/dist/plugin-system/plugin-registry.d.ts +25 -0
  105. package/dist/plugin-system/plugin-registry.js +167 -0
  106. package/dist/plugin-system/plugin-types.d.ts +205 -0
  107. package/dist/plugin-system/plugin-types.js +1 -0
  108. package/dist/ports/index.d.ts +9 -0
  109. package/dist/ports/index.js +1 -0
  110. package/dist/report/export.d.ts +3 -0
  111. package/dist/report/export.js +81 -0
  112. package/dist/report/insight.d.ts +27 -0
  113. package/dist/report/insight.js +103 -0
  114. package/dist/scoring/health.d.ts +17 -11
  115. package/dist/scoring/health.js +183 -140
  116. package/dist/utils/chalk.d.ts +6 -0
  117. package/dist/utils/chalk.js +41 -0
  118. package/dist/utils/secureConfig.d.ts +23 -0
  119. package/dist/utils/secureConfig.js +128 -0
  120. package/package.json +10 -4
  121. package/CHANGELOG.md +0 -13
  122. package/dist/db/schema.d.ts +0 -2
  123. package/dist/graph/cluster.d.ts +0 -6
  124. package/dist/graph/cluster.js +0 -221
  125. package/dist/graph/duplicate.d.ts +0 -10
  126. package/dist/graph/duplicate.js +0 -302
  127. package/dist/scoring/hits.d.ts +0 -10
  128. package/dist/scoring/hits.js +0 -131
  129. package/scripts/copy-assets.js +0 -37
  130. package/src/analysis/analysis_list.html +0 -35
  131. package/src/analysis/analysis_page.html +0 -123
  132. package/src/analysis/analyze.ts +0 -505
  133. package/src/analysis/content.ts +0 -62
  134. package/src/analysis/images.ts +0 -28
  135. package/src/analysis/links.ts +0 -41
  136. package/src/analysis/scoring.ts +0 -66
  137. package/src/analysis/seo.ts +0 -82
  138. package/src/analysis/structuredData.ts +0 -62
  139. package/src/analysis/templates.ts +0 -9
  140. package/src/audit/dns.ts +0 -49
  141. package/src/audit/headers.ts +0 -98
  142. package/src/audit/index.ts +0 -66
  143. package/src/audit/scoring.ts +0 -232
  144. package/src/audit/transport.ts +0 -258
  145. package/src/audit/types.ts +0 -102
  146. package/src/core/network/proxyAdapter.ts +0 -21
  147. package/src/core/network/rateLimiter.ts +0 -39
  148. package/src/core/network/redirectController.ts +0 -47
  149. package/src/core/network/responseLimiter.ts +0 -34
  150. package/src/core/network/retryPolicy.ts +0 -57
  151. package/src/core/scope/domainFilter.ts +0 -45
  152. package/src/core/scope/scopeManager.ts +0 -52
  153. package/src/core/scope/subdomainPolicy.ts +0 -39
  154. package/src/core/security/ipGuard.ts +0 -171
  155. package/src/crawler/crawl.ts +0 -9
  156. package/src/crawler/crawler.ts +0 -601
  157. package/src/crawler/extract.ts +0 -39
  158. package/src/crawler/fetcher.ts +0 -251
  159. package/src/crawler/metricsRunner.ts +0 -137
  160. package/src/crawler/normalize.ts +0 -108
  161. package/src/crawler/parser.ts +0 -190
  162. package/src/crawler/sitemap.ts +0 -76
  163. package/src/crawler/trap.ts +0 -96
  164. package/src/db/graphLoader.ts +0 -135
  165. package/src/db/index.ts +0 -75
  166. package/src/db/repositories/EdgeRepository.ts +0 -43
  167. package/src/db/repositories/MetricsRepository.ts +0 -63
  168. package/src/db/repositories/PageRepository.ts +0 -228
  169. package/src/db/repositories/SiteRepository.ts +0 -43
  170. package/src/db/repositories/SnapshotRepository.ts +0 -99
  171. package/src/db/schema.ts +0 -177
  172. package/src/diff/compare.ts +0 -84
  173. package/src/events.ts +0 -16
  174. package/src/graph/cluster.ts +0 -246
  175. package/src/graph/duplicate.ts +0 -350
  176. package/src/graph/graph.ts +0 -192
  177. package/src/graph/metrics.ts +0 -125
  178. package/src/graph/pagerank.ts +0 -126
  179. package/src/graph/simhash.ts +0 -76
  180. package/src/index.ts +0 -33
  181. package/src/lock/hashKey.ts +0 -51
  182. package/src/lock/lockManager.ts +0 -132
  183. package/src/lock/pidCheck.ts +0 -13
  184. package/src/report/crawl.html +0 -879
  185. package/src/report/crawlExport.ts +0 -58
  186. package/src/report/crawl_template.ts +0 -9
  187. package/src/report/html.ts +0 -27
  188. package/src/scoring/health.ts +0 -241
  189. package/src/scoring/hits.ts +0 -153
  190. package/src/scoring/orphanSeverity.ts +0 -176
  191. package/src/utils/version.ts +0 -18
  192. package/tests/__snapshots__/orphanSeverity.test.ts.snap +0 -49
  193. package/tests/analysis.unit.test.ts +0 -142
  194. package/tests/analyze.integration.test.ts +0 -133
  195. package/tests/analyze_markdown.test.ts +0 -98
  196. package/tests/audit/audit.test.ts +0 -101
  197. package/tests/audit/dns.test.ts +0 -31
  198. package/tests/audit/headers.test.ts +0 -45
  199. package/tests/audit/scoring.test.ts +0 -133
  200. package/tests/audit/security.test.ts +0 -12
  201. package/tests/audit/transport.test.ts +0 -111
  202. package/tests/clustering.test.ts +0 -118
  203. package/tests/clustering_risk.test.ts +0 -118
  204. package/tests/crawler.test.ts +0 -364
  205. package/tests/db/index.test.ts +0 -134
  206. package/tests/db/repositories.test.ts +0 -115
  207. package/tests/db.test.ts +0 -159
  208. package/tests/db_repos.test.ts +0 -72
  209. package/tests/diff.test.ts +0 -67
  210. package/tests/duplicate.test.ts +0 -110
  211. package/tests/extract.test.ts +0 -86
  212. package/tests/fetcher.test.ts +0 -110
  213. package/tests/fetcher_safety.test.ts +0 -91
  214. package/tests/fixtures/analyze-crawl.json +0 -26
  215. package/tests/graph/graph.test.ts +0 -100
  216. package/tests/graphLoader.test.ts +0 -124
  217. package/tests/hits.test.ts +0 -134
  218. package/tests/html_report.test.ts +0 -59
  219. package/tests/ipGuard.test.ts +0 -73
  220. package/tests/lock/lockManager.test.ts +0 -198
  221. package/tests/metrics.test.ts +0 -196
  222. package/tests/normalize.test.ts +0 -88
  223. package/tests/orphanSeverity.test.ts +0 -160
  224. package/tests/pagerank.test.ts +0 -98
  225. package/tests/parser.test.ts +0 -117
  226. package/tests/proxy_safety.test.ts +0 -57
  227. package/tests/redirect_safety.test.ts +0 -77
  228. package/tests/renderAnalysisCsv.test.ts +0 -183
  229. package/tests/safety.test.ts +0 -126
  230. package/tests/scope.test.ts +0 -84
  231. package/tests/scoring.test.ts +0 -60
  232. package/tests/sitemap.test.ts +0 -100
  233. package/tests/soft404.test.ts +0 -41
  234. package/tests/ssrf_fix.test.ts +0 -69
  235. package/tests/trap.test.ts +0 -39
  236. package/tests/visualization_data.test.ts +0 -46
  237. package/tsconfig.json +0 -11
@@ -1,5 +1,6 @@
1
1
  import { Graph } from '../graph/graph.js';
2
2
  import { EngineContext } from '../events.js';
3
+ import { PluginRegistry } from '../plugin-system/plugin-registry.js';
3
4
  export interface CrawlOptions {
4
5
  limit: number;
5
6
  depth: number;
@@ -7,7 +8,7 @@ export interface CrawlOptions {
7
8
  ignoreRobots?: boolean;
8
9
  stripQuery?: boolean;
9
10
  previousGraph?: Graph;
10
- sitemap?: string;
11
+ sitemap?: string | boolean;
11
12
  debug?: boolean;
12
13
  detectSoft404?: boolean;
13
14
  detectTraps?: boolean;
@@ -19,12 +20,16 @@ export interface CrawlOptions {
19
20
  proxyUrl?: string;
20
21
  maxRedirects?: number;
21
22
  userAgent?: string;
22
- snapshotType?: 'full' | 'partial' | 'incremental';
23
+ snapshotRunType?: 'completed' | 'incremental' | 'single';
24
+ registry?: PluginRegistry;
25
+ plugins?: any[];
26
+ robots?: any;
23
27
  }
24
28
  export declare class Crawler {
25
29
  private startUrl;
26
30
  private options;
27
31
  private context;
32
+ private registry?;
28
33
  private visited;
29
34
  private uniqueQueue;
30
35
  private queue;
@@ -41,27 +46,34 @@ export declare class Crawler {
41
46
  private metricsRepo;
42
47
  private siteId;
43
48
  private snapshotId;
49
+ private reusingSnapshot;
50
+ private runType;
44
51
  private rootOrigin;
45
52
  private discoveryDepths;
46
53
  private pageBuffer;
47
54
  private edgeBuffer;
48
55
  private metricsBuffer;
56
+ private pendingSitemaps;
57
+ private edgesFound;
58
+ private lastProgressEmitAt;
59
+ private progressPhase;
49
60
  private scopeManager;
50
61
  private fetcher;
51
62
  private parser;
52
63
  private sitemapFetcher;
53
- private trapDetector;
54
64
  private robots;
55
65
  constructor(startUrl: string, options: CrawlOptions, context?: EngineContext);
66
+ private toStorageUrl;
56
67
  initialize(): Promise<void>;
57
68
  setupModules(): void;
58
- fetchRobots(): Promise<void>;
69
+ private fetchRobots;
59
70
  shouldEnqueue(url: string, depth: number): boolean;
60
- addToQueue(u: string, d: number): void;
71
+ addToQueue(u: string, d: number, data?: any): void;
61
72
  seedQueue(): Promise<void>;
62
73
  private bufferPage;
63
74
  private flushPages;
64
75
  private bufferEdge;
76
+ private emitProgress;
65
77
  private flushEdges;
66
78
  private bufferMetrics;
67
79
  private flushMetrics;