mcp-scraper 0.3.24 → 0.3.26

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 (66) hide show
  1. package/dist/bin/api-server.cjs +8220 -5991
  2. package/dist/bin/api-server.cjs.map +1 -1
  3. package/dist/bin/api-server.js +3 -3
  4. package/dist/bin/mcp-scraper-cli.cjs +320 -58
  5. package/dist/bin/mcp-scraper-cli.cjs.map +1 -1
  6. package/dist/bin/mcp-scraper-cli.js +4 -3
  7. package/dist/bin/mcp-scraper-cli.js.map +1 -1
  8. package/dist/bin/mcp-scraper-install.cjs +3 -3
  9. package/dist/bin/mcp-scraper-install.cjs.map +1 -1
  10. package/dist/bin/mcp-scraper-install.js +2 -2
  11. package/dist/bin/mcp-stdio-server.cjs +186 -49
  12. package/dist/bin/mcp-stdio-server.cjs.map +1 -1
  13. package/dist/bin/mcp-stdio-server.js +5 -5
  14. package/dist/bin/paa-harvest.cjs +284 -10
  15. package/dist/bin/paa-harvest.cjs.map +1 -1
  16. package/dist/bin/paa-harvest.js +5 -3
  17. package/dist/bin/paa-harvest.js.map +1 -1
  18. package/dist/{chunk-GZ4W72WF.js → chunk-2GHI2D6Q.js} +184 -48
  19. package/dist/chunk-2GHI2D6Q.js.map +1 -0
  20. package/dist/{chunk-ZAP7MYVO.js → chunk-3PRO376E.js} +2 -3
  21. package/dist/chunk-3PRO376E.js.map +1 -0
  22. package/dist/{chunk-LFATOGDF.js → chunk-BP27CZ5Q.js} +4 -3
  23. package/dist/chunk-BP27CZ5Q.js.map +1 -0
  24. package/dist/{chunk-DE7WP4UU.js → chunk-DOBQN3EY.js} +3 -3
  25. package/dist/chunk-DOBQN3EY.js.map +1 -0
  26. package/dist/{chunk-IGOEAKC7.js → chunk-G7PQ64LM.js} +274 -9
  27. package/dist/chunk-G7PQ64LM.js.map +1 -0
  28. package/dist/chunk-K443GQY5.js +24 -0
  29. package/dist/chunk-K443GQY5.js.map +1 -0
  30. package/dist/chunk-MS2UZ6HR.js +7 -0
  31. package/dist/chunk-MS2UZ6HR.js.map +1 -0
  32. package/dist/{chunk-H2R232HK.js → chunk-NNEIXK5L.js} +307 -62
  33. package/dist/chunk-NNEIXK5L.js.map +1 -0
  34. package/dist/{chunk-3KYRG7O7.js → chunk-TRNSXR46.js} +185 -2
  35. package/dist/chunk-TRNSXR46.js.map +1 -0
  36. package/dist/{chunk-JTWQGPKF.js → chunk-WYCER2HW.js} +33 -10
  37. package/dist/chunk-WYCER2HW.js.map +1 -0
  38. package/dist/{db-EG5ETPTY.js → db-FP2ABUU4.js} +32 -2
  39. package/dist/index.cjs +284 -10
  40. package/dist/index.cjs.map +1 -1
  41. package/dist/index.d.cts +7 -3
  42. package/dist/index.d.ts +7 -3
  43. package/dist/index.js +5 -3
  44. package/dist/index.js.map +1 -1
  45. package/dist/{server-2SRARAO5.js → server-HIGHKTEV.js} +1563 -275
  46. package/dist/server-HIGHKTEV.js.map +1 -0
  47. package/dist/{worker-UM5UM6O5.js → worker-UC6D2756.js} +7 -6
  48. package/dist/{worker-UM5UM6O5.js.map → worker-UC6D2756.js.map} +1 -1
  49. package/docs/kernel-proxy-future-enhancements.md +80 -0
  50. package/docs/spec-browser-routing.md +108 -0
  51. package/docs/spec-mcp-tools.md +146 -0
  52. package/docs/spec-server-instructions.md +94 -0
  53. package/docs/specs/audit-visual-demo.md +309 -0
  54. package/package.json +5 -2
  55. package/dist/chunk-3KYRG7O7.js.map +0 -1
  56. package/dist/chunk-DE7WP4UU.js.map +0 -1
  57. package/dist/chunk-GZ4W72WF.js.map +0 -1
  58. package/dist/chunk-H2R232HK.js.map +0 -1
  59. package/dist/chunk-H7R4PPMG.js +0 -7
  60. package/dist/chunk-H7R4PPMG.js.map +0 -1
  61. package/dist/chunk-IGOEAKC7.js.map +0 -1
  62. package/dist/chunk-JTWQGPKF.js.map +0 -1
  63. package/dist/chunk-LFATOGDF.js.map +0 -1
  64. package/dist/chunk-ZAP7MYVO.js.map +0 -1
  65. package/dist/server-2SRARAO5.js.map +0 -1
  66. /package/dist/{db-EG5ETPTY.js.map → db-FP2ABUU4.js.map} +0 -0
@@ -1 +0,0 @@
1
- {"version":3,"sources":["../src/schemas.ts"],"sourcesContent":["import { z } from 'zod'\n\nexport const DEFAULT_PROXY_MODE = 'configured' as const\nexport const DEFAULT_MAPS_PROXY_MODE = 'location' as const\n\nexport const HarvestOptionsSchema = z.object({\n query: z.string().min(1),\n location: z.string().optional(),\n gl: z.string().length(2).default('us'),\n hl: z.string().length(2).default('en'),\n device: z.enum(['desktop', 'mobile']).default('desktop'),\n proxyMode: z.enum(['location', 'configured', 'none']).default(DEFAULT_PROXY_MODE),\n proxyZip: z.string().regex(/^\\d{5}$/).optional(),\n debug: z.boolean().default(false),\n depth: z.number().int().min(1).max(30).default(3),\n maxQuestions: z.number().int().min(1).max(1000).default(100),\n headless: z.boolean().default(false),\n profileDir: z.string().optional(),\n proxy: z.string().url().optional(),\n kernelApiKey: z.string().optional(),\n kernelProxyId: z.string().optional(),\n kernelProxyResolution: z.unknown().optional(),\n outputDir: z.string().default('./paa-output'),\n format: z.enum(['json', 'csv', 'both']).default('both'),\n serpOnly: z.boolean().default(false),\n pages: z.number().int().min(1).max(2).default(1),\n})\n\nexport const MapsPlaceOptionsSchema = z.object({\n businessName: z.string().min(1),\n location: z.string().min(1),\n gl: z.string().length(2).default('us'),\n hl: z.string().length(2).default('en'),\n includeReviews: z.boolean().default(false),\n maxReviews: z.number().int().min(1).max(500).default(50),\n kernelApiKey: z.string().optional(),\n kernelProxyId: z.string().optional(),\n headless: z.boolean().default(true),\n})\n\nexport const MapsSearchOptionsSchema = z.object({\n query: z.string().min(1),\n location: z.string().optional(),\n gl: z.string().length(2).default('us'),\n hl: z.string().length(2).default('en'),\n maxResults: z.number().int().min(1).max(50).default(10),\n proxyMode: z.enum(['location', 'configured', 'none']).default(DEFAULT_MAPS_PROXY_MODE),\n proxyZip: z.string().regex(/^\\d{5}$/).optional(),\n debug: z.boolean().default(false),\n kernelApiKey: z.string().optional(),\n kernelProxyId: z.string().optional(),\n kernelProxyResolution: z.unknown().optional(),\n headless: z.boolean().default(true),\n})\n\nexport const RawPAAItemSchema = z.object({\n question: z.string().min(1),\n answer: z.string().optional(),\n sourceTitle: z.string().optional(),\n sourceSite: z.string().optional(),\n sourceCite: z.string().optional(),\n})\n\nexport const RawMapsOverviewSchema = z.object({\n name: z.string().nullable(),\n rating: z.string().nullable(),\n reviewCount: z.string().nullable(),\n category: z.string().nullable(),\n address: z.string().nullable(),\n hoursSummary: z.string().nullable(),\n phone: z.string().nullable(),\n phoneDisplay: z.string().nullable(),\n website: z.string().nullable(),\n plusCode: z.string().nullable(),\n bookingUrl: z.string().nullable(),\n})\n\nexport const RawMapsHoursRowSchema = z.object({\n day: z.string(),\n hours: z.string(),\n})\n\nexport const RawMapsReviewStatsSchema = z.object({\n reviewHistogram: z.array(z.object({\n stars: z.number(),\n count: z.string(),\n })),\n reviewTopics: z.array(z.object({\n label: z.string(),\n count: z.string(),\n })),\n})\n\nexport const RawMapsReviewCardSchema = z.object({\n reviewId: z.string(),\n author: z.string().nullable(),\n stars: z.string().nullable(),\n date: z.string().nullable(),\n text: z.string().nullable(),\n ownerResponse: z.string().nullable(),\n})\n\nexport const RawMapsAboutAttributeSchema = z.object({\n section: z.string(),\n attribute: z.string(),\n})\n"],"mappings":";AAAA,SAAS,SAAS;AAEX,IAAM,qBAAqB;AAC3B,IAAM,0BAA0B;AAEhC,IAAM,uBAAuB,EAAE,OAAO;AAAA,EAC3C,OAAc,EAAE,OAAO,EAAE,IAAI,CAAC;AAAA,EAC9B,UAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,IAAc,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,QAAQ,IAAI;AAAA,EAC/C,IAAc,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,QAAQ,IAAI;AAAA,EAC/C,QAAc,EAAE,KAAK,CAAC,WAAW,QAAQ,CAAC,EAAE,QAAQ,SAAS;AAAA,EAC7D,WAAc,EAAE,KAAK,CAAC,YAAY,cAAc,MAAM,CAAC,EAAE,QAAQ,kBAAkB;AAAA,EACnF,UAAc,EAAE,OAAO,EAAE,MAAM,SAAS,EAAE,SAAS;AAAA,EACnD,OAAc,EAAE,QAAQ,EAAE,QAAQ,KAAK;AAAA,EACvC,OAAc,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI,EAAE,EAAE,QAAQ,CAAC;AAAA,EACvD,cAAc,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI,GAAI,EAAE,QAAQ,GAAG;AAAA,EAC3D,UAAc,EAAE,QAAQ,EAAE,QAAQ,KAAK;AAAA,EACvC,YAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,OAAc,EAAE,OAAO,EAAE,IAAI,EAAE,SAAS;AAAA,EACxC,cAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,eAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,uBAAuB,EAAE,QAAQ,EAAE,SAAS;AAAA,EAC5C,WAAc,EAAE,OAAO,EAAE,QAAQ,cAAc;AAAA,EAC/C,QAAc,EAAE,KAAK,CAAC,QAAQ,OAAO,MAAM,CAAC,EAAE,QAAQ,MAAM;AAAA,EAC5D,UAAc,EAAE,QAAQ,EAAE,QAAQ,KAAK;AAAA,EACvC,OAAc,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI,CAAC,EAAE,QAAQ,CAAC;AACxD,CAAC;AAEM,IAAM,yBAAyB,EAAE,OAAO;AAAA,EAC7C,cAAe,EAAE,OAAO,EAAE,IAAI,CAAC;AAAA,EAC/B,UAAe,EAAE,OAAO,EAAE,IAAI,CAAC;AAAA,EAC/B,IAAe,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,QAAQ,IAAI;AAAA,EAChD,IAAe,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,QAAQ,IAAI;AAAA,EAChD,gBAAgB,EAAE,QAAQ,EAAE,QAAQ,KAAK;AAAA,EACzC,YAAe,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI,GAAG,EAAE,QAAQ,EAAE;AAAA,EAC1D,cAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,eAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,UAAe,EAAE,QAAQ,EAAE,QAAQ,IAAI;AACzC,CAAC;AAEM,IAAM,0BAA0B,EAAE,OAAO;AAAA,EAC9C,OAAe,EAAE,OAAO,EAAE,IAAI,CAAC;AAAA,EAC/B,UAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,IAAe,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,QAAQ,IAAI;AAAA,EAChD,IAAe,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,QAAQ,IAAI;AAAA,EAChD,YAAe,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE;AAAA,EACzD,WAAe,EAAE,KAAK,CAAC,YAAY,cAAc,MAAM,CAAC,EAAE,QAAQ,uBAAuB;AAAA,EACzF,UAAe,EAAE,OAAO,EAAE,MAAM,SAAS,EAAE,SAAS;AAAA,EACpD,OAAe,EAAE,QAAQ,EAAE,QAAQ,KAAK;AAAA,EACxC,cAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,eAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,uBAAuB,EAAE,QAAQ,EAAE,SAAS;AAAA,EAC5C,UAAe,EAAE,QAAQ,EAAE,QAAQ,IAAI;AACzC,CAAC;AAEM,IAAM,mBAAmB,EAAE,OAAO;AAAA,EACvC,UAAa,EAAE,OAAO,EAAE,IAAI,CAAC;AAAA,EAC7B,QAAa,EAAE,OAAO,EAAE,SAAS;AAAA,EACjC,aAAa,EAAE,OAAO,EAAE,SAAS;AAAA,EACjC,YAAa,EAAE,OAAO,EAAE,SAAS;AAAA,EACjC,YAAa,EAAE,OAAO,EAAE,SAAS;AACnC,CAAC;AAEM,IAAM,wBAAwB,EAAE,OAAO;AAAA,EAC5C,MAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,QAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,aAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,UAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,SAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,cAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,OAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,cAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,SAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,UAAc,EAAE,OAAO,EAAE,SAAS;AAAA,EAClC,YAAc,EAAE,OAAO,EAAE,SAAS;AACpC,CAAC;AAEM,IAAM,wBAAwB,EAAE,OAAO;AAAA,EAC5C,KAAO,EAAE,OAAO;AAAA,EAChB,OAAO,EAAE,OAAO;AAClB,CAAC;AAEM,IAAM,2BAA2B,EAAE,OAAO;AAAA,EAC/C,iBAAiB,EAAE,MAAM,EAAE,OAAO;AAAA,IAChC,OAAO,EAAE,OAAO;AAAA,IAChB,OAAO,EAAE,OAAO;AAAA,EAClB,CAAC,CAAC;AAAA,EACF,cAAc,EAAE,MAAM,EAAE,OAAO;AAAA,IAC7B,OAAO,EAAE,OAAO;AAAA,IAChB,OAAO,EAAE,OAAO;AAAA,EAClB,CAAC,CAAC;AACJ,CAAC;AAEM,IAAM,0BAA0B,EAAE,OAAO;AAAA,EAC9C,UAAe,EAAE,OAAO;AAAA,EACxB,QAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,OAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,MAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,MAAe,EAAE,OAAO,EAAE,SAAS;AAAA,EACnC,eAAe,EAAE,OAAO,EAAE,SAAS;AACrC,CAAC;AAEM,IAAM,8BAA8B,EAAE,OAAO;AAAA,EAClD,SAAW,EAAE,OAAO;AAAA,EACpB,WAAW,EAAE,OAAO;AACtB,CAAC;","names":[]}
@@ -1 +0,0 @@
1
- {"version":3,"sources":["../src/lib/browser-service-env.ts","../src/errors.ts"],"sourcesContent":["export function browserServiceApiKey(): string | undefined {\n const value = (process.env.BROWSER_SERVICE_API_KEY ?? process.env.KERNEL_API_KEY)?.trim()\n return value || undefined\n}\n\nexport function browserServiceProxyId(): string | undefined {\n const value = (process.env.BROWSER_SERVICE_PROXY_ID ?? process.env.KERNEL_PROXY_ID)?.trim()\n return value || undefined\n}\n\nexport function browserServiceProfileName(): string | undefined {\n const value = (\n process.env.BROWSER_AGENT_PROFILE_NAME ??\n process.env.BROWSER_SERVICE_PROFILE_NAME ??\n process.env.KERNEL_BROWSER_PROFILE_NAME ??\n process.env.KERNEL_PROFILE_NAME\n )?.trim()\n return value || undefined\n}\n\nexport function browserServiceProfileSaveChanges(): boolean | undefined {\n const value = (\n process.env.BROWSER_AGENT_PROFILE_SAVE_CHANGES ??\n process.env.BROWSER_SERVICE_PROFILE_SAVE_CHANGES ??\n process.env.KERNEL_BROWSER_PROFILE_SAVE_CHANGES ??\n process.env.KERNEL_PROFILE_SAVE_CHANGES\n )?.trim().toLowerCase()\n if (!value) return undefined\n if (['1', 'true', 'yes', 'on'].includes(value)) return true\n if (['0', 'false', 'no', 'off'].includes(value)) return false\n return undefined\n}\n","export const RECAPTCHA_INSTRUCTIONS = 'Google returned a CAPTCHA. Run with --headless=false to re-warm the browser profile, then retry.'\n\nexport function sanitizeVendorName(message: string): string {\n return message\n .replace(/kernel\\.sh\\s+sessions?/gi, 'sessions')\n .replace(/kernel\\.sh\\s+session/gi, 'this session')\n .replace(/kernel\\.sh/gi, 'the service')\n .replace(/kernel\\s+sessions?/gi, 'sessions')\n .replace(/kernel\\s+session/gi, 'this session')\n .replace(/\\bkernel\\b/gi, 'the service')\n .replace(/ +/g, ' ')\n .trim()\n}\n\nexport class CaptchaError extends Error {\n readonly name = 'CaptchaError'\n constructor(public readonly instructions: string) {\n super(`CAPTCHA detected. ${instructions}`)\n }\n}\n\nexport class ExtractionError extends Error {\n readonly name = 'ExtractionError'\n constructor(message: string, public readonly cause?: unknown) {\n super(message)\n }\n}\n\nexport class RequestAbortedError extends Error {\n readonly name = 'RequestAbortedError'\n constructor(message = 'Request aborted before harvest completed') {\n super(message)\n }\n}\n\nexport class LocationMismatchError extends Error {\n readonly name = 'LocationMismatchError'\n constructor(message = 'Google returned results for a different location than requested') {\n super(message)\n }\n}\n"],"mappings":";AAAO,SAAS,uBAA2C;AACzD,QAAM,SAAS,QAAQ,IAAI,2BAA2B,QAAQ,IAAI,iBAAiB,KAAK;AACxF,SAAO,SAAS;AAClB;AAEO,SAAS,wBAA4C;AAC1D,QAAM,SAAS,QAAQ,IAAI,4BAA4B,QAAQ,IAAI,kBAAkB,KAAK;AAC1F,SAAO,SAAS;AAClB;AAEO,SAAS,4BAAgD;AAC9D,QAAM,SACJ,QAAQ,IAAI,8BACZ,QAAQ,IAAI,gCACZ,QAAQ,IAAI,+BACZ,QAAQ,IAAI,sBACX,KAAK;AACR,SAAO,SAAS;AAClB;AAEO,SAAS,mCAAwD;AACtE,QAAM,SACJ,QAAQ,IAAI,sCACZ,QAAQ,IAAI,wCACZ,QAAQ,IAAI,uCACZ,QAAQ,IAAI,8BACX,KAAK,EAAE,YAAY;AACtB,MAAI,CAAC,MAAO,QAAO;AACnB,MAAI,CAAC,KAAK,QAAQ,OAAO,IAAI,EAAE,SAAS,KAAK,EAAG,QAAO;AACvD,MAAI,CAAC,KAAK,SAAS,MAAM,KAAK,EAAE,SAAS,KAAK,EAAG,QAAO;AACxD,SAAO;AACT;;;AC/BO,IAAM,yBAAyB;AAE/B,SAAS,mBAAmB,SAAyB;AAC1D,SAAO,QACJ,QAAQ,4BAA4B,UAAU,EAC9C,QAAQ,0BAA0B,cAAc,EAChD,QAAQ,gBAAgB,aAAa,EACrC,QAAQ,wBAAwB,UAAU,EAC1C,QAAQ,sBAAsB,cAAc,EAC5C,QAAQ,gBAAgB,aAAa,EACrC,QAAQ,QAAQ,GAAG,EACnB,KAAK;AACV;AAEO,IAAM,eAAN,cAA2B,MAAM;AAAA,EAEtC,YAA4B,cAAsB;AAChD,UAAM,qBAAqB,YAAY,EAAE;AADf;AAAA,EAE5B;AAAA,EAF4B;AAAA,EADnB,OAAO;AAIlB;AAEO,IAAM,kBAAN,cAA8B,MAAM;AAAA,EAEzC,YAAY,SAAiC,OAAiB;AAC5D,UAAM,OAAO;AAD8B;AAAA,EAE7C;AAAA,EAF6C;AAAA,EADpC,OAAO;AAIlB;AAEO,IAAM,sBAAN,cAAkC,MAAM;AAAA,EACpC,OAAO;AAAA,EAChB,YAAY,UAAU,4CAA4C;AAChE,UAAM,OAAO;AAAA,EACf;AACF;AAEO,IAAM,wBAAN,cAAoC,MAAM;AAAA,EACtC,OAAO;AAAA,EAChB,YAAY,UAAU,mEAAmE;AACvF,UAAM,OAAO;AAAA,EACf;AACF;","names":[]}