recker 1.0.43 → 1.0.44

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 (459) hide show
  1. package/README.md +47 -0
  2. package/dist/bin/recker-linux-x64 +0 -0
  3. package/dist/bin/recker-macos-x64 +0 -0
  4. package/dist/bin/recker-win-x64.exe +0 -0
  5. package/dist/bin/rek.cjs +85152 -100207
  6. package/dist/browser/ai/adaptive-timeout.d.ts +50 -0
  7. package/dist/browser/ai/adaptive-timeout.js +208 -0
  8. package/dist/browser/ai/client.d.ts +22 -0
  9. package/dist/browser/ai/client.js +294 -0
  10. package/dist/browser/ai/index.d.ts +14 -0
  11. package/dist/browser/ai/index.js +11 -0
  12. package/dist/browser/ai/providers/anthropic.d.ts +63 -0
  13. package/dist/browser/ai/providers/anthropic.js +370 -0
  14. package/dist/browser/ai/providers/base.d.ts +48 -0
  15. package/dist/browser/ai/providers/base.js +150 -0
  16. package/dist/browser/ai/providers/google.d.ts +59 -0
  17. package/dist/browser/ai/providers/google.js +305 -0
  18. package/dist/browser/ai/providers/ollama.d.ts +44 -0
  19. package/dist/browser/ai/providers/ollama.js +240 -0
  20. package/dist/browser/ai/providers/openai.d.ts +64 -0
  21. package/dist/browser/ai/providers/openai.js +298 -0
  22. package/dist/browser/ai/rate-limiter.d.ts +43 -0
  23. package/dist/browser/ai/rate-limiter.js +215 -0
  24. package/dist/browser/ai/vector/index.d.ts +2 -0
  25. package/dist/browser/ai/vector/index.js +2 -0
  26. package/dist/browser/ai/vector/similarity.d.ts +2 -0
  27. package/dist/browser/ai/vector/similarity.js +27 -0
  28. package/dist/browser/ai/vector/store.d.ts +27 -0
  29. package/dist/browser/ai/vector/store.js +82 -0
  30. package/dist/browser/browser/cache.d.ts +2 -40
  31. package/dist/browser/browser/cache.js +2 -199
  32. package/dist/browser/browser/index.d.ts +8 -0
  33. package/dist/browser/browser/index.js +8 -0
  34. package/dist/browser/browser/recker.d.ts +8 -1
  35. package/dist/browser/browser/recker.js +8 -2
  36. package/dist/browser/cache/indexed-db.d.ts +10 -0
  37. package/dist/browser/cache/indexed-db.js +88 -0
  38. package/dist/browser/cache/service-worker-cache.d.ts +18 -0
  39. package/dist/browser/cache/service-worker-cache.js +103 -0
  40. package/dist/browser/cache.d.ts +2 -40
  41. package/dist/browser/cache.js +2 -199
  42. package/dist/browser/constants/user-agents.d.ts +7 -0
  43. package/dist/browser/constants/user-agents.js +7 -0
  44. package/dist/browser/core/client.d.ts +2 -0
  45. package/dist/browser/core/client.js +19 -1
  46. package/dist/browser/index.d.ts +8 -0
  47. package/dist/browser/index.js +8 -0
  48. package/dist/browser/plugins/har-recorder.d.ts +40 -0
  49. package/dist/browser/plugins/har-recorder.js +120 -0
  50. package/dist/browser/plugins/network-simulation.d.ts +7 -0
  51. package/dist/browser/plugins/network-simulation.js +13 -0
  52. package/dist/browser/presets/android.d.ts +2 -0
  53. package/dist/browser/presets/android.js +16 -0
  54. package/dist/browser/presets/anthropic.d.ts +8 -0
  55. package/dist/browser/presets/anthropic.js +27 -0
  56. package/dist/browser/presets/aws.d.ts +19 -0
  57. package/dist/browser/presets/aws.js +68 -0
  58. package/dist/browser/presets/azure-openai.d.ts +10 -0
  59. package/dist/browser/presets/azure-openai.js +35 -0
  60. package/dist/browser/presets/azure.d.ts +41 -0
  61. package/dist/browser/presets/azure.js +104 -0
  62. package/dist/browser/presets/chaturbate.d.ts +2 -0
  63. package/dist/browser/presets/chaturbate.js +17 -0
  64. package/dist/browser/presets/cloudflare.d.ts +12 -0
  65. package/dist/browser/presets/cloudflare.js +39 -0
  66. package/dist/browser/presets/cohere.d.ts +7 -0
  67. package/dist/browser/presets/cohere.js +22 -0
  68. package/dist/browser/presets/deepseek.d.ts +7 -0
  69. package/dist/browser/presets/deepseek.js +22 -0
  70. package/dist/browser/presets/digitalocean.d.ts +5 -0
  71. package/dist/browser/presets/digitalocean.js +16 -0
  72. package/dist/browser/presets/discord.d.ts +6 -0
  73. package/dist/browser/presets/discord.js +17 -0
  74. package/dist/browser/presets/elevenlabs.d.ts +6 -0
  75. package/dist/browser/presets/elevenlabs.js +20 -0
  76. package/dist/browser/presets/enhancers.d.ts +20 -0
  77. package/dist/browser/presets/enhancers.js +85 -0
  78. package/dist/browser/presets/fireworks.d.ts +7 -0
  79. package/dist/browser/presets/fireworks.js +22 -0
  80. package/dist/browser/presets/gcp.d.ts +34 -0
  81. package/dist/browser/presets/gcp.js +91 -0
  82. package/dist/browser/presets/gemini.d.ts +7 -0
  83. package/dist/browser/presets/gemini.js +23 -0
  84. package/dist/browser/presets/github.d.ts +6 -0
  85. package/dist/browser/presets/github.js +17 -0
  86. package/dist/browser/presets/gitlab.d.ts +6 -0
  87. package/dist/browser/presets/gitlab.js +16 -0
  88. package/dist/browser/presets/groq.d.ts +7 -0
  89. package/dist/browser/presets/groq.js +22 -0
  90. package/dist/browser/presets/hubspot.d.ts +9 -0
  91. package/dist/browser/presets/hubspot.js +28 -0
  92. package/dist/browser/presets/huggingface.d.ts +7 -0
  93. package/dist/browser/presets/huggingface.js +23 -0
  94. package/dist/browser/presets/index.d.ts +47 -0
  95. package/dist/browser/presets/index.js +47 -0
  96. package/dist/browser/presets/ios.d.ts +2 -0
  97. package/dist/browser/presets/ios.js +13 -0
  98. package/dist/browser/presets/linear.d.ts +5 -0
  99. package/dist/browser/presets/linear.js +16 -0
  100. package/dist/browser/presets/mailgun.d.ts +7 -0
  101. package/dist/browser/presets/mailgun.js +20 -0
  102. package/dist/browser/presets/meta.d.ts +10 -0
  103. package/dist/browser/presets/meta.js +33 -0
  104. package/dist/browser/presets/mistral.d.ts +7 -0
  105. package/dist/browser/presets/mistral.js +22 -0
  106. package/dist/browser/presets/notion.d.ts +6 -0
  107. package/dist/browser/presets/notion.js +17 -0
  108. package/dist/browser/presets/openai.d.ts +9 -0
  109. package/dist/browser/presets/openai.js +30 -0
  110. package/dist/browser/presets/oracle.d.ts +19 -0
  111. package/dist/browser/presets/oracle.js +117 -0
  112. package/dist/browser/presets/perplexity.d.ts +7 -0
  113. package/dist/browser/presets/perplexity.js +22 -0
  114. package/dist/browser/presets/pinecone.d.ts +8 -0
  115. package/dist/browser/presets/pinecone.js +42 -0
  116. package/dist/browser/presets/registry.d.ts +23 -0
  117. package/dist/browser/presets/registry.js +519 -0
  118. package/dist/browser/presets/replicate.d.ts +7 -0
  119. package/dist/browser/presets/replicate.js +23 -0
  120. package/dist/browser/presets/sendgrid.d.ts +6 -0
  121. package/dist/browser/presets/sendgrid.js +20 -0
  122. package/dist/browser/presets/sentry.d.ts +11 -0
  123. package/dist/browser/presets/sentry.js +48 -0
  124. package/dist/browser/presets/sinch.d.ts +9 -0
  125. package/dist/browser/presets/sinch.js +39 -0
  126. package/dist/browser/presets/slack.d.ts +5 -0
  127. package/dist/browser/presets/slack.js +16 -0
  128. package/dist/browser/presets/square.d.ts +10 -0
  129. package/dist/browser/presets/square.js +33 -0
  130. package/dist/browser/presets/stripe.d.ts +7 -0
  131. package/dist/browser/presets/stripe.js +23 -0
  132. package/dist/browser/presets/supabase.d.ts +6 -0
  133. package/dist/browser/presets/supabase.js +18 -0
  134. package/dist/browser/presets/tiktok.d.ts +10 -0
  135. package/dist/browser/presets/tiktok.js +38 -0
  136. package/dist/browser/presets/together.d.ts +7 -0
  137. package/dist/browser/presets/together.js +22 -0
  138. package/dist/browser/presets/twilio.d.ts +6 -0
  139. package/dist/browser/presets/twilio.js +17 -0
  140. package/dist/browser/presets/vercel.d.ts +6 -0
  141. package/dist/browser/presets/vercel.js +23 -0
  142. package/dist/browser/presets/vultr.d.ts +5 -0
  143. package/dist/browser/presets/vultr.js +16 -0
  144. package/dist/browser/presets/xai.d.ts +8 -0
  145. package/dist/browser/presets/xai.js +23 -0
  146. package/dist/browser/presets/youtube.d.ts +5 -0
  147. package/dist/browser/presets/youtube.js +20 -0
  148. package/dist/browser/recker.d.ts +8 -1
  149. package/dist/browser/recker.js +8 -2
  150. package/dist/browser/scrape/document.d.ts +5 -4
  151. package/dist/browser/scrape/document.js +89 -76
  152. package/dist/browser/scrape/element.d.ts +10 -8
  153. package/dist/browser/scrape/element.js +295 -81
  154. package/dist/browser/scrape/extractors.d.ts +11 -11
  155. package/dist/browser/scrape/extractors.js +145 -113
  156. package/dist/browser/scrape/parser/back.d.ts +1 -0
  157. package/dist/browser/scrape/parser/back.js +3 -0
  158. package/dist/browser/scrape/parser/index.d.ts +20 -0
  159. package/dist/browser/scrape/parser/index.js +19 -0
  160. package/dist/browser/scrape/parser/matcher.d.ts +30 -0
  161. package/dist/browser/scrape/parser/matcher.js +99 -0
  162. package/dist/browser/scrape/parser/nodes/comment.d.ts +12 -0
  163. package/dist/browser/scrape/parser/nodes/comment.js +21 -0
  164. package/dist/browser/scrape/parser/nodes/html.d.ts +110 -0
  165. package/dist/browser/scrape/parser/nodes/html.js +978 -0
  166. package/dist/browser/scrape/parser/nodes/node.d.ts +18 -0
  167. package/dist/browser/scrape/parser/nodes/node.js +31 -0
  168. package/dist/browser/scrape/parser/nodes/text.d.ts +14 -0
  169. package/dist/browser/scrape/parser/nodes/text.js +30 -0
  170. package/dist/browser/scrape/parser/nodes/type.d.ts +6 -0
  171. package/dist/browser/scrape/parser/nodes/type.js +7 -0
  172. package/dist/browser/scrape/parser/parse.d.ts +1 -0
  173. package/dist/browser/scrape/parser/parse.js +1 -0
  174. package/dist/browser/scrape/parser/valid.d.ts +2 -0
  175. package/dist/browser/scrape/parser/valid.js +5 -0
  176. package/dist/browser/scrape/parser/void-tag.d.ts +7 -0
  177. package/dist/browser/scrape/parser/void-tag.js +43 -0
  178. package/dist/browser/scrape/types.d.ts +7 -0
  179. package/dist/browser/seo/analyzer.d.ts +59 -0
  180. package/dist/browser/seo/analyzer.js +1399 -0
  181. package/dist/browser/seo/keywords.d.ts +16 -0
  182. package/dist/browser/seo/keywords.js +55 -0
  183. package/dist/browser/seo/rules/accessibility.d.ts +2 -0
  184. package/dist/browser/seo/rules/accessibility.js +733 -0
  185. package/dist/browser/seo/rules/ai-search.d.ts +2 -0
  186. package/dist/browser/seo/rules/ai-search.js +436 -0
  187. package/dist/browser/seo/rules/analytics.d.ts +2 -0
  188. package/dist/browser/seo/rules/analytics.js +306 -0
  189. package/dist/browser/seo/rules/best-practices.d.ts +2 -0
  190. package/dist/browser/seo/rules/best-practices.js +195 -0
  191. package/dist/browser/seo/rules/canonical.d.ts +12 -0
  192. package/dist/browser/seo/rules/canonical.js +270 -0
  193. package/dist/browser/seo/rules/content.d.ts +2 -0
  194. package/dist/browser/seo/rules/content.js +522 -0
  195. package/dist/browser/seo/rules/crawl.d.ts +2 -0
  196. package/dist/browser/seo/rules/crawl.js +435 -0
  197. package/dist/browser/seo/rules/cwv.d.ts +2 -0
  198. package/dist/browser/seo/rules/cwv.js +248 -0
  199. package/dist/browser/seo/rules/ecommerce.d.ts +2 -0
  200. package/dist/browser/seo/rules/ecommerce.js +312 -0
  201. package/dist/browser/seo/rules/i18n.d.ts +2 -0
  202. package/dist/browser/seo/rules/i18n.js +288 -0
  203. package/dist/browser/seo/rules/images.d.ts +2 -0
  204. package/dist/browser/seo/rules/images.js +255 -0
  205. package/dist/browser/seo/rules/index.d.ts +52 -0
  206. package/dist/browser/seo/rules/index.js +159 -0
  207. package/dist/browser/seo/rules/internal-linking.d.ts +2 -0
  208. package/dist/browser/seo/rules/internal-linking.js +394 -0
  209. package/dist/browser/seo/rules/links.d.ts +2 -0
  210. package/dist/browser/seo/rules/links.js +498 -0
  211. package/dist/browser/seo/rules/local.d.ts +2 -0
  212. package/dist/browser/seo/rules/local.js +289 -0
  213. package/dist/browser/seo/rules/meta.d.ts +2 -0
  214. package/dist/browser/seo/rules/meta.js +805 -0
  215. package/dist/browser/seo/rules/mobile.d.ts +2 -0
  216. package/dist/browser/seo/rules/mobile.js +161 -0
  217. package/dist/browser/seo/rules/performance.d.ts +2 -0
  218. package/dist/browser/seo/rules/performance.js +738 -0
  219. package/dist/browser/seo/rules/pwa.d.ts +2 -0
  220. package/dist/browser/seo/rules/pwa.js +299 -0
  221. package/dist/browser/seo/rules/readability.d.ts +2 -0
  222. package/dist/browser/seo/rules/readability.js +264 -0
  223. package/dist/browser/seo/rules/redirects.d.ts +16 -0
  224. package/dist/browser/seo/rules/redirects.js +199 -0
  225. package/dist/browser/seo/rules/resources.d.ts +2 -0
  226. package/dist/browser/seo/rules/resources.js +390 -0
  227. package/dist/browser/seo/rules/schema.d.ts +2 -0
  228. package/dist/browser/seo/rules/schema.js +379 -0
  229. package/dist/browser/seo/rules/security.d.ts +2 -0
  230. package/dist/browser/seo/rules/security.js +877 -0
  231. package/dist/browser/seo/rules/social.d.ts +2 -0
  232. package/dist/browser/seo/rules/social.js +603 -0
  233. package/dist/browser/seo/rules/structural.d.ts +2 -0
  234. package/dist/browser/seo/rules/structural.js +223 -0
  235. package/dist/browser/seo/rules/technical-advanced.d.ts +10 -0
  236. package/dist/browser/seo/rules/technical-advanced.js +289 -0
  237. package/dist/browser/seo/rules/technical.d.ts +2 -0
  238. package/dist/browser/seo/rules/technical.js +480 -0
  239. package/dist/browser/seo/rules/thresholds.d.ts +196 -0
  240. package/dist/browser/seo/rules/thresholds.js +118 -0
  241. package/dist/browser/seo/rules/types.d.ts +498 -0
  242. package/dist/browser/seo/rules/types.js +11 -0
  243. package/dist/browser/seo/types.d.ts +211 -0
  244. package/dist/browser/seo/types.js +1 -0
  245. package/dist/browser/transport/curl.d.ts +4 -0
  246. package/dist/browser/transport/curl.js +101 -0
  247. package/dist/browser/transport/undici.js +1 -2
  248. package/dist/browser/transport/worker.d.ts +18 -0
  249. package/dist/browser/transport/worker.js +278 -0
  250. package/dist/browser/types/index.d.ts +4 -1
  251. package/dist/browser/utils/binary-manager.d.ts +4 -0
  252. package/dist/browser/utils/binary-manager.js +72 -0
  253. package/dist/browser/utils/user-agent.js +2 -13
  254. package/dist/cache/indexed-db.d.ts +10 -0
  255. package/dist/cache/indexed-db.js +88 -0
  256. package/dist/cache/service-worker-cache.d.ts +18 -0
  257. package/dist/cache/service-worker-cache.js +103 -0
  258. package/dist/cli/commands/ai.d.ts +2 -0
  259. package/dist/cli/commands/ai.js +162 -0
  260. package/dist/cli/commands/bench.d.ts +2 -0
  261. package/dist/cli/commands/bench.js +51 -0
  262. package/dist/cli/commands/dns.d.ts +2 -0
  263. package/dist/cli/commands/dns.js +295 -0
  264. package/dist/cli/commands/har.d.ts +2 -0
  265. package/dist/cli/commands/har.js +171 -0
  266. package/dist/cli/commands/hls.d.ts +2 -0
  267. package/dist/cli/commands/hls.js +192 -0
  268. package/dist/cli/commands/network.d.ts +2 -0
  269. package/dist/cli/commands/network.js +288 -0
  270. package/dist/cli/commands/protocols.d.ts +2 -0
  271. package/dist/cli/commands/protocols.js +344 -0
  272. package/dist/cli/commands/scrape.d.ts +2 -0
  273. package/dist/cli/commands/scrape.js +176 -0
  274. package/dist/cli/commands/security.d.ts +2 -0
  275. package/dist/cli/commands/security.js +57 -0
  276. package/dist/cli/commands/seo.d.ts +2 -0
  277. package/dist/cli/commands/seo.js +125 -0
  278. package/dist/cli/commands/serve.d.ts +2 -0
  279. package/dist/cli/commands/serve.js +531 -0
  280. package/dist/cli/commands/spider.d.ts +3 -0
  281. package/dist/cli/commands/spider.js +456 -0
  282. package/dist/cli/commands/utils.d.ts +2 -0
  283. package/dist/cli/commands/utils.js +176 -0
  284. package/dist/cli/commands/vector.d.ts +2 -0
  285. package/dist/cli/commands/vector.js +158 -0
  286. package/dist/cli/handler.d.ts +2 -2
  287. package/dist/cli/handler.js +6 -6
  288. package/dist/cli/helpers.d.ts +7 -0
  289. package/dist/cli/helpers.js +128 -0
  290. package/dist/cli/index.js +96 -5228
  291. package/dist/cli/parser/help.d.ts +2 -0
  292. package/dist/cli/parser/help.js +52 -0
  293. package/dist/cli/parser/index.d.ts +3 -0
  294. package/dist/cli/parser/index.js +3 -0
  295. package/dist/cli/parser/parser.d.ts +4 -0
  296. package/dist/cli/parser/parser.js +146 -0
  297. package/dist/cli/parser/types.d.ts +41 -0
  298. package/dist/cli/parser/types.js +1 -0
  299. package/dist/cli/presets.d.ts +1 -1
  300. package/dist/cli/presets.js +1 -1
  301. package/dist/cli/router.d.ts +36 -0
  302. package/dist/cli/router.js +195 -0
  303. package/dist/cli/tui/ai-chat.js +1 -1
  304. package/dist/cli/tui/commands/context.d.ts +9 -0
  305. package/dist/cli/tui/commands/context.js +1 -0
  306. package/dist/cli/tui/commands/dns.d.ts +10 -0
  307. package/dist/cli/tui/commands/dns.js +461 -0
  308. package/dist/cli/tui/commands/hls.d.ts +2 -0
  309. package/dist/cli/tui/commands/hls.js +162 -0
  310. package/dist/cli/tui/commands/ip.d.ts +2 -0
  311. package/dist/cli/tui/commands/ip.js +45 -0
  312. package/dist/cli/tui/commands/network.d.ts +3 -0
  313. package/dist/cli/tui/commands/network.js +81 -0
  314. package/dist/cli/tui/commands/protocols.d.ts +6 -0
  315. package/dist/cli/tui/commands/protocols.js +531 -0
  316. package/dist/cli/tui/commands/security.d.ts +2 -0
  317. package/dist/cli/tui/commands/security.js +48 -0
  318. package/dist/cli/tui/commands/seo.d.ts +2 -0
  319. package/dist/cli/tui/commands/seo.js +74 -0
  320. package/dist/cli/tui/context.d.ts +12 -0
  321. package/dist/cli/tui/context.js +1 -0
  322. package/dist/cli/tui/shell.d.ts +11 -20
  323. package/dist/cli/tui/shell.js +216 -1873
  324. package/dist/constants/user-agents.d.ts +7 -0
  325. package/dist/constants/user-agents.js +7 -0
  326. package/dist/core/client.d.ts +2 -0
  327. package/dist/core/client.js +19 -1
  328. package/dist/index.d.ts +1 -0
  329. package/dist/index.js +1 -0
  330. package/dist/mcp/cli.js +2 -3
  331. package/dist/mcp/data/embeddings.json +1 -1
  332. package/dist/mcp/tools/network.js +298 -158
  333. package/dist/plugins/har-player.d.ts +23 -0
  334. package/dist/plugins/har-player.js +49 -0
  335. package/dist/plugins/har-recorder.d.ts +37 -3
  336. package/dist/plugins/har-recorder.js +116 -63
  337. package/dist/plugins/network-simulation.d.ts +7 -0
  338. package/dist/plugins/network-simulation.js +13 -0
  339. package/dist/presets/android.d.ts +2 -0
  340. package/dist/presets/android.js +16 -0
  341. package/dist/presets/chaturbate.d.ts +2 -0
  342. package/dist/presets/chaturbate.js +17 -0
  343. package/dist/presets/elevenlabs.d.ts +6 -0
  344. package/dist/presets/elevenlabs.js +20 -0
  345. package/dist/presets/enhancers.d.ts +20 -0
  346. package/dist/presets/enhancers.js +85 -0
  347. package/dist/presets/hubspot.d.ts +9 -0
  348. package/dist/presets/hubspot.js +28 -0
  349. package/dist/presets/index.d.ts +10 -0
  350. package/dist/presets/index.js +10 -0
  351. package/dist/presets/ios.d.ts +2 -0
  352. package/dist/presets/ios.js +13 -0
  353. package/dist/presets/pinecone.d.ts +8 -0
  354. package/dist/presets/pinecone.js +42 -0
  355. package/dist/presets/registry.js +60 -0
  356. package/dist/presets/sendgrid.d.ts +6 -0
  357. package/dist/presets/sendgrid.js +20 -0
  358. package/dist/presets/sentry.d.ts +11 -0
  359. package/dist/presets/sentry.js +48 -0
  360. package/dist/presets/square.d.ts +10 -0
  361. package/dist/presets/square.js +33 -0
  362. package/dist/recker.d.ts +3 -0
  363. package/dist/recker.js +4 -0
  364. package/dist/scrape/document.d.ts +5 -4
  365. package/dist/scrape/document.js +89 -76
  366. package/dist/scrape/element.d.ts +10 -8
  367. package/dist/scrape/element.js +295 -81
  368. package/dist/scrape/extractors.d.ts +11 -11
  369. package/dist/scrape/extractors.js +145 -113
  370. package/dist/scrape/index.d.ts +2 -0
  371. package/dist/scrape/index.js +1 -0
  372. package/dist/scrape/parser/back.d.ts +1 -0
  373. package/dist/scrape/parser/back.js +3 -0
  374. package/dist/scrape/parser/index.d.ts +20 -0
  375. package/dist/scrape/parser/index.js +19 -0
  376. package/dist/scrape/parser/matcher.d.ts +30 -0
  377. package/dist/scrape/parser/matcher.js +99 -0
  378. package/dist/scrape/parser/nodes/comment.d.ts +12 -0
  379. package/dist/scrape/parser/nodes/comment.js +21 -0
  380. package/dist/scrape/parser/nodes/html.d.ts +110 -0
  381. package/dist/scrape/parser/nodes/html.js +978 -0
  382. package/dist/scrape/parser/nodes/node.d.ts +18 -0
  383. package/dist/scrape/parser/nodes/node.js +31 -0
  384. package/dist/scrape/parser/nodes/text.d.ts +14 -0
  385. package/dist/scrape/parser/nodes/text.js +30 -0
  386. package/dist/scrape/parser/nodes/type.d.ts +6 -0
  387. package/dist/scrape/parser/nodes/type.js +7 -0
  388. package/dist/scrape/parser/parse.d.ts +1 -0
  389. package/dist/scrape/parser/parse.js +1 -0
  390. package/dist/scrape/parser/valid.d.ts +2 -0
  391. package/dist/scrape/parser/valid.js +5 -0
  392. package/dist/scrape/parser/void-tag.d.ts +7 -0
  393. package/dist/scrape/parser/void-tag.js +43 -0
  394. package/dist/scrape/spider.d.ts +19 -0
  395. package/dist/scrape/spider.js +28 -3
  396. package/dist/scrape/types.d.ts +7 -0
  397. package/dist/seo/analyzer.d.ts +15 -5
  398. package/dist/seo/analyzer.js +636 -175
  399. package/dist/seo/formatter.d.ts +16 -0
  400. package/dist/seo/formatter.js +228 -0
  401. package/dist/seo/index.d.ts +2 -0
  402. package/dist/seo/index.js +1 -0
  403. package/dist/seo/keywords.d.ts +16 -0
  404. package/dist/seo/keywords.js +55 -0
  405. package/dist/seo/rules/accessibility.js +96 -57
  406. package/dist/seo/rules/ai-search.js +44 -31
  407. package/dist/seo/rules/analytics.d.ts +2 -0
  408. package/dist/seo/rules/analytics.js +306 -0
  409. package/dist/seo/rules/best-practices.js +21 -14
  410. package/dist/seo/rules/canonical.js +53 -32
  411. package/dist/seo/rules/content.js +317 -31
  412. package/dist/seo/rules/crawl.js +55 -40
  413. package/dist/seo/rules/cwv.js +21 -15
  414. package/dist/seo/rules/ecommerce.js +82 -22
  415. package/dist/seo/rules/i18n.js +75 -36
  416. package/dist/seo/rules/images.js +109 -30
  417. package/dist/seo/rules/index.js +2 -0
  418. package/dist/seo/rules/internal-linking.js +58 -39
  419. package/dist/seo/rules/links.js +79 -52
  420. package/dist/seo/rules/local.js +49 -25
  421. package/dist/seo/rules/meta.js +339 -81
  422. package/dist/seo/rules/mobile.js +112 -2
  423. package/dist/seo/rules/performance.js +434 -66
  424. package/dist/seo/rules/pwa.js +36 -39
  425. package/dist/seo/rules/readability.js +31 -22
  426. package/dist/seo/rules/redirects.js +21 -15
  427. package/dist/seo/rules/resources.js +59 -42
  428. package/dist/seo/rules/schema.js +333 -8
  429. package/dist/seo/rules/security.js +142 -80
  430. package/dist/seo/rules/social.js +277 -47
  431. package/dist/seo/rules/structural.js +87 -19
  432. package/dist/seo/rules/technical-advanced.js +30 -24
  433. package/dist/seo/rules/technical.js +243 -42
  434. package/dist/seo/rules/types.d.ts +53 -1
  435. package/dist/seo/seo-spider.d.ts +22 -0
  436. package/dist/seo/seo-spider.js +77 -13
  437. package/dist/seo/types.d.ts +8 -1
  438. package/dist/seo/validators/llms-txt.js +19 -0
  439. package/dist/seo/validators/rss.d.ts +11 -0
  440. package/dist/seo/validators/rss.js +93 -0
  441. package/dist/seo/validators/sitemap.js +36 -26
  442. package/dist/transport/curl.d.ts +4 -0
  443. package/dist/transport/curl.js +101 -0
  444. package/dist/transport/udp.js +0 -1
  445. package/dist/transport/undici.js +1 -2
  446. package/dist/transport/worker.d.ts +18 -0
  447. package/dist/transport/worker.js +278 -0
  448. package/dist/types/index.d.ts +4 -1
  449. package/dist/utils/binary-manager.d.ts +4 -0
  450. package/dist/utils/binary-manager.js +72 -0
  451. package/dist/utils/optional-require.d.ts +7 -8
  452. package/dist/utils/optional-require.js +2 -21
  453. package/dist/utils/upload.d.ts +6 -0
  454. package/dist/utils/upload.js +11 -0
  455. package/dist/utils/user-agent.js +2 -13
  456. package/dist/version.js +1 -1
  457. package/package.json +12 -6
  458. package/dist/browser/utils/optional-require.d.ts +0 -19
  459. package/dist/browser/utils/optional-require.js +0 -105
@@ -1,37 +1,32 @@
1
- import { requireOptional } from '../utils/optional-require.js';
2
1
  import { ScrapeElement } from './element.js';
2
+ import { parse } from './parser/index.js';
3
3
  import { extractLinks, extractImages, extractMeta, extractOpenGraph, extractTwitterCard, extractJsonLd, extractForms, extractTables, extractScripts, extractStyles, } from './extractors.js';
4
- let cheerioModule = null;
5
- async function loadCheerio() {
6
- if (cheerioModule) {
7
- return cheerioModule;
8
- }
9
- cheerioModule = await requireOptional('cheerio', 'recker/scrape');
10
- return cheerioModule;
11
- }
12
4
  export class ScrapeDocument {
13
- $;
5
+ rootElement;
14
6
  options;
15
- constructor($, options) {
16
- this.$ = $;
7
+ constructor(root, options) {
8
+ this.rootElement = root;
17
9
  this.options = options || {};
18
10
  }
19
11
  static async create(html, options) {
20
- const { load } = await loadCheerio();
21
- return new ScrapeDocument(load(html), options);
12
+ const root = parse(html);
13
+ return new ScrapeDocument(root, options);
14
+ }
15
+ static createSync(html, options) {
16
+ const root = parse(html);
17
+ return new ScrapeDocument(root, options);
22
18
  }
23
19
  select(selector) {
24
- return new ScrapeElement(this.$(selector), this.$);
20
+ const elements = this.rootElement.querySelectorAll(selector);
21
+ return new ScrapeElement(elements);
25
22
  }
26
23
  selectFirst(selector) {
27
- return new ScrapeElement(this.$(selector).first(), this.$);
24
+ const element = this.rootElement.querySelector(selector);
25
+ return new ScrapeElement(element ? [element] : []);
28
26
  }
29
27
  selectAll(selector) {
30
- const elements = [];
31
- this.$(selector).each((_, element) => {
32
- elements.push(new ScrapeElement(this.$(element), this.$));
33
- });
34
- return elements;
28
+ const elements = this.rootElement.querySelectorAll(selector);
29
+ return elements.map((el) => new ScrapeElement(el));
35
30
  }
36
31
  query(selector) {
37
32
  return this.select(selector);
@@ -40,78 +35,87 @@ export class ScrapeDocument {
40
35
  return this.selectAll(selector);
41
36
  }
42
37
  text(selector) {
43
- return this.$(selector).first().text().trim();
38
+ const el = this.rootElement.querySelector(selector);
39
+ return el ? el.text.trim() : '';
44
40
  }
45
41
  texts(selector) {
46
- const texts = [];
47
- this.$(selector).each((_, element) => {
48
- const text = this.$(element).text().trim();
49
- if (text) {
50
- texts.push(text);
51
- }
52
- });
53
- return texts;
42
+ const elements = this.rootElement.querySelectorAll(selector);
43
+ return elements
44
+ .map((el) => el.text.trim())
45
+ .filter((text) => text.length > 0);
54
46
  }
55
47
  attr(selector, attribute) {
56
- return this.$(selector).first().attr(attribute);
48
+ const el = this.rootElement.querySelector(selector);
49
+ return el ? el.getAttribute(attribute) : undefined;
57
50
  }
58
51
  attrs(selector, attribute) {
52
+ const elements = this.rootElement.querySelectorAll(selector);
59
53
  const attrs = [];
60
- this.$(selector).each((_, element) => {
61
- const value = this.$(element).attr(attribute);
62
- if (value !== undefined) {
63
- attrs.push(value);
54
+ elements.forEach((el) => {
55
+ const val = el.getAttribute(attribute);
56
+ if (val !== undefined) {
57
+ attrs.push(val);
64
58
  }
65
59
  });
66
60
  return attrs;
67
61
  }
68
62
  innerHtml(selector) {
69
- return this.$(selector).first().html();
63
+ const el = this.rootElement.querySelector(selector);
64
+ return el ? el.innerHTML : null;
70
65
  }
71
66
  outerHtml(selector) {
72
- const el = this.$(selector).first();
73
- return this.$.html(el) || '';
67
+ const el = this.rootElement.querySelector(selector);
68
+ return el ? el.outerHTML : '';
74
69
  }
75
70
  links(options) {
76
- return extractLinks(this.$, {
71
+ return extractLinks(this.rootElement, {
77
72
  ...options,
78
73
  baseUrl: this.options.baseUrl,
79
74
  });
80
75
  }
81
76
  images(options) {
82
- return extractImages(this.$, {
77
+ return extractImages(this.rootElement, {
83
78
  ...options,
84
79
  baseUrl: this.options.baseUrl,
85
80
  });
86
81
  }
87
82
  meta() {
88
- return extractMeta(this.$);
83
+ return extractMeta(this.rootElement);
89
84
  }
90
85
  openGraph() {
91
- return extractOpenGraph(this.$);
86
+ return extractOpenGraph(this.rootElement);
92
87
  }
93
88
  twitterCard() {
94
- return extractTwitterCard(this.$);
89
+ return extractTwitterCard(this.rootElement);
95
90
  }
96
91
  jsonLd() {
97
- return extractJsonLd(this.$);
92
+ return extractJsonLd(this.rootElement);
98
93
  }
99
94
  forms(selector) {
100
- return extractForms(this.$, selector);
95
+ return extractForms(this.rootElement, selector);
101
96
  }
102
97
  tables(selector) {
103
- return extractTables(this.$, selector);
98
+ return extractTables(this.rootElement, selector);
104
99
  }
105
100
  scripts() {
106
- return extractScripts(this.$);
101
+ return extractScripts(this.rootElement);
107
102
  }
108
103
  styles() {
109
- return extractStyles(this.$);
104
+ return extractStyles(this.rootElement);
110
105
  }
111
106
  extract(schema) {
112
107
  const result = {};
113
108
  for (const [key, fieldConfig] of Object.entries(schema)) {
114
- result[key] = this.extractField(fieldConfig);
109
+ const value = this.extractField(fieldConfig);
110
+ if (value === undefined) {
111
+ const isOptional = typeof fieldConfig === 'object' && fieldConfig.optional === true;
112
+ if (!isOptional) {
113
+ result[key] = undefined;
114
+ }
115
+ }
116
+ else {
117
+ result[key] = value;
118
+ }
115
119
  }
116
120
  return result;
117
121
  }
@@ -120,77 +124,86 @@ export class ScrapeDocument {
120
124
  return this.text(field) || undefined;
121
125
  }
122
126
  const { selector, attribute, multiple, transform } = field;
127
+ const defaultValue = 'default' in field ? field.default : undefined;
123
128
  if (multiple) {
129
+ const elements = this.rootElement.querySelectorAll(selector);
124
130
  const values = [];
125
- this.$(selector).each((_, element) => {
126
- const $el = this.$(element);
131
+ elements.forEach(el => {
127
132
  let value;
128
133
  if (attribute) {
129
- value = $el.attr(attribute) || '';
134
+ value = el.getAttribute(attribute) || '';
130
135
  }
131
136
  else {
132
- value = $el.text().trim();
137
+ value = el.text.trim();
133
138
  }
134
139
  if (value) {
135
140
  values.push(transform ? transform(value) : value);
136
141
  }
137
142
  });
143
+ if (values.length === 0 && defaultValue !== undefined) {
144
+ return defaultValue;
145
+ }
138
146
  return values;
139
147
  }
140
148
  else {
141
- const $el = this.$(selector).first();
149
+ const el = this.rootElement.querySelector(selector);
150
+ if (!el) {
151
+ return defaultValue;
152
+ }
142
153
  let value;
143
154
  if (attribute) {
144
- value = $el.attr(attribute) || '';
155
+ value = el.getAttribute(attribute) || '';
145
156
  }
146
157
  else {
147
- value = $el.text().trim();
158
+ value = el.text.trim();
159
+ }
160
+ if (!value) {
161
+ return defaultValue;
148
162
  }
149
- if (!value)
150
- return undefined;
151
163
  return transform ? transform(value) : value;
152
164
  }
153
165
  }
154
166
  title() {
155
- const title = this.$('title').first().text().trim();
167
+ const el = this.rootElement.querySelector('title');
168
+ const title = el ? el.text.trim() : '';
156
169
  return title || undefined;
157
170
  }
158
171
  body() {
159
- return new ScrapeElement(this.$('body').first(), this.$);
172
+ const el = this.rootElement.querySelector('body');
173
+ return new ScrapeElement(el ? [el] : []);
160
174
  }
161
175
  head() {
162
- return new ScrapeElement(this.$('head').first(), this.$);
176
+ const el = this.rootElement.querySelector('head');
177
+ return new ScrapeElement(el ? [el] : []);
163
178
  }
164
179
  html() {
165
- return this.$.html() || '';
180
+ return this.rootElement.outerHTML;
166
181
  }
167
182
  root() {
168
- return new ScrapeElement(this.$.root(), this.$);
183
+ return new ScrapeElement(this.rootElement);
169
184
  }
170
185
  exists(selector) {
171
- return this.$(selector).length > 0;
186
+ return this.rootElement.querySelector(selector) !== null;
172
187
  }
173
188
  count(selector) {
174
- return this.$(selector).length;
189
+ return this.rootElement.querySelectorAll(selector).length;
175
190
  }
176
191
  findByText(text, selector) {
177
- const baseSelector = selector || '*';
178
192
  const elements = [];
179
- this.$(baseSelector).each((_, element) => {
180
- const $el = this.$(element);
181
- if ($el.text().includes(text)) {
182
- elements.push(new ScrapeElement($el, this.$));
193
+ const candidates = selector ? this.rootElement.querySelectorAll(selector) : this.rootElement.querySelectorAll('*');
194
+ candidates.forEach(el => {
195
+ if (el.text.includes(text)) {
196
+ elements.push(new ScrapeElement(el));
183
197
  }
184
198
  });
185
199
  return elements;
186
200
  }
187
201
  findByExactText(text, selector) {
188
- const baseSelector = selector || '*';
189
202
  const elements = [];
190
- this.$(baseSelector).each((_, element) => {
191
- const $el = this.$(element);
192
- if ($el.text().trim() === text) {
193
- elements.push(new ScrapeElement($el, this.$));
203
+ const candidates = selector ? this.rootElement.querySelectorAll(selector) : this.rootElement.querySelectorAll('*');
204
+ candidates.forEach(el => {
205
+ if (el.text.trim() === text) {
206
+ elements.push(new ScrapeElement(el));
194
207
  }
195
208
  });
196
209
  return elements;
@@ -202,7 +215,7 @@ export class ScrapeDocument {
202
215
  return this.selectAll(selector);
203
216
  }
204
217
  get raw() {
205
- return this.$;
218
+ return this.rootElement;
206
219
  }
207
220
  get baseUrl() {
208
221
  return this.options.baseUrl;
@@ -1,9 +1,7 @@
1
- import type { Cheerio, CheerioAPI } from 'cheerio';
2
- import type { Element } from 'domhandler';
1
+ import { HTMLElement, Node } from './parser/index.js';
3
2
  export declare class ScrapeElement {
4
- private $el;
5
- private $;
6
- constructor($el: Cheerio<Element>, $: CheerioAPI);
3
+ private elements;
4
+ constructor(elements: HTMLElement | HTMLElement[] | Node | Node[]);
7
5
  find(selector: string): ScrapeElement;
8
6
  parent(selector?: string): ScrapeElement;
9
7
  children(selector?: string): ScrapeElement;
@@ -16,11 +14,15 @@ export declare class ScrapeElement {
16
14
  first(): ScrapeElement;
17
15
  last(): ScrapeElement;
18
16
  eq(index: number): ScrapeElement;
19
- filter(selector: string): ScrapeElement;
17
+ filter(selectorOrCallback: string | ((el: ScrapeElement, index: number) => boolean)): ScrapeElement;
20
18
  not(selector: string): ScrapeElement;
21
19
  has(selector: string): ScrapeElement;
22
20
  add(selector: string): ScrapeElement;
23
21
  parents(selector?: string): ScrapeElement;
22
+ parentsUntil(selector: string): ScrapeElement;
23
+ nextUntil(selector: string): ScrapeElement;
24
+ prevUntil(selector: string): ScrapeElement;
25
+ slice(start: number, end?: number): ScrapeElement;
24
26
  contents(): ScrapeElement;
25
27
  text(): string;
26
28
  html(): string | null;
@@ -44,6 +46,6 @@ export declare class ScrapeElement {
44
46
  tagName(): string | undefined;
45
47
  clone(): ScrapeElement;
46
48
  toString(): string;
47
- get raw(): Cheerio<Element>;
48
- get(index?: number): Element | undefined;
49
+ get raw(): HTMLElement[];
50
+ get(index?: number): HTMLElement | undefined;
49
51
  }