@crawlee/core 4.0.0-beta.4 → 4.0.0-beta.40

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 (171) hide show
  1. package/README.md +9 -5
  2. package/autoscaling/autoscaled_pool.d.ts +3 -5
  3. package/autoscaling/autoscaled_pool.d.ts.map +1 -1
  4. package/autoscaling/autoscaled_pool.js +3 -9
  5. package/autoscaling/autoscaled_pool.js.map +1 -1
  6. package/autoscaling/snapshotter.d.ts +3 -13
  7. package/autoscaling/snapshotter.d.ts.map +1 -1
  8. package/autoscaling/snapshotter.js +15 -29
  9. package/autoscaling/snapshotter.js.map +1 -1
  10. package/autoscaling/system_status.d.ts +0 -3
  11. package/autoscaling/system_status.d.ts.map +1 -1
  12. package/autoscaling/system_status.js +2 -3
  13. package/autoscaling/system_status.js.map +1 -1
  14. package/configuration.d.ts +5 -78
  15. package/configuration.d.ts.map +1 -1
  16. package/configuration.js +6 -102
  17. package/configuration.js.map +1 -1
  18. package/cookie_utils.d.ts +1 -1
  19. package/cookie_utils.d.ts.map +1 -1
  20. package/cookie_utils.js +8 -8
  21. package/cookie_utils.js.map +1 -1
  22. package/crawlers/context_pipeline.d.ts +71 -0
  23. package/crawlers/context_pipeline.d.ts.map +1 -0
  24. package/crawlers/context_pipeline.js +121 -0
  25. package/crawlers/context_pipeline.js.map +1 -0
  26. package/crawlers/crawler_commons.d.ts +15 -23
  27. package/crawlers/crawler_commons.d.ts.map +1 -1
  28. package/crawlers/crawler_commons.js +0 -8
  29. package/crawlers/crawler_commons.js.map +1 -1
  30. package/crawlers/error_snapshotter.d.ts +3 -2
  31. package/crawlers/error_snapshotter.d.ts.map +1 -1
  32. package/crawlers/error_snapshotter.js +2 -2
  33. package/crawlers/error_snapshotter.js.map +1 -1
  34. package/crawlers/error_tracker.d.ts +2 -1
  35. package/crawlers/error_tracker.d.ts.map +1 -1
  36. package/crawlers/error_tracker.js.map +1 -1
  37. package/crawlers/index.d.ts +1 -1
  38. package/crawlers/index.d.ts.map +1 -1
  39. package/crawlers/index.js +1 -1
  40. package/crawlers/index.js.map +1 -1
  41. package/crawlers/internals/types.d.ts +8 -0
  42. package/crawlers/internals/types.d.ts.map +1 -0
  43. package/crawlers/internals/types.js +2 -0
  44. package/crawlers/internals/types.js.map +1 -0
  45. package/crawlers/statistics.d.ts +15 -15
  46. package/crawlers/statistics.d.ts.map +1 -1
  47. package/crawlers/statistics.js +21 -18
  48. package/crawlers/statistics.js.map +1 -1
  49. package/enqueue_links/enqueue_links.d.ts +30 -18
  50. package/enqueue_links/enqueue_links.d.ts.map +1 -1
  51. package/enqueue_links/enqueue_links.js +41 -23
  52. package/enqueue_links/enqueue_links.js.map +1 -1
  53. package/enqueue_links/shared.d.ts +24 -7
  54. package/enqueue_links/shared.d.ts.map +1 -1
  55. package/enqueue_links/shared.js +66 -37
  56. package/enqueue_links/shared.js.map +1 -1
  57. package/errors.d.ts +18 -0
  58. package/errors.d.ts.map +1 -1
  59. package/errors.js +35 -0
  60. package/errors.js.map +1 -1
  61. package/events/event_manager.d.ts +8 -5
  62. package/events/event_manager.d.ts.map +1 -1
  63. package/events/event_manager.js +7 -9
  64. package/events/event_manager.js.map +1 -1
  65. package/events/local_event_manager.d.ts +14 -4
  66. package/events/local_event_manager.d.ts.map +1 -1
  67. package/events/local_event_manager.js +27 -39
  68. package/events/local_event_manager.js.map +1 -1
  69. package/index.d.ts +2 -1
  70. package/index.d.ts.map +1 -1
  71. package/index.js +2 -1
  72. package/index.js.map +1 -1
  73. package/log.d.ts +146 -2
  74. package/log.d.ts.map +1 -1
  75. package/log.js +102 -0
  76. package/log.js.map +1 -1
  77. package/package.json +6 -7
  78. package/proxy_configuration.d.ts +17 -94
  79. package/proxy_configuration.d.ts.map +1 -1
  80. package/proxy_configuration.js +18 -54
  81. package/proxy_configuration.js.map +1 -1
  82. package/recoverable_state.d.ts +121 -0
  83. package/recoverable_state.d.ts.map +1 -0
  84. package/recoverable_state.js +137 -0
  85. package/recoverable_state.js.map +1 -0
  86. package/request.d.ts +48 -6
  87. package/request.d.ts.map +1 -1
  88. package/request.js +62 -16
  89. package/request.js.map +1 -1
  90. package/service_locator.d.ts +130 -0
  91. package/service_locator.d.ts.map +1 -0
  92. package/service_locator.js +249 -0
  93. package/service_locator.js.map +1 -0
  94. package/session_pool/session.d.ts +9 -31
  95. package/session_pool/session.d.ts.map +1 -1
  96. package/session_pool/session.js +17 -21
  97. package/session_pool/session.js.map +1 -1
  98. package/session_pool/session_pool.d.ts +27 -54
  99. package/session_pool/session_pool.d.ts.map +1 -1
  100. package/session_pool/session_pool.js +54 -69
  101. package/session_pool/session_pool.js.map +1 -1
  102. package/storages/dataset.d.ts +53 -3
  103. package/storages/dataset.d.ts.map +1 -1
  104. package/storages/dataset.js +78 -6
  105. package/storages/dataset.js.map +1 -1
  106. package/storages/index.d.ts +2 -0
  107. package/storages/index.d.ts.map +1 -1
  108. package/storages/index.js +2 -0
  109. package/storages/index.js.map +1 -1
  110. package/storages/key_value_store.d.ts +71 -1
  111. package/storages/key_value_store.d.ts.map +1 -1
  112. package/storages/key_value_store.js +95 -12
  113. package/storages/key_value_store.js.map +1 -1
  114. package/storages/request_list.d.ts +9 -9
  115. package/storages/request_list.d.ts.map +1 -1
  116. package/storages/request_list.js +11 -8
  117. package/storages/request_list.js.map +1 -1
  118. package/storages/request_list_adapter.d.ts +58 -0
  119. package/storages/request_list_adapter.d.ts.map +1 -0
  120. package/storages/request_list_adapter.js +81 -0
  121. package/storages/request_list_adapter.js.map +1 -0
  122. package/storages/request_manager_tandem.d.ts +68 -0
  123. package/storages/request_manager_tandem.d.ts.map +1 -0
  124. package/storages/request_manager_tandem.js +124 -0
  125. package/storages/request_manager_tandem.js.map +1 -0
  126. package/storages/request_provider.d.ts +76 -9
  127. package/storages/request_provider.d.ts.map +1 -1
  128. package/storages/request_provider.js +92 -54
  129. package/storages/request_provider.js.map +1 -1
  130. package/storages/request_queue.d.ts +1 -3
  131. package/storages/request_queue.d.ts.map +1 -1
  132. package/storages/request_queue.js +2 -4
  133. package/storages/request_queue.js.map +1 -1
  134. package/storages/request_queue_v2.d.ts +3 -3
  135. package/storages/request_queue_v2.d.ts.map +1 -1
  136. package/storages/request_queue_v2.js +4 -5
  137. package/storages/request_queue_v2.js.map +1 -1
  138. package/storages/sitemap_request_list.d.ts +5 -5
  139. package/storages/sitemap_request_list.d.ts.map +1 -1
  140. package/storages/sitemap_request_list.js +8 -7
  141. package/storages/sitemap_request_list.js.map +1 -1
  142. package/storages/storage_manager.d.ts +10 -8
  143. package/storages/storage_manager.d.ts.map +1 -1
  144. package/storages/storage_manager.js +12 -22
  145. package/storages/storage_manager.js.map +1 -1
  146. package/storages/utils.d.ts.map +1 -1
  147. package/storages/utils.js +4 -3
  148. package/storages/utils.js.map +1 -1
  149. package/typedefs.d.ts +1 -1
  150. package/typedefs.d.ts.map +1 -1
  151. package/crawlers/crawler_extension.d.ts +0 -12
  152. package/crawlers/crawler_extension.d.ts.map +0 -1
  153. package/crawlers/crawler_extension.js +0 -14
  154. package/crawlers/crawler_extension.js.map +0 -1
  155. package/http_clients/base-http-client.d.ts +0 -134
  156. package/http_clients/base-http-client.d.ts.map +0 -1
  157. package/http_clients/base-http-client.js +0 -33
  158. package/http_clients/base-http-client.js.map +0 -1
  159. package/http_clients/form-data-like.d.ts +0 -67
  160. package/http_clients/form-data-like.d.ts.map +0 -1
  161. package/http_clients/form-data-like.js +0 -5
  162. package/http_clients/form-data-like.js.map +0 -1
  163. package/http_clients/got-scraping-http-client.d.ts +0 -15
  164. package/http_clients/got-scraping-http-client.d.ts.map +0 -1
  165. package/http_clients/got-scraping-http-client.js +0 -69
  166. package/http_clients/got-scraping-http-client.js.map +0 -1
  167. package/http_clients/index.d.ts +0 -3
  168. package/http_clients/index.d.ts.map +0 -1
  169. package/http_clients/index.js +0 -3
  170. package/http_clients/index.js.map +0 -1
  171. package/tsconfig.build.tsbuildinfo +0 -1
@@ -1 +0,0 @@
1
- {"version":3,"file":"form-data-like.d.ts","sourceRoot":"","sources":["../../src/http_clients/form-data-like.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,UAAU,QAAQ;IACd;;OAEG;IACH,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB;;OAEG;IACH,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB;;OAEG;IACH,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB;;OAEG;IACH,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;IAC9B;;OAEG;IACH,MAAM,IAAI,cAAc,CAAC,UAAU,CAAC,GAAG,aAAa,CAAC,UAAU,CAAC,CAAC;IACjE,QAAQ,CAAC,CAAC,MAAM,CAAC,WAAW,CAAC,CAAC,EAAE,MAAM,CAAC;CAC1C;AAED;;GAEG;AACH,KAAK,kBAAkB,GAAG,MAAM,GAAG,QAAQ,CAAC;AAC5C;;GAEG;AACH,MAAM,WAAW,YAAY;IACzB;;;;;;;;;;OAUG;IACH,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9D;;;;;;OAMG;IACH,MAAM,CAAC,IAAI,EAAE,MAAM,GAAG,kBAAkB,EAAE,CAAC;IAC3C;;;OAGG;IACH,OAAO,IAAI,gBAAgB,CAAC,CAAC,MAAM,EAAE,kBAAkB,CAAC,CAAC,CAAC;IAC1D;;OAEG;IACH,CAAC,MAAM,CAAC,QAAQ,CAAC,IAAI,gBAAgB,CAAC,CAAC,MAAM,EAAE,kBAAkB,CAAC,CAAC,CAAC;IACpE,QAAQ,CAAC,CAAC,MAAM,CAAC,WAAW,CAAC,CAAC,EAAE,MAAM,CAAC;CAC1C"}
@@ -1,5 +0,0 @@
1
- /**
2
- * This is copied from https://github.com/octet-stream/form-data-encoder
3
- */
4
- export {};
5
- //# sourceMappingURL=form-data-like.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"form-data-like.js","sourceRoot":"","sources":["../../src/http_clients/form-data-like.ts"],"names":[],"mappings":"AAAA;;GAEG"}
@@ -1,15 +0,0 @@
1
- import type { BaseHttpClient, HttpRequest, HttpResponse, RedirectHandler, ResponseTypes, StreamingHttpResponse } from './base-http-client.js';
2
- /**
3
- * A HTTP client implementation based on the `got-scraping` library.
4
- */
5
- export declare class GotScrapingHttpClient implements BaseHttpClient {
6
- /**
7
- * @inheritDoc
8
- */
9
- sendRequest<TResponseType extends keyof ResponseTypes>(request: HttpRequest<TResponseType>): Promise<HttpResponse<TResponseType>>;
10
- /**
11
- * @inheritDoc
12
- */
13
- stream(request: HttpRequest, handleRedirect?: RedirectHandler): Promise<StreamingHttpResponse>;
14
- }
15
- //# sourceMappingURL=got-scraping-http-client.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"got-scraping-http-client.d.ts","sourceRoot":"","sources":["../../src/http_clients/got-scraping-http-client.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EACR,cAAc,EACd,WAAW,EACX,YAAY,EACZ,eAAe,EACf,aAAa,EACb,qBAAqB,EACxB,MAAM,uBAAuB,CAAC;AAE/B;;GAEG;AACH,qBAAa,qBAAsB,YAAW,cAAc;IACxD;;OAEG;IACG,WAAW,CAAC,aAAa,SAAS,MAAM,aAAa,EACvD,OAAO,EAAE,WAAW,CAAC,aAAa,CAAC,GACpC,OAAO,CAAC,YAAY,CAAC,aAAa,CAAC,CAAC;IAgBvC;;OAEG;IACG,MAAM,CAAC,OAAO,EAAE,WAAW,EAAE,cAAc,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,qBAAqB,CAAC;CAmDvG"}
@@ -1,69 +0,0 @@
1
- import { gotScraping } from 'got-scraping';
2
- /**
3
- * A HTTP client implementation based on the `got-scraping` library.
4
- */
5
- export class GotScrapingHttpClient {
6
- /**
7
- * @inheritDoc
8
- */
9
- async sendRequest(request) {
10
- const gotResult = await gotScraping({
11
- ...request,
12
- retry: {
13
- limit: 0,
14
- ...request.retry,
15
- },
16
- });
17
- return {
18
- ...gotResult,
19
- body: gotResult.body,
20
- request: { url: request.url, ...gotResult.request },
21
- };
22
- }
23
- /**
24
- * @inheritDoc
25
- */
26
- async stream(request, handleRedirect) {
27
- // eslint-disable-next-line no-async-promise-executor
28
- return new Promise(async (resolve, reject) => {
29
- const stream = gotScraping({ ...request, isStream: true });
30
- stream.on('redirect', (updatedOptions, redirectResponse) => {
31
- handleRedirect?.(redirectResponse, updatedOptions);
32
- });
33
- // We need to end the stream for DELETE requests, otherwise it will hang.
34
- if (request.method && ['DELETE', 'delete'].includes(request.method)) {
35
- stream.end();
36
- }
37
- stream.on('error', reject);
38
- stream.on('response', (response) => {
39
- const result = {
40
- stream,
41
- request,
42
- redirectUrls: response.redirectUrls,
43
- url: response.url,
44
- ip: response.ip,
45
- statusCode: response.statusCode,
46
- headers: response.headers,
47
- trailers: response.trailers,
48
- complete: response.complete,
49
- get downloadProgress() {
50
- return stream.downloadProgress;
51
- },
52
- get uploadProgress() {
53
- return stream.uploadProgress;
54
- },
55
- };
56
- Object.assign(result, response); // TODO BC - remove in 4.0
57
- resolve(result);
58
- stream.on('end', () => {
59
- result.complete = response.complete;
60
- result.trailers ??= {};
61
- Object.assign(result.trailers, response.trailers);
62
- result.rawTrailers ??= []; // TODO BC - remove in 4.0
63
- Object.assign(result.rawTrailers, response.rawTrailers);
64
- });
65
- });
66
- });
67
- }
68
- }
69
- //# sourceMappingURL=got-scraping-http-client.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"got-scraping-http-client.js","sourceRoot":"","sources":["../../src/http_clients/got-scraping-http-client.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,WAAW,EAAE,MAAM,cAAc,CAAC;AAW3C;;GAEG;AACH,MAAM,OAAO,qBAAqB;IAC9B;;OAEG;IACH,KAAK,CAAC,WAAW,CACb,OAAmC;QAEnC,MAAM,SAAS,GAAG,MAAM,WAAW,CAAC;YAChC,GAAG,OAAO;YACV,KAAK,EAAE;gBACH,KAAK,EAAE,CAAC;gBACR,GAAI,OAAO,CAAC,KAA6C;aAC5D;SACJ,CAAC,CAAC;QAEH,OAAO;YACH,GAAG,SAAS;YACZ,IAAI,EAAE,SAAS,CAAC,IAAoC;YACpD,OAAO,EAAE,EAAE,GAAG,EAAE,OAAO,CAAC,GAAG,EAAE,GAAG,SAAS,CAAC,OAAO,EAAE;SACtD,CAAC;IACN,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,MAAM,CAAC,OAAoB,EAAE,cAAgC;QAC/D,qDAAqD;QACrD,OAAO,IAAI,OAAO,CAAC,KAAK,EAAE,OAAO,EAAE,MAAM,EAAE,EAAE;YACzC,MAAM,MAAM,GAAG,WAAW,CAAC,EAAE,GAAG,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;YAE3D,MAAM,CAAC,EAAE,CAAC,UAAU,EAAE,CAAC,cAAuB,EAAE,gBAA+B,EAAE,EAAE;gBAC/E,cAAc,EAAE,CAAC,gBAAgB,EAAE,cAAc,CAAC,CAAC;YACvD,CAAC,CAAC,CAAC;YAEH,yEAAyE;YACzE,IAAI,OAAO,CAAC,MAAM,IAAI,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,QAAQ,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC;gBAClE,MAAM,CAAC,GAAG,EAAE,CAAC;YACjB,CAAC;YAED,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;YAE3B,MAAM,CAAC,EAAE,CAAC,UAAU,EAAE,CAAC,QAAuB,EAAE,EAAE;gBAC9C,MAAM,MAAM,GAA0B;oBAClC,MAAM;oBACN,OAAO;oBACP,YAAY,EAAE,QAAQ,CAAC,YAAY;oBACnC,GAAG,EAAE,QAAQ,CAAC,GAAG;oBACjB,EAAE,EAAE,QAAQ,CAAC,EAAE;oBACf,UAAU,EAAE,QAAQ,CAAC,UAAU;oBAC/B,OAAO,EAAE,QAAQ,CAAC,OAAO;oBACzB,QAAQ,EAAE,QAAQ,CAAC,QAAQ;oBAC3B,QAAQ,EAAE,QAAQ,CAAC,QAAQ;oBAC3B,IAAI,gBAAgB;wBAChB,OAAO,MAAM,CAAC,gBAAgB,CAAC;oBACnC,CAAC;oBACD,IAAI,cAAc;wBACd,OAAO,MAAM,CAAC,cAAc,CAAC;oBACjC,CAAC;iBACJ,CAAC;gBAEF,MAAM,CAAC,MAAM,CAAC,MAAM,EAAE,QAAQ,CAAC,CAAC,CAAC,0BAA0B;gBAE3D,OAAO,CAAC,MAAM,CAAC,CAAC;gBAEhB,MAAM,CAAC,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE;oBAClB,MAAM,CAAC,QAAQ,GAAG,QAAQ,CAAC,QAAQ,CAAC;oBAEpC,MAAM,CAAC,QAAQ,KAAK,EAAE,CAAC;oBACvB,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,QAAQ,EAAE,QAAQ,CAAC,QAAQ,CAAC,CAAC;oBAEjD,MAAc,CAAC,WAAW,KAAK,EAAE,CAAC,CAAC,0BAA0B;oBAC9D,MAAM,CAAC,MAAM,CAAE,MAAc,CAAC,WAAW,EAAE,QAAQ,CAAC,WAAW,CAAC,CAAC;gBACrE,CAAC,CAAC,CAAC;YACP,CAAC,CAAC,CAAC;QACP,CAAC,CAAC,CAAC;IACP,CAAC;CACJ"}
@@ -1,3 +0,0 @@
1
- export * from './base-http-client.js';
2
- export * from './got-scraping-http-client.js';
3
- //# sourceMappingURL=index.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/http_clients/index.ts"],"names":[],"mappings":"AAAA,cAAc,uBAAuB,CAAC;AACtC,cAAc,+BAA+B,CAAC"}
@@ -1,3 +0,0 @@
1
- export * from './base-http-client.js';
2
- export * from './got-scraping-http-client.js';
3
- //# sourceMappingURL=index.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/http_clients/index.ts"],"names":[],"mappings":"AAAA,cAAc,uBAAuB,CAAC;AACtC,cAAc,+BAA+B,CAAC"}