@crawlee/core 3.17.1-beta.79 → 3.17.1-beta.80

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.
@@ -6,7 +6,11 @@ import type { AddRequestsBatchedOptions, AddRequestsBatchedResult, RequestProvid
6
6
  import type { GlobInput, PseudoUrlInput, RegExpInput, RequestTransform, SkippedRequestCallback } from './shared';
7
7
  export { EnqueueStrategy };
8
8
  export interface EnqueueLinksOptions extends RequestQueueOperationOptions {
9
- /** Limit the amount of actually enqueued URLs to this number. Useful for testing across the entire crawling scope. */
9
+ /**
10
+ * Limit the amount of actually enqueued URLs to this number. Useful for testing across the entire crawling scope.
11
+ * When called from a crawler context, the limit is further capped by what's left of the crawler's
12
+ * {@link BasicCrawlerOptions.maxRequestsPerCrawl|`maxRequestsPerCrawl`} budget.
13
+ */
10
14
  limit?: number;
11
15
  /** An array of URLs to enqueue. */
12
16
  urls?: readonly string[];
@@ -154,6 +158,9 @@ export interface EnqueueLinksOptions extends RequestQueueOperationOptions {
154
158
  * 1. based on robots.txt file,
155
159
  * 2. because they don't match enqueueLinks filters,
156
160
  * 3. or because the maxRequestsPerCrawl limit has been reached
161
+ *
162
+ * When calling `enqueueLinks` through a crawler context, this callback runs in addition to (after) the
163
+ * crawler-level `onSkippedRequest`, it does not replace it.
157
164
  */
158
165
  onSkippedRequest?: SkippedRequestCallback;
159
166
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@crawlee/core",
3
- "version": "3.17.1-beta.79",
3
+ "version": "3.17.1-beta.80",
4
4
  "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.",
5
5
  "engines": {
6
6
  "node": ">=16.0.0"
@@ -59,9 +59,9 @@
59
59
  "@apify/pseudo_url": "^2.0.30",
60
60
  "@apify/timeout": "^0.4.0",
61
61
  "@apify/utilities": "^2.7.10",
62
- "@crawlee/memory-storage": "3.17.1-beta.79",
63
- "@crawlee/types": "3.17.1-beta.79",
64
- "@crawlee/utils": "3.17.1-beta.79",
62
+ "@crawlee/memory-storage": "3.17.1-beta.80",
63
+ "@crawlee/types": "3.17.1-beta.80",
64
+ "@crawlee/utils": "3.17.1-beta.80",
65
65
  "@sapphire/async-queue": "^1.5.1",
66
66
  "@standard-schema/spec": "^1.0.0",
67
67
  "@vladfrangu/async_event_emitter": "^2.2.2",
@@ -84,5 +84,5 @@
84
84
  }
85
85
  }
86
86
  },
87
- "gitHead": "267c92b57f2cc05380a2d8e0323fe9f1ee35b142"
87
+ "gitHead": "5b3c2d52f128643de6f515e87eeb531d55a187f0"
88
88
  }