@crawlee/core 4.0.0-beta.110 → 4.0.0-beta.111
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.
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import type { Awaitable } from '@crawlee/types';
|
|
2
2
|
import type { RequestOptions } from '../request.js';
|
|
3
3
|
import type { EnqueueLinksOptions } from './enqueue_links.js';
|
|
4
|
-
export { tryAbsoluteURL } from '@crawlee/utils';
|
|
4
|
+
export { tryAbsoluteURL } from '@crawlee/utils/internal';
|
|
5
5
|
export interface UrlPatternObject {
|
|
6
6
|
glob?: string;
|
|
7
7
|
regexp?: RegExp;
|
package/enqueue_links/shared.js
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { URL } from 'node:url';
|
|
2
2
|
import { Minimatch } from 'minimatch';
|
|
3
|
-
export { tryAbsoluteURL } from '@crawlee/utils';
|
|
3
|
+
export { tryAbsoluteURL } from '@crawlee/utils/internal';
|
|
4
4
|
const MAX_ENQUEUE_LINKS_CACHE_SIZE = 1000;
|
|
5
5
|
/**
|
|
6
6
|
* To keep high performance when the same patterns are passed on every `enqueueLinks()` call,
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@crawlee/core",
|
|
3
|
-
"version": "4.0.0-beta.
|
|
3
|
+
"version": "4.0.0-beta.111",
|
|
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": ">=22.0.0"
|
|
@@ -52,9 +52,9 @@
|
|
|
52
52
|
"@apify/log": "^2.5.18",
|
|
53
53
|
"@apify/timeout": "^0.4.4",
|
|
54
54
|
"@apify/utilities": "^2.15.5",
|
|
55
|
-
"@crawlee/fs-storage": "4.0.0-beta.
|
|
56
|
-
"@crawlee/types": "4.0.0-beta.
|
|
57
|
-
"@crawlee/utils": "4.0.0-beta.
|
|
55
|
+
"@crawlee/fs-storage": "4.0.0-beta.111",
|
|
56
|
+
"@crawlee/types": "4.0.0-beta.111",
|
|
57
|
+
"@crawlee/utils": "4.0.0-beta.111",
|
|
58
58
|
"@sapphire/async-queue": "^1.5.5",
|
|
59
59
|
"@sapphire/shapeshift": "^4.0.0",
|
|
60
60
|
"@vladfrangu/async_event_emitter": "^2.4.6",
|
|
@@ -78,5 +78,5 @@
|
|
|
78
78
|
}
|
|
79
79
|
}
|
|
80
80
|
},
|
|
81
|
-
"gitHead": "
|
|
81
|
+
"gitHead": "a6b7dec651fa7d81c61689e0a3cd0a8d06fdb586"
|
|
82
82
|
}
|
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
import { inspect } from 'node:util';
|
|
2
|
-
import {
|
|
2
|
+
import { isAsyncIterable, isIterable } from '@crawlee/utils/internal';
|
|
3
|
+
import { downloadListOfUrls, sleep } from '@crawlee/utils';
|
|
3
4
|
import ow from 'ow';
|
|
4
5
|
import { LruCache } from '@apify/datastructures';
|
|
5
6
|
import { tryCancel } from '@apify/timeout';
|