@crawlee/utils 4.0.0-beta.280 → 4.0.0-beta.282

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.
@@ -3,12 +3,12 @@ import { setTimeout } from 'node:timers/promises';
3
3
  * Default regular expression to match URLs in a string that may be plain text, JSON, CSV or other. It supports common URL characters
4
4
  * and does not support URLs containing commas or spaces. The URLs also may contain Unicode letters (not symbols).
5
5
  */
6
- export const URL_NO_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}0-9@:%._+~#=]{0,254}[\p{L}0-9])\.[a-z]{2,63}(:\d{1,5})?(\/[-\p{L}0-9@:%_+.~#?&/=()'*]*)?/giu;
6
+ export const URL_NO_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}\p{M}0-9@:%._+~#=]{0,254}[\p{L}\p{M}0-9])\.(xn--[a-z0-9-]{1,59}|[a-z]{2,63}|[\p{L}\p{M}]{2,63})(:\d{1,5})?(\/[-\p{L}\p{M}0-9@:%_+.~#?&/=()'*]*)?/giu;
7
7
  /**
8
8
  * Regular expression that, in addition to the default regular expression `URL_NO_COMMAS_REGEX`, supports matching commas in URL path and query.
9
9
  * Note, however, that this may prevent parsing URLs from comma delimited lists, or the URLs may become malformed.
10
10
  */
11
- export const URL_WITH_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}0-9@:%._+~#=]{0,254}[\p{L}0-9])\.[a-z]{2,63}(:\d{1,5})?(\/[-\p{L}0-9@:%_+,.~#?&/=()'*]*)?/giu;
11
+ export const URL_WITH_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}\p{M}0-9@:%._+~#=]{0,254}[\p{L}\p{M}0-9])\.(xn--[a-z0-9-]{1,59}|[a-z]{2,63}|[\p{L}\p{M}]{2,63})(:\d{1,5})?(\/[-\p{L}\p{M}0-9@:%_+,.~#?&/=()'*]*)?/giu;
12
12
  /**
13
13
  * Returns a `Promise` that resolves after a specific period of time. This is useful to implement waiting
14
14
  * in your code, e.g. to prevent overloading of target website or to avoid bot detection.
@@ -239,6 +239,10 @@ export async function* parseSitemap(initialSources, proxyUrl, options) {
239
239
  // URL entries dropped by the enqueue strategy filter, reported in one warning per sitemap after
240
240
  // the loop (per-entry warnings could flood the log; individual drops are logged at debug level).
241
241
  let droppedUrlEntries = 0;
242
+ // The same for every entry of this source, so compute it once.
243
+ const originSitemapUrl = source.type === 'url'
244
+ ? source.url
245
+ : `raw://${createHash('sha256').update(source.content).digest('base64')}`;
242
246
  const iterator = items[Symbol.asyncIterator]();
243
247
  try {
244
248
  while (true) {
@@ -288,9 +292,7 @@ export async function* parseSitemap(initialSources, proxyUrl, options) {
288
292
  }
289
293
  yield {
290
294
  ...item,
291
- originSitemapUrl: source.type === 'url'
292
- ? source.url
293
- : `raw://${createHash('sha256').update(source.content).digest('base64')}`,
295
+ originSitemapUrl,
294
296
  };
295
297
  }
296
298
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@crawlee/utils",
3
- "version": "4.0.0-beta.280",
3
+ "version": "4.0.0-beta.282",
4
4
  "description": "A set of shared utilities that can be used by crawlers",
5
5
  "engines": {
6
6
  "node": ">=22.13.0"
@@ -43,8 +43,8 @@
43
43
  },
44
44
  "dependencies": {
45
45
  "@apify/validations": "^1.1.4",
46
- "@crawlee/http-client": "4.0.0-beta.280",
47
- "@crawlee/types": "4.0.0-beta.280",
46
+ "@crawlee/http-client": "4.0.0-beta.282",
47
+ "@crawlee/types": "4.0.0-beta.282",
48
48
  "@types/sax": "^1.2.7",
49
49
  "cheerio": "^1.2.0",
50
50
  "domhandler": "^6.0.1",
@@ -63,5 +63,5 @@
63
63
  }
64
64
  }
65
65
  },
66
- "gitHead": "8c8d5e57a8015e3147dbe4e50843d924e63f4212"
66
+ "gitHead": "3fa4c0e74481d10cb0c8807a9d50735da9a367a5"
67
67
  }