@crawlee/cheerio 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.
@@ -112,7 +112,9 @@ class CheerioCrawler extends http_1.HttpCrawler {
112
112
  body,
113
113
  enqueueLinks: async (enqueueOptions) => {
114
114
  return cheerioCrawlerEnqueueLinks({
115
- options: { ...enqueueOptions, limit: this.calculateEnqueuedRequestLimit(enqueueOptions?.limit) },
115
+ // `originalEnqueueLinks` clamps `limit` by the remaining `maxRequestsPerCrawl` budget itself;
116
+ // pre-clamping it here would make the crawler log the internal limit as a user-provided one
117
+ options: enqueueOptions,
116
118
  $,
117
119
  requestQueue: await this.getRequestQueue(),
118
120
  robotsTxtFile: await this.getRobotsTxtFileForUrl(crawlingContext.request.url),
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@crawlee/cheerio",
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"
@@ -53,9 +53,9 @@
53
53
  "access": "public"
54
54
  },
55
55
  "dependencies": {
56
- "@crawlee/http": "3.17.1-beta.79",
57
- "@crawlee/types": "3.17.1-beta.79",
58
- "@crawlee/utils": "3.17.1-beta.79",
56
+ "@crawlee/http": "3.17.1-beta.80",
57
+ "@crawlee/types": "3.17.1-beta.80",
58
+ "@crawlee/utils": "3.17.1-beta.80",
59
59
  "cheerio": "1.0.0-rc.12",
60
60
  "htmlparser2": "^9.0.0",
61
61
  "tslib": "^2.4.0"
@@ -67,5 +67,5 @@
67
67
  }
68
68
  }
69
69
  },
70
- "gitHead": "267c92b57f2cc05380a2d8e0323fe9f1ee35b142"
70
+ "gitHead": "5b3c2d52f128643de6f515e87eeb531d55a187f0"
71
71
  }