@crawlbrulee/sdk 0.7.1 → 0.8.0

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.
package/dist/index.d.cts CHANGED
@@ -257,11 +257,6 @@ interface ScrapeCache {
257
257
  * Defaults to 2 days when omitted.
258
258
  */
259
259
  max_age?: number | string;
260
- /**
261
- * Treat URLs with different query parameters as the same cache entry.
262
- * Defaults to `false`.
263
- */
264
- ignore_query_params?: boolean;
265
260
  }
266
261
  /** Optional locale + country emulation for the scrape. */
267
262
  interface ScrapeLocation {
@@ -278,7 +273,12 @@ interface ScrapeLocation {
278
273
  }
279
274
  /** Request body for `POST /api/scrape` (and `POST /api/scrape/async`). */
280
275
  interface ScrapeRequest {
281
- /** The URL to scrape. */
276
+ /**
277
+ * The URL to scrape. Known tracking parameters (`utm_*`, `mtm_*`, `ga_*`, `pk_*`, `gclid`,
278
+ * `fbclid`, `msclkid`, and more) are removed before the page is fetched, so they reach
279
+ * neither the target site nor the cache key. Every other query parameter is kept verbatim
280
+ * and is part of the cache key.
281
+ */
282
282
  url: string;
283
283
  /** Which content formats to extract. Defaults to `metadata + cleaned_html`. */
284
284
  extract?: ScrapeExtract;
package/dist/index.d.ts CHANGED
@@ -257,11 +257,6 @@ interface ScrapeCache {
257
257
  * Defaults to 2 days when omitted.
258
258
  */
259
259
  max_age?: number | string;
260
- /**
261
- * Treat URLs with different query parameters as the same cache entry.
262
- * Defaults to `false`.
263
- */
264
- ignore_query_params?: boolean;
265
260
  }
266
261
  /** Optional locale + country emulation for the scrape. */
267
262
  interface ScrapeLocation {
@@ -278,7 +273,12 @@ interface ScrapeLocation {
278
273
  }
279
274
  /** Request body for `POST /api/scrape` (and `POST /api/scrape/async`). */
280
275
  interface ScrapeRequest {
281
- /** The URL to scrape. */
276
+ /**
277
+ * The URL to scrape. Known tracking parameters (`utm_*`, `mtm_*`, `ga_*`, `pk_*`, `gclid`,
278
+ * `fbclid`, `msclkid`, and more) are removed before the page is fetched, so they reach
279
+ * neither the target site nor the cache key. Every other query parameter is kept verbatim
280
+ * and is part of the cache key.
281
+ */
282
282
  url: string;
283
283
  /** Which content formats to extract. Defaults to `metadata + cleaned_html`. */
284
284
  extract?: ScrapeExtract;
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@crawlbrulee/sdk",
3
- "version": "0.7.1",
3
+ "version": "0.8.0",
4
4
  "description": "Official TypeScript / JavaScript SDK for crawlbrulee - web-scraping API.",
5
5
  "keywords": [
6
6
  "crawlbrulee",