fix: update doc examples and lint errors for include/exclude API

- Replace remaining `globs` → `include` in docs (4 examples + 2 guides)
- Convert `type` to `interface` for UrlPatternObject, GlobObject, RegExpObject (ESLint)

Author: l2ysho

docs/deployment/apify_platform_init_exit.ts

@@ -13,7 +13,7 @@ const crawler = new CheerioCrawler({
 
         // Add URLs that match the provided pattern.
         await enqueueLinks({
-            globs: ['https://www.iana.org/*'],
+            include: ['https://www.iana.org/*'],
         });
 
         // Save extracted data to dataset.

docs/deployment/apify_platform_main.ts

@@ -12,7 +12,7 @@ await Actor.main(async () => {
 
             // Add URLs that match the provided pattern.
             await enqueueLinks({
-                globs: ['https://www.iana.org/*'],
+                include: ['https://www.iana.org/*'],
             });
 
             // Save extracted data to dataset.

docs/examples/crawl_some_links.ts

@@ -9,7 +9,7 @@ const crawler = new CheerioCrawler({
         log.info(request.url);
         // Add some links from page to the crawler's RequestQueue
         await enqueueLinks({
-            globs: ['http?(s)://crawlee.dev/*/*'],
+            include: ['http?(s)://crawlee.dev/*/*'],
         });
     },
 });

docs/examples/puppeteer_recursive_crawl.ts

@@ -6,7 +6,7 @@ const crawler = new PuppeteerCrawler({
         log.info(`Title of ${request.url}: ${title}`);
 
         await enqueueLinks({
-            globs: ['http?(s)://www.iana.org/**'],
+            include: ['http?(s)://www.iana.org/**'],
         });
     },
     maxRequestsPerCrawl: 10,

docs/introduction/03-adding-urls.mdx

@@ -140,17 +140,17 @@ If you provide one of those options, the default `same-hostname` strategy will *
 
 ```ts
 await enqueueLinks({
-    globs: ['http?(s)://apify.com/*/*'],
+    include: ['http?(s)://apify.com/*/*'],
 });
 ```
 
 ### Transform requests
 
-To have absolute control, we have the <ApiLink to="core/interface/EnqueueLinksOptions/#transformRequestFunction">`transformRequestFunction`</ApiLink>. Just before a new <ApiLink to="core/class/Request">`Request`</ApiLink> is constructed and enqueued to the <ApiLink to="core/class/RequestQueue">`RequestQueue`</ApiLink>, this function can be used to skip it or modify its contents such as `userData`, `payload` or, most importantly, `uniqueKey`. This is useful when you need to enqueue multiple requests to the queue, and these requests share the same URL, but differ in methods or payloads. Another use case is to dynamically update or create the `userData`.
+To have absolute control, we have the <ApiLink to="core/interface/EnqueueLinksOptions/#transformRequestFunction">`transformRequestFunction`</ApiLink>. After request options are filtered by `include`/`exclude` patterns, this function can be used to skip them or modify their contents such as `userData`, `payload` or, most importantly, `uniqueKey`. This is useful when you need to enqueue multiple requests to the queue, and these requests share the same URL, but differ in methods or payloads. Another use case is to dynamically update or create the `userData`.
 
 ```ts
 await enqueueLinks({
-    globs: ['http?(s)://apify.com/*/*'],
+    include: ['http?(s)://apify.com/*/*'],
     transformRequestFunction(req) {
         // ignore all links ending with `.pdf`
         if (req.url.endsWith('.pdf')) return false;

docs/upgrading/upgrading_v3.md

@@ -188,14 +188,13 @@ One common helper that received more attention is the `enqueueLinks`. As mention
 
 This means we can even call `enqueueLinks()` without any parameters. By default, it will go through all the links found on current page and filter only those targeting the same subdomain.
 
-Moreover, we can specify patterns the URL should match via globs:
+Moreover, we can specify patterns the URL should match via `include`:
 
 ```ts
 const crawler = new PlaywrightCrawler({
     async requestHandler({ enqueueLinks }) {
         await enqueueLinks({
-            globs: ['https://crawlee.dev/*/*'],
-            // we can also use `regexps` and `pseudoUrls` keys here
+            include: ['https://crawlee.dev/*/*'],
         });
     },
 });
@@ -231,7 +230,7 @@ Labeling requests used to work via the `Request.userData` object. With Crawlee,
 async requestHandler({ request, enqueueLinks }) {
     if (request.label !== 'DETAIL') {
         await enqueueLinks({
-            globs: ['...'],
+            include: ['...'],
             label: 'DETAIL',
         });
     }

packages/core/src/enqueue_links/shared.ts

@@ -18,16 +18,20 @@ const MAX_ENQUEUE_LINKS_CACHE_SIZE = 1000;
  */
 const enqueueLinksPatternCache = new Map();
 
-export type UrlPatternObject = {
+export interface UrlPatternObject {
     glob?: string;
     regexp?: RegExp;
-};
+}
 
-export type GlobObject = { glob: string };
+export interface GlobObject {
+    glob: string;
+}
 
 export type GlobInput = string | GlobObject;
 
-export type RegExpObject = { regexp: RegExp };
+export interface RegExpObject {
+    regexp: RegExp;
+}
 
 export type RegExpInput = RegExp | RegExpObject;