@crawlee/basic 4.0.0-beta.2 → 4.0.0-beta.200

package/README.md

@@ -1,19 +1,23 @@
 <h1 align="center">
     <a href="https://crawlee.dev">
         <picture>
-          <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-dark.svg?sanitize=true">
-          <img alt="Crawlee" src="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-light.svg?sanitize=true" width="500">
+          <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-dark.svg?sanitize=true" />
+          <img alt="Crawlee" src="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-light.svg?sanitize=true" width="500" />
         </picture>
     </a>
-    <br>
+    <br />
     <small>A web scraping and browser automation library</small>
 </h1>
 
-<p align=center>
-    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/v/@crawlee/core.svg" alt="NPM latest version" data-canonical-src="https://img.shields.io/npm/v/@crawlee/core/next.svg" style="max-width: 100%;"></a>
-    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/dm/@crawlee/core.svg" alt="Downloads" data-canonical-src="https://img.shields.io/npm/dm/@crawlee/core.svg" style="max-width: 100%;"></a>
-    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" data-canonical-src="https://img.shields.io/discord/801163717915574323?label=discord" style="max-width: 100%;"></a>
-    <a href="https://github.com/apify/crawlee/actions/workflows/test-ci.yml"><img src="https://github.com/apify/crawlee/actions/workflows/test-ci.yml/badge.svg?branch=master" alt="Build Status" style="max-width: 100%;"></a>
+<p align="center">
+    <a href="https://trendshift.io/repositories/5179" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5179" alt="apify%2Fcrawlee | Trendshift" width="250" height="55"/></a>
+</p>
+
+<p align="center">
+    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/v/@crawlee/core.svg" alt="NPM latest version" data-canonical-src="https://img.shields.io/npm/v/@crawlee/core/next.svg" /></a>
+    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/dm/@crawlee/core.svg" alt="Downloads" data-canonical-src="https://img.shields.io/npm/dm/@crawlee/core.svg" /></a>
+    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" data-canonical-src="https://img.shields.io/discord/801163717915574323?label=discord" /></a>
+    <a href="https://github.com/apify/crawlee/actions/workflows/test-ci.yml"><img src="https://github.com/apify/crawlee/actions/workflows/test-ci.yml/badge.svg?branch=master" alt="Build Status" /></a>
 </p>
 
 Crawlee covers your crawling and scraping end-to-end and **helps you build reliable scrapers. Fast.**
@@ -24,7 +28,7 @@ Crawlee is available as the [`crawlee`](https://www.npmjs.com/package/crawlee) N
 
 > 👉 **View full documentation, guides and examples on the [Crawlee project website](https://crawlee.dev)** 👈
 
-> Crawlee for Python is open for early adopters. 🐍  [👉 Checkout the source code 👈](https://github.com/apify/crawlee-python).
+> Do you prefer 🐍 Python instead of JavaScript? [👉 Checkout Crawlee for Python 👈](https://github.com/apify/crawlee-python).
 
 ## Installation
 
@@ -85,7 +89,7 @@ By default, Crawlee stores data to `./storage` in the current working directory.
 We provide automated beta builds for every merged code change in Crawlee. You can find them in the npm [list of releases](https://www.npmjs.com/package/crawlee?activeTab=versions). If you want to test new features or bug fixes before we release them, feel free to install a beta build like this:
 
 ```bash
-npm install crawlee@3.12.3-beta.13
+npm install crawlee@next
 ```
 
 If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need to specify dependency overrides in your `package.json` file so that you don't end up with multiple versions of Crawlee installed:
@@ -94,9 +98,9 @@ If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need
 {
     "overrides": {
        "apify": {
-           "@crawlee/core": "3.12.3-beta.13",
-           "@crawlee/types": "3.12.3-beta.13",
-           "@crawlee/utils": "3.12.3-beta.13"
+           "@crawlee/core": "$crawlee",
+           "@crawlee/types": "$crawlee",
+           "@crawlee/utils": "$crawlee"
        }
     }
 }

package/index.d.ts

@@ -1,4 +1,13 @@
 export * from '@crawlee/core';
+export * from './internals/autoscaling/index.js';
 export * from './internals/basic-crawler.js';
-export * from './internals/constants.js';
-//# sourceMappingURL=index.d.ts.map
+export * from './internals/cookie_utils.js';
+export * from './internals/crawlers/index.js';
+export * from './internals/crawling_request.js';
+export * from './internals/enqueue_links/index.js';
+export * from './internals/errors.js';
+export * from './internals/http.js';
+export * from './internals/router.js';
+export * from './internals/session_pool/index.js';
+export * from './internals/sitemap_request_loader.js';
+export * from './internals/throttling_request_manager.js';

package/index.js

@@ -1,4 +1,13 @@
 export * from '@crawlee/core';
+export * from './internals/autoscaling/index.js';
 export * from './internals/basic-crawler.js';
-export * from './internals/constants.js';
-//# sourceMappingURL=index.js.map
+export * from './internals/cookie_utils.js';
+export * from './internals/crawlers/index.js';
+export * from './internals/crawling_request.js';
+export * from './internals/enqueue_links/index.js';
+export * from './internals/errors.js';
+export * from './internals/http.js';
+export * from './internals/router.js';
+export * from './internals/session_pool/index.js';
+export * from './internals/sitemap_request_loader.js';
+export * from './internals/throttling_request_manager.js';

package/internals/autoscaling/autoscaled_pool.d.ts

@@ -0,0 +1,198 @@
+import type { CrawleeLogger } from '@crawlee/core';
+import type { ConcurrencyConsumer, IConcurrencySystem } from './concurrency_system.js';
+/**
+ * The two predicates that steer a task loop: *is there work ready?* and *are we done?* These are the parts of the loop
+ * a caller legitimately overrides, as opposed to the task itself (`runTaskFunction`), which the loop's driver owns.
+ */
+export interface TaskLoopPredicates {
+    /**
+     * A function that indicates whether `runTaskFunction` should be called.
+     * This function is called every time there is free capacity for a new task and it should
+     * indicate whether it should start a new task or not by resolving to either `true` or `false`.
+     * Besides its obvious use, it is also useful for task throttling to save resources.
+     */
+    isTaskReadyFunction?: () => Promise<boolean>;
+    /**
+     * A function that is called only when there are no tasks to be processed.
+     * If it resolves to `true` then the run finishes. Being called only
+     * when there are no tasks being processed means that as long as `isTaskReadyFunction()`
+     * keeps resolving to `true`, `isFinishedFunction()` will never be called.
+     */
+    isFinishedFunction?: () => Promise<boolean>;
+}
+export interface TaskLoopOptions extends TaskLoopPredicates {
+    /**
+     * How often the pool should check if a new task is ready, in seconds.
+     * @default 0.5
+     */
+    maybeRunIntervalSecs?: number;
+}
+/** @internal */
+export interface AutoscaledPoolOptions extends TaskLoopOptions {
+    /**
+     * The governor that decides whether there is free compute for one more task. Typically a
+     * {@link ConcurrencySystem}, but any {@link IConcurrencySystem} works. Share a single instance across
+     * multiple pools (and therefore multiple crawlers) to cap their *combined* concurrency against one budget.
+     *
+     * All concurrency/scaling/snapshotter configuration lives on the governor — the pool only owns the task loop and
+     * its cadence.
+     */
+    concurrencySystem: IConcurrencySystem;
+    /**
+     * Who this pool is, presented to the governor on every capacity query and booking so that a shared one can tell
+     * several pools apart. Worth naming meaningfully — a governor that allocates per consumer reports this `id`.
+     */
+    consumer: ConcurrencyConsumer;
+    /**
+     * A function that performs an asynchronous resource-intensive task.
+     * The function must either be labeled `async` or return a promise.
+     * @param taskId The id the task is {@link IConcurrencySystem.tryRegisterTaskStart|booked} under, so work done
+     * inside can be correlated with what the governor sees.
+     */
+    runTaskFunction?: (taskId: string) => Promise<unknown>;
+    /**
+     * Timeout in which the `runTaskFunction` needs to finish, given in seconds.
+     * @default 0
+     */
+    taskTimeoutSecs?: number;
+    log?: CrawleeLogger;
+}
+/**
+ * Manages a pool of asynchronous resource-intensive tasks that are executed in parallel.
+ * The pool only starts new tasks while its {@link IConcurrencySystem|concurrency system} reports free capacity —
+ * that governor is what monitors CPU, memory and event loop load and autoscales the concurrency budget.
+ *
+ * Before running the pool, you need to implement the following three functions:
+ * {@link AutoscaledPoolOptions.runTaskFunction|`runTaskFunction`},
+ * {@link TaskLoopPredicates.isTaskReadyFunction|`isTaskReadyFunction`} and
+ * {@link TaskLoopPredicates.isFinishedFunction|`isFinishedFunction`}.
+ *
+ * The auto-scaled pool is started by calling the {@link AutoscaledPool.run} function.
+ * The pool periodically queries `isTaskReadyFunction` for more tasks, managing optimal concurrency, until the function
+ * resolves to `false`. The pool then queries `isFinishedFunction`. If it resolves to `true`, the run finishes after all
+ * running tasks complete. If it resolves to `false`, it assumes there will be more tasks available later and keeps
+ * periodically querying for tasks.
+ * If any of the tasks throws then the {@link AutoscaledPool.run} function rejects the promise with an error.
+ *
+ * The pool evaluates whether it should start a new task every time one of the tasks finishes
+ * and also in the interval set by the `options.maybeRunIntervalSecs` parameter.
+ *
+ * **Example usage:**
+ *
+ * ```javascript
+ * const concurrencySystem = new ConcurrencySystem({ maxConcurrency: 50 });
+ * await concurrencySystem.start();
+ *
+ * const pool = new AutoscaledPool({
+ *     concurrencySystem,
+ *     consumer: { id: 'my-pool' },
+ *     runTaskFunction: async () => {
+ *         // Run some resource-intensive asynchronous operation here.
+ *     },
+ *     isTaskReadyFunction: async () => {
+ *         // Tell the pool whether more tasks are ready to be processed.
+ *         // Return true or false
+ *     },
+ *     isFinishedFunction: async () => {
+ *         // Tell the pool whether it should finish
+ *         // or wait for more tasks to become available.
+ *         // Return true or false
+ *     }
+ * });
+ *
+ * try {
+ *     await pool.run();
+ * } finally {
+ *     await concurrencySystem.stop();
+ * }
+ * ```
+ *
+ * @internal
+ */
+export declare class AutoscaledPool {
+    #private;
+    constructor(options: AutoscaledPoolOptions);
+    /**
+     * The governor backing this pool, as supplied to the constructor — exposed as the read-only
+     * {@link IConcurrencySystem} contract.
+     *
+     * This and the two getters below are telemetry only: concurrency is configured and tuned on the concrete
+     * {@link ConcurrencySystem} its owner holds, never through the pool.
+     */
+    get system(): IConcurrencySystem;
+    /** The estimated number of parallel tasks the governor can currently support. */
+    get desiredConcurrency(): number;
+    /**
+     * The number of parallel tasks currently booked against the governor. When it is shared, this counts every
+     * borrowing pool's tasks, not just this one's.
+     */
+    get currentConcurrency(): number;
+    /**
+     * Runs the auto-scaled pool. Returns a promise that gets resolved or rejected once
+     * all the tasks are finished or one of them fails.
+     *
+     * Throws if the {@link IConcurrencySystem|concurrency system} it borrows was never started — the pool assumes
+     * a running governor and cannot start one it does not own.
+     */
+    run(): Promise<void>;
+    /**
+     * Aborts the run of the auto-scaled pool and destroys it. The promise returned from
+     * the {@link AutoscaledPool.run} function will immediately resolve, no more new tasks
+     * will be spawned and all running tasks will be left in their current state.
+     *
+     * Due to the nature of the tasks, auto-scaled pool cannot reliably guarantee abortion
+     * of all the running tasks, therefore, no abortion is attempted and some of the tasks
+     * may finish, while others may not. Essentially, auto-scaled pool doesn't care about
+     * their state after the invocation of `.abort()`, but that does not mean that some
+     * parts of their asynchronous chains of commands will not execute.
+     */
+    abort(): Promise<void>;
+    /**
+     * Prevents the auto-scaled pool from starting new tasks, but allows the running ones to finish
+     * (unlike abort, which terminates them). Used together with {@link AutoscaledPool.resume}
+     *
+     * The function's promise will resolve once all running tasks have completed and the pool
+     * is effectively idle. If the `timeoutSecs` argument is provided, the promise will reject
+     * with a timeout error after the `timeoutSecs` seconds.
+     *
+     * The promise returned from the {@link AutoscaledPool.run} function will not resolve
+     * when `.pause()` is invoked (unlike abort, which resolves it).
+     *
+     * > *NOTE:* Pausing the pool does not suspend the (possibly shared) {@link ConcurrencySystem} — its
+     * autoscaling and resource monitoring keep running, since other pools borrowing it may still be active. To silence
+     * it during a long pause, its owner can `stop()` and `start()` it again.
+     */
+    pause(timeoutSecs?: number): Promise<void>;
+    /**
+     * Resumes the operation of the autoscaled-pool by allowing more tasks to be run.
+     * Used together with {@link AutoscaledPool.pause}
+     *
+     * Tasks will automatically start running again in `options.maybeRunIntervalSecs`.
+     */
+    resume(): void;
+    /**
+     * Explicitly check the queue for new tasks. The AutoscaledPool checks the queue for new tasks periodically,
+     * every `maybeRunIntervalSecs` seconds. If you want to trigger the processing immediately, use this method.
+     */
+    notify(): Promise<void>;
+    /**
+     * Starts a new task
+     * if the number of running tasks (current concurrency) is lower than desired concurrency
+     * and the system is not currently overloaded
+     * and `isTaskReadyFunction()` returns true.
+     *
+     * It doesn't allow multiple concurrent runs of this method.
+     */
+    private maybeRunTask;
+    /**
+     * If there are no running tasks and `isFinishedFunction()` returns true then closes
+     * the pool and resolves the pool's promise returned by the run() method.
+     *
+     * It doesn't allow multiple concurrent runs of this method.
+     */
+    private maybeFinish;
+    /**
+     * Cleans up resources.
+     */
+    private destroy;
+}