@crawlee/playwright 3.0.0-alpha.2 → 3.0.0-alpha.3

package/dist/LICENSE.md

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "{}"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2018 Apify Technologies s.r.o.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/dist/index.d.ts

@@ -0,0 +1,6 @@
+export * from '@crawlee/browser';
+export * from './internals/playwright-crawler';
+export * from './internals/playwright-launcher';
+export * as playwrightUtils from './internals/utils/playwright-utils';
+export type { DirectNavigationOptions as PlaywrightDirectNavigationOptions } from './internals/utils/playwright-utils';
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,kBAAkB,CAAC;AACjC,cAAc,gCAAgC,CAAC;AAC/C,cAAc,iCAAiC,CAAC;AAEhD,OAAO,KAAK,eAAe,MAAM,oCAAoC,CAAC;AACtE,YAAY,EAAE,uBAAuB,IAAI,iCAAiC,EAAE,MAAM,oCAAoC,CAAC"}

package/dist/index.js

@@ -0,0 +1,9 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.playwrightUtils = void 0;
+const tslib_1 = require("tslib");
+tslib_1.__exportStar(require("@crawlee/browser"), exports);
+tslib_1.__exportStar(require("./internals/playwright-crawler"), exports);
+tslib_1.__exportStar(require("./internals/playwright-launcher"), exports);
+exports.playwrightUtils = tslib_1.__importStar(require("./internals/utils/playwright-utils"));
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";;;;AAAA,2DAAiC;AACjC,yEAA+C;AAC/C,0EAAgD;AAEhD,8FAAsE"}

package/dist/index.mjs

@@ -0,0 +1,73 @@
+import mod from "./index.js";
+
+export default mod;
+export const API_PROCESSED_REQUESTS_DELAY_MILLIS = mod.API_PROCESSED_REQUESTS_DELAY_MILLIS;
+export const AutoscaledPool = mod.AutoscaledPool;
+export const BASIC_CRAWLER_TIMEOUT_BUFFER_SECS = mod.BASIC_CRAWLER_TIMEOUT_BUFFER_SECS;
+export const BasicCrawler = mod.BasicCrawler;
+export const BrowserCrawler = mod.BrowserCrawler;
+export const BrowserLauncher = mod.BrowserLauncher;
+export const Configuration = mod.Configuration;
+export const CookieParseError = mod.CookieParseError;
+export const CrawlerExtension = mod.CrawlerExtension;
+export const DATASET_ITERATORS_DEFAULT_LIMIT = mod.DATASET_ITERATORS_DEFAULT_LIMIT;
+export const Dataset = mod.Dataset;
+export const EVENT_SESSION_RETIRED = mod.EVENT_SESSION_RETIRED;
+export const EnqueueStrategy = mod.EnqueueStrategy;
+export const EventManager = mod.EventManager;
+export const EventType = mod.EventType;
+export const KeyValueStore = mod.KeyValueStore;
+export const LocalEventManager = mod.LocalEventManager;
+export const Log = mod.Log;
+export const LogLevel = mod.LogLevel;
+export const Logger = mod.Logger;
+export const LoggerJson = mod.LoggerJson;
+export const LoggerText = mod.LoggerText;
+export const MAX_QUERIES_FOR_CONSISTENCY = mod.MAX_QUERIES_FOR_CONSISTENCY;
+export const PlaywrightCrawler = mod.PlaywrightCrawler;
+export const PlaywrightLauncher = mod.PlaywrightLauncher;
+export const ProxyConfiguration = mod.ProxyConfiguration;
+export const QUERY_HEAD_BUFFER = mod.QUERY_HEAD_BUFFER;
+export const QUERY_HEAD_MIN_LENGTH = mod.QUERY_HEAD_MIN_LENGTH;
+export const REQUESTS_PERSISTENCE_KEY = mod.REQUESTS_PERSISTENCE_KEY;
+export const Request = mod.Request;
+export const RequestList = mod.RequestList;
+export const RequestQueue = mod.RequestQueue;
+export const STATE_PERSISTENCE_KEY = mod.STATE_PERSISTENCE_KEY;
+export const STATUS_CODES_BLOCKED = mod.STATUS_CODES_BLOCKED;
+export const STORAGE_CONSISTENCY_DELAY_MILLIS = mod.STORAGE_CONSISTENCY_DELAY_MILLIS;
+export const Session = mod.Session;
+export const SessionPool = mod.SessionPool;
+export const Snapshotter = mod.Snapshotter;
+export const Statistics = mod.Statistics;
+export const StorageManager = mod.StorageManager;
+export const SystemStatus = mod.SystemStatus;
+export const basicCrawlerEnqueueLinks = mod.basicCrawlerEnqueueLinks;
+export const browserCrawlerEnqueueLinks = mod.browserCrawlerEnqueueLinks;
+export const checkAndSerialize = mod.checkAndSerialize;
+export const chunkBySize = mod.chunkBySize;
+export const constructGlobObjectsFromGlobs = mod.constructGlobObjectsFromGlobs;
+export const constructRegExpObjectsFromPseudoUrls = mod.constructRegExpObjectsFromPseudoUrls;
+export const constructRegExpObjectsFromRegExps = mod.constructRegExpObjectsFromRegExps;
+export const createDeserialize = mod.createDeserialize;
+export const createRequestOptions = mod.createRequestOptions;
+export const createRequests = mod.createRequests;
+export const deserializeArray = mod.deserializeArray;
+export const diffCookies = mod.diffCookies;
+export const enqueueLinks = mod.enqueueLinks;
+export const getCookiesFromResponse = mod.getCookiesFromResponse;
+export const getRequestId = mod.getRequestId;
+export const handleRequestTimeout = mod.handleRequestTimeout;
+export const launchPlaywright = mod.launchPlaywright;
+export const log = mod.log;
+export const maybeStringify = mod.maybeStringify;
+export const mergeCookies = mod.mergeCookies;
+export const openDataset = mod.openDataset;
+export const playwrightUtils = mod.playwrightUtils;
+export const pushData = mod.pushData;
+export const serializeArray = mod.serializeArray;
+export const storage = mod.storage;
+export const throwOnBlockedRequest = mod.throwOnBlockedRequest;
+export const updateEnqueueLinksPatternCache = mod.updateEnqueueLinksPatternCache;
+export const validateGlobPattern = mod.validateGlobPattern;
+export const validators = mod.validators;

package/dist/internals/playwright-crawler.d.ts

@@ -0,0 +1,223 @@
+import { LaunchOptions, Page, Response } from 'playwright';
+import { PlaywrightPlugin } from '@crawlee/browser-pool';
+import { BrowserCrawler, BrowserCrawlerOptions, BrowserCrawlingContext, BrowserCrawlerHandleRequest, BrowserHook } from '@crawlee/browser';
+import { PlaywrightLaunchContext } from './playwright-launcher';
+import { DirectNavigationOptions } from './utils/playwright-utils';
+export declare type PlaywrightController = ReturnType<PlaywrightPlugin['_createController']>;
+export declare type PlaywrightCrawlContext = BrowserCrawlingContext<Page, Response, PlaywrightController>;
+export declare type PlaywrightHook = BrowserHook<PlaywrightCrawlContext, PlaywrightGotoOptions>;
+export declare type PlaywrightRequestHandlerParam = BrowserCrawlingContext<Page, Response, PlaywrightController>;
+export declare type PlaywrightRequestHandler = BrowserCrawlerHandleRequest<PlaywrightRequestHandlerParam>;
+export declare type PlaywrightGotoOptions = Parameters<Page['goto']>[1];
+export interface PlaywrightCrawlerOptions extends BrowserCrawlerOptions<PlaywrightCrawlContext, PlaywrightGotoOptions, {
+    browserPlugins: [PlaywrightPlugin];
+}> {
+    /**
+     * Function that is called to process each request.
+     * It is passed an object with the following fields:
+     *
+     * ```
+     * {
+     *   request: Request,
+     *   response: Response,
+     *   page: Page,
+     *   session: Session,
+     *   browserController: BrowserController,
+     *   proxyInfo: ProxyInfo,
+     *   crawler: PlaywrightCrawler,
+     * }
+     * ```
+     *
+     * `request` is an instance of the {@link Request} object with details about the URL to open, HTTP method etc.
+     * `page` is an instance of the `Playwright`
+     * [`Page`](https://playwright.dev/docs/api/class-page)
+     * `browserController` is an instance of the
+     * [`BrowserController`](https://github.com/apify/browser-pool#browsercontroller),
+     * `response` is an instance of the `Playwright`
+     * [`Response`](https://playwright.dev/docs/api/class-response),
+     * which is the main resource response as returned by `page.goto(request.url)`.
+     * The function must return a promise, which is then awaited by the crawler.
+     *
+     * If the function throws an exception, the crawler will try to re-crawl the
+     * request later, up to `option.maxRequestRetries` times.
+     * If all the retries fail, the crawler calls the function
+     * provided to the `handleFailedRequestFunction` parameter.
+     * To make this work, you should **always**
+     * let your function throw exceptions rather than catch them.
+     * The exceptions are logged to the request using the
+     * {@link Request.pushErrorMessage} function.
+     */
+    requestHandler: PlaywrightRequestHandler;
+    /**
+     * Function that is called to process each request.
+     * It is passed an object with the following fields:
+     *
+     * ```
+     * {
+     *   request: Request,
+     *   response: Response,
+     *   page: Page,
+     *   session: Session,
+     *   browserController: BrowserController,
+     *   proxyInfo: ProxyInfo,
+     *   crawler: PlaywrightCrawler,
+     * }
+     * ```
+     *
+     * `request` is an instance of the {@link Request} object with details about the URL to open, HTTP method etc.
+     * `page` is an instance of the `Playwright`
+     * [`Page`](https://playwright.dev/docs/api/class-page)
+     * `browserController` is an instance of the
+     * [`BrowserController`](https://github.com/apify/browser-pool#browsercontroller),
+     * `response` is an instance of the `Playwright`
+     * [`Response`](https://playwright.dev/docs/api/class-response),
+     * which is the main resource response as returned by `page.goto(request.url)`.
+     * The function must return a promise, which is then awaited by the crawler.
+     *
+     * If the function throws an exception, the crawler will try to re-crawl the
+     * request later, up to `option.maxRequestRetries` times.
+     * If all the retries fail, the crawler calls the function
+     * provided to the `handleFailedRequestFunction` parameter.
+     * To make this work, you should **always**
+     * let your function throw exceptions rather than catch them.
+     * The exceptions are logged to the request using the
+     * {@link Request.pushErrorMessage} function.
+     *
+     * @deprecated `handlePageFunction` has been renamed to `requestHandler` and will be removed in a future version.
+     */
+    handlePageFunction?: PlaywrightRequestHandler;
+    /**
+     * Async functions that are sequentially evaluated before the navigation. Good for setting additional cookies
+     * or browser properties before navigation. The function accepts two parameters, `crawlingContext` and `gotoOptions`,
+     * which are passed to the `page.goto()` function the crawler calls to navigate.
+     * Example:
+     * ```
+     * preNavigationHooks: [
+     *     async (crawlingContext, gotoOptions) => {
+     *         await page.evaluate((attr) => { window.foo = attr; }, 'bar');
+     *     },
+     * ]
+     * ```
+     */
+    preNavigationHooks?: PlaywrightHook[];
+    /**
+     * Async functions that are sequentially evaluated after the navigation. Good for checking if the navigation was successful.
+     * The function accepts `crawlingContext` as the only parameter.
+     * Example:
+     * ```
+     * postNavigationHooks: [
+     *     async (crawlingContext) => {
+     *         const { page } = crawlingContext;
+     *         if (hasCaptcha(page)) {
+     *             await solveCaptcha (page);
+     *         }
+     *     },
+     * ]
+     * ```
+     */
+    postNavigationHooks?: PlaywrightHook[];
+    /**
+     * The same options as used by {@link launchPlaywright}.
+     */
+    launchContext?: PlaywrightLaunchContext;
+}
+/**
+ * Provides a simple framework for parallel crawling of web pages
+ * using headless Chromium, Firefox and Webkit browsers with [Playwright](https://github.com/microsoft/playwright).
+ * The URLs to crawl are fed either from a static list of URLs
+ * or from a dynamic queue of URLs enabling recursive crawling of websites.
+ *
+ * Since `Playwright` uses headless browser to download web pages and extract data,
+ * it is useful for crawling of websites that require to execute JavaScript.
+ * If the target website doesn't need JavaScript, consider using {@link CheerioCrawler},
+ * which downloads the pages using raw HTTP requests and is about 10x faster.
+ *
+ * The source URLs are represented using {@link Request} objects that are fed from
+ * {@link RequestList} or {@link RequestQueue} instances provided by the {@link PlaywrightCrawlerOptions.requestList}
+ * or {@link PlaywrightCrawlerOptions.requestQueue} constructor options, respectively.
+ *
+ * If both {@link PlaywrightCrawlerOptions.requestList} and {@link PlaywrightCrawlerOptions.requestQueue} are used,
+ * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
+ * to {@link RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ *
+ * The crawler finishes when there are no more {@link Request} objects to crawl.
+ *
+ * `PlaywrightCrawler` opens a new Chrome page (i.e. tab) for each {@link Request} object to crawl
+ * and then calls the function provided by user as the {@link PlaywrightCrawlerOptions.handlePageFunction} option.
+ *
+ * New pages are only opened when there is enough free CPU and memory available,
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the {@link PlaywrightCrawlerOptions.autoscaledPoolOptions}
+ * parameter of the `PlaywrightCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
+ * {@link AutoscaledPoolOptions} are available directly in the `PlaywrightCrawler` constructor.
+ *
+ * Note that the pool of Playwright instances is internally managed by the [BrowserPool](https://github.com/apify/browser-pool) class.
+ *
+ * **Example usage:**
+ *
+ * ```javascript
+ * const crawler = new PlaywrightCrawler({
+ *     requestList,
+ *     handlePageFunction: async ({ page, request }) => {
+ *         // This function is called to extract data from a single web page
+ *         // 'page' is an instance of Playwright.Page with page.goto(request.url) already called
+ *         // 'request' is an instance of Request class with information about the page to load
+ *         await Actor.pushData({
+ *             title: await page.title(),
+ *             url: request.url,
+ *             succeeded: true,
+ *         })
+ *     },
+ *     handleFailedRequestFunction: async ({ request }) => {
+ *         // This function is called when the crawling of a request failed too many times
+ *         await Actor.pushData({
+ *             url: request.url,
+ *             succeeded: false,
+ *             errors: request.errorMessages,
+ *         })
+ *     },
+ * });
+ *
+ * await crawler.run();
+ * ```
+ * @category Crawlers
+ */
+export declare class PlaywrightCrawler extends BrowserCrawler<{
+    browserPlugins: [PlaywrightPlugin];
+}, LaunchOptions, PlaywrightCrawlContext> {
+    protected static optionsShape: {
+        browserPoolOptions: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        launcher: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        launchContext: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        handlePageFunction: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
+        gotoFunction: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
+        gotoTimeoutSecs: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        navigationTimeoutSecs: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        preNavigationHooks: import("ow").ArrayPredicate<unknown> & import("ow").BasePredicate<unknown[] | undefined>;
+        postNavigationHooks: import("ow").ArrayPredicate<unknown> & import("ow").BasePredicate<unknown[] | undefined>;
+        sessionPoolOptions: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        persistCookiesPerSession: import("ow").BooleanPredicate & import("ow").BasePredicate<boolean | undefined>;
+        useSessionPool: import("ow").BooleanPredicate & import("ow").BasePredicate<boolean | undefined>;
+        proxyConfiguration: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        requestList: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        requestQueue: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        requestHandler: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
+        handleRequestFunction: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
+        requestHandlerTimeoutSecs: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        handleRequestTimeoutSecs: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        failedRequestHandler: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
+        handleFailedRequestFunction: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
+        maxRequestRetries: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        maxRequestsPerCrawl: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        autoscaledPoolOptions: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+        minConcurrency: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        maxConcurrency: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
+        log: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
+    };
+    /**
+     * All `PlaywrightCrawler` parameters are passed via an options object.
+     */
+    constructor(options: PlaywrightCrawlerOptions);
+    protected _navigationHandler(crawlingContext: PlaywrightCrawlContext, gotoOptions: DirectNavigationOptions): Promise<any>;
+}
+//# sourceMappingURL=playwright-crawler.d.ts.map

package/dist/internals/playwright-crawler.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"playwright-crawler.d.ts","sourceRoot":"","sources":["../../src/internals/playwright-crawler.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,aAAa,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,YAAY,CAAC;AAC3D,OAAO,EAAsB,gBAAgB,EAAE,MAAM,uBAAuB,CAAC;AAE7E,OAAO,EACH,cAAc,EACd,qBAAqB,EACrB,sBAAsB,EACtB,2BAA2B,EAC3B,WAAW,EACd,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EAAsB,uBAAuB,EAAE,MAAM,uBAAuB,CAAC;AACpF,OAAO,EAAE,uBAAuB,EAAgB,MAAM,0BAA0B,CAAC;AAEjF,oBAAY,oBAAoB,GAAG,UAAU,CAAC,gBAAgB,CAAC,mBAAmB,CAAC,CAAC,CAAC;AAErF,oBAAY,sBAAsB,GAAG,sBAAsB,CAAC,IAAI,EAAE,QAAQ,EAAE,oBAAoB,CAAC,CAAA;AAEjG,oBAAY,cAAc,GAAG,WAAW,CAAC,sBAAsB,EAAE,qBAAqB,CAAC,CAAC;AAExF,oBAAY,6BAA6B,GAAG,sBAAsB,CAAC,IAAI,EAAE,QAAQ,EAAE,oBAAoB,CAAC,CAAA;AAExG,oBAAY,wBAAwB,GAAG,2BAA2B,CAAC,6BAA6B,CAAC,CAAC;AAElG,oBAAY,qBAAqB,GAAG,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;AAEhE,MAAM,WAAW,wBAAyB,SAAQ,qBAAqB,CACnE,sBAAsB,EACtB,qBAAqB,EACrB;IAAE,cAAc,EAAE,CAAC,gBAAgB,CAAC,CAAA;CAAE,CACzC;IACG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;OAkCG;IACH,cAAc,EAAE,wBAAwB,CAAC;IAEzC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;OAoCG;IACH,kBAAkB,CAAC,EAAE,wBAAwB,CAAC;IAE9C;;;;;;;;;;;;OAYG;IACH,kBAAkB,CAAC,EAAE,cAAc,EAAE,CAAC;IAEtC;;;;;;;;;;;;;;OAcG;IACH,mBAAmB,CAAC,EAAE,cAAc,EAAE,CAAC;IAEvC;;OAEG;IACH,aAAa,CAAC,EAAE,uBAAuB,CAAC;CAM3C;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4DG;AACH,qBAAa,iBAAkB,SAAQ,cAAc,CAAC;IAAE,cAAc,EAAE,CAAC,gBAAgB,CAAC,CAAA;CAAE,EAAE,aAAa,EAAE,sBAAsB,CAAC;IAChI,iBAA0B,YAAY;;;;;;;;;;;;;;;;;;;;;;;;;;;;MAKpC;IAEF;;OAEG;gBACS,OAAO,EAAE,wBAAwB;cAuBpB,kBAAkB,CAAC,eAAe,EAAE,sBAAsB,EAAE,WAAW,EAAE,uBAAuB;CAQ5H"}

package/dist/internals/playwright-crawler.js

@@ -0,0 +1,108 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.PlaywrightCrawler = void 0;
+const tslib_1 = require("tslib");
+const ow_1 = tslib_1.__importDefault(require("ow"));
+const browser_1 = require("@crawlee/browser");
+const playwright_launcher_1 = require("./playwright-launcher");
+const playwright_utils_1 = require("./utils/playwright-utils");
+/**
+ * Provides a simple framework for parallel crawling of web pages
+ * using headless Chromium, Firefox and Webkit browsers with [Playwright](https://github.com/microsoft/playwright).
+ * The URLs to crawl are fed either from a static list of URLs
+ * or from a dynamic queue of URLs enabling recursive crawling of websites.
+ *
+ * Since `Playwright` uses headless browser to download web pages and extract data,
+ * it is useful for crawling of websites that require to execute JavaScript.
+ * If the target website doesn't need JavaScript, consider using {@link CheerioCrawler},
+ * which downloads the pages using raw HTTP requests and is about 10x faster.
+ *
+ * The source URLs are represented using {@link Request} objects that are fed from
+ * {@link RequestList} or {@link RequestQueue} instances provided by the {@link PlaywrightCrawlerOptions.requestList}
+ * or {@link PlaywrightCrawlerOptions.requestQueue} constructor options, respectively.
+ *
+ * If both {@link PlaywrightCrawlerOptions.requestList} and {@link PlaywrightCrawlerOptions.requestQueue} are used,
+ * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
+ * to {@link RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ *
+ * The crawler finishes when there are no more {@link Request} objects to crawl.
+ *
+ * `PlaywrightCrawler` opens a new Chrome page (i.e. tab) for each {@link Request} object to crawl
+ * and then calls the function provided by user as the {@link PlaywrightCrawlerOptions.handlePageFunction} option.
+ *
+ * New pages are only opened when there is enough free CPU and memory available,
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the {@link PlaywrightCrawlerOptions.autoscaledPoolOptions}
+ * parameter of the `PlaywrightCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
+ * {@link AutoscaledPoolOptions} are available directly in the `PlaywrightCrawler` constructor.
+ *
+ * Note that the pool of Playwright instances is internally managed by the [BrowserPool](https://github.com/apify/browser-pool) class.
+ *
+ * **Example usage:**
+ *
+ * ```javascript
+ * const crawler = new PlaywrightCrawler({
+ *     requestList,
+ *     handlePageFunction: async ({ page, request }) => {
+ *         // This function is called to extract data from a single web page
+ *         // 'page' is an instance of Playwright.Page with page.goto(request.url) already called
+ *         // 'request' is an instance of Request class with information about the page to load
+ *         await Actor.pushData({
+ *             title: await page.title(),
+ *             url: request.url,
+ *             succeeded: true,
+ *         })
+ *     },
+ *     handleFailedRequestFunction: async ({ request }) => {
+ *         // This function is called when the crawling of a request failed too many times
+ *         await Actor.pushData({
+ *             url: request.url,
+ *             succeeded: false,
+ *             errors: request.errorMessages,
+ *         })
+ *     },
+ * });
+ *
+ * await crawler.run();
+ * ```
+ * @category Crawlers
+ */
+class PlaywrightCrawler extends browser_1.BrowserCrawler {
+    /**
+     * All `PlaywrightCrawler` parameters are passed via an options object.
+     */
+    constructor(options) {
+        (0, ow_1.default)(options, 'PlaywrightCrawlerOptions', ow_1.default.object.exactShape(PlaywrightCrawler.optionsShape));
+        const { launchContext = {}, browserPoolOptions = {}, ...browserCrawlerOptions } = options;
+        if (launchContext.proxyUrl) {
+            throw new Error('PlaywrightCrawlerOptions.launchContext.proxyUrl is not allowed in PlaywrightCrawler.'
+                + 'Use PlaywrightCrawlerOptions.proxyConfiguration');
+        }
+        const playwrightLauncher = new playwright_launcher_1.PlaywrightLauncher(launchContext);
+        browserPoolOptions.browserPlugins = [
+            playwrightLauncher.createBrowserPlugin(),
+        ];
+        super({ ...browserCrawlerOptions, browserPoolOptions });
+        this.launchContext = launchContext;
+    }
+    async _navigationHandler(crawlingContext, gotoOptions) {
+        if (this.gotoFunction) {
+            this.log.deprecated('PlaywrightCrawler.gotoFunction is deprecated. Use "preNavigationHooks" and "postNavigationHooks" instead.');
+            return this.gotoFunction(crawlingContext, gotoOptions);
+        }
+        return (0, playwright_utils_1.gotoExtended)(crawlingContext.page, crawlingContext.request, gotoOptions);
+    }
+}
+exports.PlaywrightCrawler = PlaywrightCrawler;
+Object.defineProperty(PlaywrightCrawler, "optionsShape", {
+    enumerable: true,
+    configurable: true,
+    writable: true,
+    value: {
+        ...browser_1.BrowserCrawler.optionsShape,
+        browserPoolOptions: ow_1.default.optional.object,
+        launcher: ow_1.default.optional.object,
+        launchContext: ow_1.default.optional.object,
+    }
+});
+//# sourceMappingURL=playwright-crawler.js.map

package/dist/internals/playwright-crawler.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"playwright-crawler.js","sourceRoot":"","sources":["../../src/internals/playwright-crawler.ts"],"names":[],"mappings":";;;;AAAA,oDAAoB;AAIpB,8CAM0B;AAC1B,+DAAoF;AACpF,+DAAiF;AA0IjF;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4DG;AACH,MAAa,iBAAkB,SAAQ,wBAA6F;IAQhI;;OAEG;IACH,YAAY,OAAiC;QACzC,IAAA,YAAE,EAAC,OAAO,EAAE,0BAA0B,EAAE,YAAE,CAAC,MAAM,CAAC,UAAU,CAAC,iBAAiB,CAAC,YAAY,CAAC,CAAC,CAAC;QAE9F,MAAM,EACF,aAAa,GAAG,EAAE,EAClB,kBAAkB,GAAG,EAA0C,EAC/D,GAAG,qBAAqB,EAC3B,GAAG,OAAO,CAAC;QAEZ,IAAI,aAAa,CAAC,QAAQ,EAAE;YACxB,MAAM,IAAI,KAAK,CAAC,sFAAsF;kBAChG,iDAAiD,CAAC,CAAC;SAC5D;QACD,MAAM,kBAAkB,GAAG,IAAI,wCAAkB,CAAC,aAAa,CAAC,CAAC;QAEjE,kBAAkB,CAAC,cAAc,GAAG;YAChC,kBAAkB,CAAC,mBAAmB,EAAE;SAC3C,CAAC;QAEF,KAAK,CAAC,EAAE,GAAG,qBAAqB,EAAE,kBAAkB,EAAE,CAAC,CAAC;QACxD,IAAI,CAAC,aAAa,GAAG,aAAa,CAAC;IACvC,CAAC;IAEkB,KAAK,CAAC,kBAAkB,CAAC,eAAuC,EAAE,WAAoC;QACrH,IAAI,IAAI,CAAC,YAAY,EAAE;YACnB,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,2GAA2G,CAAC,CAAC;YACjI,OAAO,IAAI,CAAC,YAAY,CAAC,eAAe,EAAE,WAAyB,CAAC,CAAC;SACxE;QAED,OAAO,IAAA,+BAAY,EAAC,eAAe,CAAC,IAAI,EAAE,eAAe,CAAC,OAAO,EAAE,WAAW,CAAC,CAAC;IACpF,CAAC;;AAzCL,8CA0CC;AAzCG;;;;WAAyC;QACrC,GAAG,wBAAc,CAAC,YAAY;QAC9B,kBAAkB,EAAE,YAAE,CAAC,QAAQ,CAAC,MAAM;QACtC,QAAQ,EAAE,YAAE,CAAC,QAAQ,CAAC,MAAM;QAC5B,aAAa,EAAE,YAAE,CAAC,QAAQ,CAAC,MAAM;KACpC;GAAC"}