@adobe/spacecat-shared-scrape-client 1.0.0

package/CHANGELOG.md

@@ -0,0 +1,6 @@
+# @adobe/spacecat-shared-scrape-client-v1.0.0 (2025-06-19)
+
+
+### Features
+
+* added scrape client ([#814](https://github.com/adobe/spacecat-shared/issues/814)) ([fad6614](https://github.com/adobe/spacecat-shared/commit/fad6614672a046da5319e493cc7c26bfdc3993d2))

package/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Adobe Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at Grp-opensourceoffice@adobe.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

package/CONTRIBUTING.md

@@ -0,0 +1,74 @@
+# Contributing to Project Franklin
+
+This project (like almost all of Project Franklin) is an Open Development project and welcomes contributions from everyone who finds it useful or lacking.
+
+## Code Of Conduct
+
+This project adheres to the Adobe [code of conduct](CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code. Please report unacceptable behavior to cstaub at adobe dot com.
+
+## Contributor License Agreement
+
+All third-party contributions to this project must be accompanied by a signed contributor license. This gives Adobe permission to redistribute your contributions as part of the project. [Sign our CLA](http://opensource.adobe.com/cla.html)! You only need to submit an Adobe CLA one time, so if you have submitted one previously, you are good to go!
+
+## Things to Keep in Mind
+
+This project uses a **commit then review** process, which means that for approved maintainers, changes can be merged immediately, but will be reviewed by others.
+
+For other contributors, a maintainer of the project has to approve the pull request.
+
+# Before You Contribute
+
+* Check that there is an existing issue in GitHub issues
+* Check if there are other pull requests that might overlap or conflict with your intended contribution
+
+# How to Contribute
+
+1. Fork the repository
+2. Make some changes on a branch on your fork
+3. Create a pull request from your branch
+
+In your pull request, outline:
+
+* What the changes intend
+* How they change the existing code
+* If (and what) they breaks
+* Start the pull request with the GitHub issue ID, e.g. #123
+
+Lastly, please follow the [pull request template](.github/pull_request_template.md) when submitting a pull request!
+
+Each commit message that is not part of a pull request:
+
+* Should contain the issue ID like `#123`
+* Can contain the tag `[trivial]` for trivial changes that don't relate to an issue
+
+
+
+## Coding Styleguides
+
+We enforce a coding styleguide using `eslint`. As part of your build, run `npm run lint` to check if your code is conforming to the style guide. We do the same for every PR in our CI, so PRs will get rejected if they don't follow the style guide.
+
+You can fix some of the issues automatically by running `npx eslint . --fix`.
+
+## Commit Message Format
+
+This project uses a structured commit changelog format that should be used for every commit. Use `npm run commit` instead of your usual `git commit` to generate commit messages using a wizard.
+
+```bash
+# either add all changed files
+$ git add -A
+# or selectively add files
+$ git add package.json
+# then commit using the wizard
+$ npm run commit
+```
+
+# How Contributions get Reviewed
+
+One of the maintainers will look at the pull request within one week. Feedback on the pull request will be given in writing, in GitHub.
+
+# Release Management
+
+The project's committers will release to the [Adobe organization on npmjs.org](https://www.npmjs.com/org/adobe).
+Please contact the [Adobe Open Source Advisory Board](https://git.corp.adobe.com/OpenSourceAdvisoryBoard/discuss/issues) to get access to the npmjs organization.
+
+The release process is fully automated using `semantic-release`, increasing the version numbers, etc. based on the contents of the commit messages found.

package/LICENSE.txt

@@ -0,0 +1,264 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.
+
+
+APACHE JACKRABBIT SUBCOMPONENTS
+
+Apache Jackrabbit includes parts with separate copyright notices and license
+terms. Your use of these subcomponents is subject to the terms and conditions
+of the following licenses:
+
+    XPath 2.0/XQuery 1.0 Parser:
+    http://www.w3.org/2002/11/xquery-xpath-applets/xgrammar.zip
+
+    Copyright (C) 2002 World Wide Web Consortium, (Massachusetts Institute of
+    Technology, European Research Consortium for Informatics and Mathematics,
+    Keio University). All Rights Reserved.
+
+    This work is distributed under the W3C(R) Software License in the hope
+    that it will be useful, but WITHOUT ANY WARRANTY; without even the
+    implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+    W3C(R) SOFTWARE NOTICE AND LICENSE
+    http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
+
+    This work (and included software, documentation such as READMEs, or
+    other related items) is being provided by the copyright holders under
+    the following license. By obtaining, using and/or copying this work,
+    you (the licensee) agree that you have read, understood, and will comply
+    with the following terms and conditions.
+
+    Permission to copy, modify, and distribute this software and its
+    documentation, with or without modification, for any purpose and
+    without fee or royalty is hereby granted, provided that you include
+    the following on ALL copies of the software and documentation or
+    portions thereof, including modifications:
+
+       1. The full text of this NOTICE in a location viewable to users
+          of the redistributed or derivative work.
+
+       2. Any pre-existing intellectual property disclaimers, notices,
+          or terms and conditions. If none exist, the W3C Software Short
+          Notice should be included (hypertext is preferred, text is
+          permitted) within the body of any redistributed or derivative code.
+
+       3. Notice of any changes or modifications to the files, including
+          the date changes were made. (We recommend you provide URIs to the
+          location from which the code is derived.)
+
+    THIS SOFTWARE AND DOCUMENTATION IS PROVIDED "AS IS," AND COPYRIGHT
+    HOLDERS MAKE NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED,
+    INCLUDING BUT NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY OR FITNESS
+    FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE OR
+    DOCUMENTATION WILL NOT INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS,
+    TRADEMARKS OR OTHER RIGHTS.
+
+    COPYRIGHT HOLDERS WILL NOT BE LIABLE FOR ANY DIRECT, INDIRECT, SPECIAL
+    OR CONSEQUENTIAL DAMAGES ARISING OUT OF ANY USE OF THE SOFTWARE OR
+    DOCUMENTATION.
+
+    The name and trademarks of copyright holders may NOT be used in
+    advertising or publicity pertaining to the software without specific,
+    written prior permission. Title to copyright in this software and
+    any associated documentation will at all times remain with
+    copyright holders.

package/README.md

@@ -0,0 +1,249 @@
+# Spacecat Shared - Scrape Client
+
+A JavaScript client for managing web scraping jobs, part of the SpaceCat Shared library. The ScrapeClient provides a comprehensive interface for creating, monitoring, and retrieving results from web scraping operations without needing to access the SpaceCat API service directly.
+
+## Installation
+
+Install the package using npm:
+
+```bash
+npm install @adobe/spacecat-shared-scrape-client
+```
+
+## Features
+
+- **Create Scrape Jobs**: Submit URLs for web scraping with customizable options
+- **Job Monitoring**: Track job status and progress
+- **Result Retrieval**: Get detailed results for completed scraping jobs
+- **Date Range Queries**: Find jobs within specific time periods
+- **Base URL Filtering**: Search jobs by domain or base URL
+- **Processing Type Support**: Different scraping strategies and configurations
+- **Custom Headers**: Add custom HTTP headers for scraping requests
+- **Error Handling**: Comprehensive validation and error reporting
+
+## Usage
+
+### Creating an Instance
+
+#### Method 1: Direct Constructor
+
+```js
+import { ScrapeClient } from '@adobe/spacecat-shared-scrape-client';
+
+const config = {
+  dataAccess: dataAccessClient,    // Data access layer
+  sqs: sqsClient,                  // SQS client for job queuing
+  env: environmentVariables,       // Environment configuration
+  log: logger                      // Logging interface
+};
+
+const client = new ScrapeClient(config);
+```
+
+#### Method 2: From Helix Universal Context
+
+```js
+import { ScrapeClient } from '@adobe/spacecat-shared-scrape-client';
+
+const context = {
+  dataAccess: context.dataAccess,
+  sqs: context.sqs,
+  env: context.env,
+  log: context.log
+};
+
+const client = ScrapeClient.createFrom(context);
+```
+
+### Creating a Scrape Job
+
+```js
+const jobData = {
+  urls: ['https://example.com/page1', 'https://example.com/page2'],
+  options: {},
+  customHeaders: {
+    // Custom HTTP headers (optional)
+    'Authorization': 'Bearer token',
+    'X-Custom-Header': 'value'
+  },
+  processingType: 'default' // Optional, defaults to 'DEFAULT'
+};
+
+try {
+  const job = await client.createScrapeJob(jobData);
+  console.log('Job created:', job.id);
+  console.log('Job status:', job.status);
+} catch (error) {
+  console.error('Failed to create job:', error.message);
+}
+```
+
+### Checking Job Status
+
+```js
+const jobId = 'your-job-id';
+
+try {
+  const jobStatus = await client.getScrapeJobStatus(jobId);
+  if (jobStatus) {
+    console.log('Job Status:', jobStatus.status);
+    console.log('URL Count:', jobStatus.urlCount);
+    console.log('Success Count:', jobStatus.successCount);
+    console.log('Failed Count:', jobStatus.failedCount);
+    console.log('Duration:', jobStatus.duration);
+  } else {
+    console.log('Job not found');
+  }
+} catch (error) {
+  console.error('Failed to get job status:', error.message);
+}
+```
+
+### Getting Job Results
+
+```js
+const jobId = 'your-job-id';
+
+try {
+  const results = await client.getScrapeJobUrlResults(jobId);
+  if (results) {
+    results.forEach(result => {
+      console.log(`URL: ${result.url}`);
+      console.log(`Status: ${result.status}`);
+      console.log(`Reason: ${result.reason}`);
+      console.log(`Path: ${result.path}`);
+    });
+  } else {
+    console.log('Job not found');
+  }
+} catch (error) {
+  console.error('Failed to get job results:', error.message);
+}
+```
+
+### Finding Jobs by Date Range
+
+```js
+const startDate = '2024-01-01T00:00:00Z';
+const endDate = '2024-01-31T23:59:59Z';
+
+try {
+  const jobs = await client.getScrapeJobsByDateRange(startDate, endDate);
+  console.log(`Found ${jobs.length} jobs in date range`);
+  jobs.forEach(job => {
+    console.log(`Job ${job.id}: ${job.status} - ${job.baseURL}`);
+  });
+} catch (error) {
+  console.error('Failed to get jobs by date range:', error.message);
+}
+```
+
+### Finding Jobs by Base URL
+
+```js
+const baseURL = 'https://example.com';
+
+try {
+  // Get all jobs for a base URL
+  const allJobs = await client.getScrapeJobsByBaseURL(baseURL);
+  console.log(`Found ${allJobs.length} jobs for ${baseURL}`);
+
+  // Get jobs for a specific processing type
+  const specificJobs = await client.getScrapeJobsByBaseURL(baseURL, 'form');
+  console.log(`Found ${specificJobs.length} jobs with custom processing`);
+} catch (error) {
+  console.error('Failed to get jobs by base URL:', error.message);
+}
+```
+
+## Job Response Format
+
+When you retrieve a scrape job, it returns an object with the following structure:
+
+```js
+{
+  id: "job-id",
+  baseURL: "https://example.com",
+  processingType: "default",
+  options: { /* scraping options */ },
+  startedAt: "2024-01-01T10:00:00Z",
+  endedAt: "2024-01-01T10:05:00Z",
+  duration: 300000, // milliseconds
+  status: "COMPLETE",
+  urlCount: 10,
+  successCount: 8,
+  failedCount: 2,
+  redirectCount: 0,
+  customHeaders: { /* custom headers used */ }
+}
+```
+
+## URL Results Format
+
+When you retrieve job results, each URL result has this structure:
+
+```js
+{
+  url: "https://example.com/page",
+  status: "SUCCESS",
+  reason: "in case there was an error, you will this this here",
+  path: "/s3/path/to/scraped/content"
+}
+```
+
+## Configuration
+
+The client uses the `SCRAPE_JOB_CONFIGURATION` environment variable for default settings:
+
+```js
+// Example configuration
+{
+  "maxUrlsPerJob": 5,
+  "options": {
+    "enableJavascript": true,
+    "hideConsentBanner": true,
+  }
+}
+```
+
+## Testing
+
+To run tests:
+
+```bash
+npm run test
+```
+
+## Linting
+
+Lint your code:
+
+```bash
+npm run lint
+```
+
+Fix linting issues:
+
+```bash
+npm run lint:fix
+```
+
+## Cleaning
+
+To remove `node_modules` and `package-lock.json`:
+
+```bash
+npm run clean
+```
+
+## Dependencies
+
+- `@adobe/helix-universal`: Universal context support
+- `@adobe/spacecat-shared-data-access`: Data access layer
+- `@adobe/spacecat-shared-utils`: Utility functions
+
+## Additional Information
+
+- **Repository**: [GitHub](https://github.com/adobe/spacecat-shared.git)
+- **Issue Tracking**: [GitHub Issues](https://github.com/adobe/spacecat-shared/issues)
+- **License**: Apache-2.0

package/package.json

@@ -0,0 +1,50 @@
+{
+  "name": "@adobe/spacecat-shared-scrape-client",
+  "version": "1.0.0",
+  "description": "Shared modules of the Spacecat Services - Scrape Client",
+  "type": "module",
+  "engines": {
+    "node": ">=22.0.0 <23.0.0",
+    "npm": ">=10.9.0 <12.0.0"
+  },
+  "main": "src/index.js",
+  "types": "src/index.d.ts",
+  "scripts": {
+    "test": "c8 mocha --spec=test/**/*.test.js",
+    "lint": "eslint .",
+    "lint:fix": "eslint --fix .",
+    "clean": "rm -rf package-lock.json node_modules"
+  },
+  "mocha": {
+    "require": "test/setup-env.js",
+    "reporter": "mocha-multi-reporters",
+    "reporter-options": "configFile=.mocha-multi.json",
+    "spec": "test/**/*.test.js"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/adobe/spacecat-shared.git"
+  },
+  "author": "",
+  "license": "Apache-2.0",
+  "bugs": {
+    "url": "https://github.com/adobe/spacecat-shared/issues"
+  },
+  "homepage": "https://github.com/adobe/spacecat-shared#readme",
+  "publishConfig": {
+    "access": "public"
+  },
+  "dependencies": {
+    "@adobe/helix-universal": "5.2.2",
+    "@adobe/spacecat-shared-data-access": "2.25.0",
+    "@adobe/spacecat-shared-utils": "1.31.0"
+  },
+  "devDependencies": {
+    "chai": "5.2.0",
+    "chai-as-promised": "8.0.1",
+    "nock": "14.0.5",
+    "sinon": "20.0.0",
+    "sinon-chai": "4.0.0",
+    "typescript": "5.8.3"
+  }
+}

package/src/clients/ScrapeClient.d.ts

@@ -0,0 +1,66 @@
+/*
+ * Copyright 2025 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+import { UniversalContext } from '@adobe/helix-universal';
+
+export default class ScrapeClient {
+  /**
+   * Static factory method to create an instance of ScrapeClient.
+   * @param {UniversalContext} context - An object containing the AWS Lambda context information
+   * @returns An instance of ScrapeClient.
+   */
+  static createFrom(context: UniversalContext): ScrapeClient;
+
+  /**
+   * Constructor for creating an instance of ScrapeClient.
+   * @param config - Configuration object for the ScrapeClient.
+   * @param log - Optional logger instance for logging messages.
+   */
+  constructor(config: object, log?: Console);
+
+  /**
+   * Create and start a new scrape job.
+   * @param {object} data - json data for scrape job
+   * @returns {Promise<Response>} new job object
+   */
+  async createScrapeJob(data: object): Promise<object>;
+
+  /**
+   * Get all scrape jobs between startDate and endDate
+   * @param {string} startDate - The start date of the range.
+   * @param {string} endDate - The end date of the range.
+   * @returns {Promise<Response>} JSON representation of the scrape jobs.
+   */
+  async getScrapeJobsByDateRange(startDate: string, endDate: string): Promise<object[]>;
+
+  /**
+   * Get the status of an scrape job.
+   * @param {string} jobId - The ID of the job to fetch.
+   * @returns {Promise<Response>} JSON representation of the scrape job.
+   */
+  async getScrapeJobStatus(jobId: string): Promise<object>;
+
+  /**
+   * Get the result of a scrape job
+   * @param {string} jobId - The ID of the job to fetch.
+   * @returns {Promise<Response>} all results for all urls scrape jobs.
+   */
+  async getScrapeJobUrlResults(jobId: string): Promise<object[]>;
+
+  /**
+   * Get all scrape jobs by baseURL and processing type
+   * @param {string} baseURL - The baseURL of the jobs to fetch.
+   * @param {string} processingType - (optional) The processing type of the jobs to fetch.
+   * @returns {Promise<Response>} JSON representation of the scrape jobs
+   */
+  async getScrapeJobsByBaseURL(baseURL: string, processingType?: string): Promise<object[]>;
+}

package/src/clients/index.d.ts

@@ -0,0 +1,15 @@
+/*
+ * Copyright 2024 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+import type { ScrapeClient } from './ScrapeClient.d.ts';
+
+export { ScrapeClient };

package/src/clients/scrape-client.js

@@ -0,0 +1,260 @@
+/*
+ * Copyright 2025 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+import {
+  isIsoDate, isObject, isValidUrl, isNonEmptyArray, hasText,
+  isValidUUID,
+} from '@adobe/spacecat-shared-utils';
+import { ScrapeJob as ScrapeJobModel } from '@adobe/spacecat-shared-data-access';
+import { ScrapeJobDto } from './scrapeJobDto.js';
+import ScrapeJobSupervisor from './scrape-job-supervisor.js';
+
+export default class ScrapeClient {
+  config = null;
+
+  services = null;
+
+  scrapeConfiguration = null;
+
+  scrapeSupervisor = null;
+
+  maxUrlsPerJob = 1;
+
+  static validateIsoDates(startDate, endDate) {
+    if (!isIsoDate(startDate) || !isIsoDate(endDate)) {
+      throw new Error('Invalid request: startDate and endDate must be in ISO 8601 format');
+    }
+  }
+
+  validateRequestData(data) {
+    if (!isObject(data)) {
+      throw new Error('Invalid request: missing application/json request data');
+    }
+
+    if (!isNonEmptyArray(data.urls)) {
+      throw new Error('Invalid request: urls must be provided as a non-empty array');
+    }
+
+    if (data.urls.length > this.maxUrlsPerJob) {
+      throw new Error(`Invalid request: number of URLs provided (${data.urls.length}) exceeds the maximum allowed (${this.maxUrlsPerJob})`);
+    }
+
+    data.urls.forEach((url) => {
+      if (!isValidUrl(url)) {
+        throw new Error(`Invalid request: ${url} is not a valid URL`);
+      }
+    });
+
+    if (data.options && !isObject(data.options)) {
+      throw new Error('Invalid request: options must be an object');
+    }
+
+    if (data.customHeaders && !isObject(data.customHeaders)) {
+      throw new Error('Invalid request: customHeaders must be an object');
+    }
+  }
+
+  /**
+   * Creates a new ScrapeClient from the context.
+   * @param {object} context - The context object
+   * @param {object} context.dataAccess - The data access client
+   * @param {object} context.sqs - The SQS client
+   * @param {object} context.log - The logger
+   * @param {object} context.env - The environment variables
+   * @returns {ScrapeClient} - The ScrapeClient instance
+   */
+  static createFrom(context) {
+    function validateServices() {
+      const requiredServices = ['dataAccess', 'sqs', 'log', 'env'];
+      requiredServices.forEach((service) => {
+        if (!context[service]) {
+          throw new Error(`Invalid services: ${service} is required`);
+        }
+      });
+    }
+    validateServices();
+    const {
+      log,
+      dataAccess,
+      sqs,
+      env,
+    } = context;
+
+    const config = {
+      dataAccess,
+      sqs,
+      env,
+      log,
+    };
+    return new ScrapeClient(config);
+  }
+
+  constructor(config) {
+    this.config = config;
+
+    let scrapeConfiguration = {};
+    try {
+      scrapeConfiguration = JSON.parse(this.config.env.SCRAPE_JOB_CONFIGURATION);
+    } catch (error) {
+      this.config.log.error(`Failed to parse scrape job configuration: ${error.message}`);
+    }
+    this.scrapeConfiguration = scrapeConfiguration;
+
+    // default to 1 url per job
+    this.maxUrlsPerJob = scrapeConfiguration.maxUrlsPerJob || 1;
+
+    this.scrapeSupervisor = new ScrapeJobSupervisor(this.config, scrapeConfiguration);
+  }
+
+  /**
+   * Create and start a new scrape job.
+   * @param {object} data - json data for scrape job
+   * @returns {Promise<Response>} newly created job object
+   */
+  async createScrapeJob(data) {
+    try {
+      this.validateRequestData(data);
+
+      const {
+        urls, options, customHeaders, processingType = ScrapeJobModel.ScrapeProcessingType.DEFAULT,
+      } = data;
+
+      this.config.log.info(`Creating a new scrape job with ${urls.length} URLs.`);
+
+      // Merge the scrape configuration options with the request options allowing the user options
+      // to override the defaults
+      const mergedOptions = {
+        ...this.scrapeConfiguration.options,
+        ...options,
+      };
+
+      const job = await this.scrapeSupervisor.startNewJob(
+        urls,
+        processingType,
+        mergedOptions,
+        customHeaders,
+      );
+      return ScrapeJobDto.toJSON(job);
+    } catch (error) {
+      const msgError = `Failed to create a new scrape job: ${error.message}`;
+      this.config.log.error(msgError);
+      throw new Error(msgError);
+    }
+  }
+
+  /**
+   * Get all scrape jobs between startDate and endDate
+   * @param {string} startDate - The start date of the range.
+   * @param {string} endDate - The end date of the range.
+   * @returns {Promise<Response>} JSON representation of the scrape jobs.
+   */
+  async getScrapeJobsByDateRange(startDate, endDate) {
+    this.config.log.debug(`Fetching scrape jobs between startDate: ${startDate} and endDate: ${endDate}.`);
+
+    ScrapeClient.validateIsoDates(startDate, endDate);
+    try {
+      const jobs = await this.scrapeSupervisor.getScrapeJobsByDateRange(startDate, endDate);
+      return jobs.map((job) => ScrapeJobDto.toJSON(job));
+    } catch (error) {
+      const msgError = `Failed to fetch scrape jobs between startDate: ${startDate} and endDate: ${endDate}, ${error.message}`;
+      this.config.log.error(msgError);
+      throw new Error(msgError);
+    }
+  }
+
+  /**
+   * Get the status of an scrape job.
+   * @param {string} jobId - The ID of the job to fetch.
+   * @returns {Promise<Response>} JSON representation of the scrape job.
+   */
+  async getScrapeJobStatus(jobId) {
+    if (!isValidUUID(jobId)) {
+      throw new Error('Job ID is required');
+    }
+    try {
+      const job = await this.scrapeSupervisor.getScrapeJob(jobId);
+      if (!job) {
+        return null;
+      }
+      return ScrapeJobDto.toJSON(job);
+    } catch (error) {
+      const msgError = `Failed to fetch scrape job status for jobId: ${jobId}, message: ${error.message}`;
+      this.config.log.error(msgError);
+      throw new Error(msgError);
+    }
+  }
+
+  /**
+   * Get the result of a scrape job
+   * @param {string} jobId - The ID of the job to fetch.
+   * @returns {Promise<Response>} all results for all urls scrape jobs.
+   */
+  async getScrapeJobUrlResults(jobId) {
+    try {
+      const job = await this.scrapeSupervisor.getScrapeJob(jobId);
+      if (!job) {
+        return null;
+      }
+      const { ScrapeUrl } = this.config.dataAccess;
+      const scrapeUrls = await ScrapeUrl.allByScrapeJobId(job.getId());
+      const results = scrapeUrls.map((url) => ({
+        url: url.getUrl(),
+        status: url.getStatus(),
+        reason: url.getReason(),
+        path: url.getPath(),
+      }));
+
+      return results;
+    } catch (error) {
+      const msgError = `Failed to fetch the scrape job result: ${error.message}`;
+      this.config.log.error(msgError);
+      throw new Error(msgError);
+    }
+  }
+
+  /**
+   * Get all scrape jobs by baseURL and processing type
+   * @param {string} baseURL - The baseURL of the jobs to fetch.
+   * @param {string} processingType - (optional) The processing type of the jobs to fetch.
+   * @returns {Promise<Response>} JSON representation of the scrape jobs
+   */
+  async getScrapeJobsByBaseURL(baseURL, processingType = undefined) {
+    let decodedBaseURL = baseURL;
+    try {
+      decodedBaseURL = decodeURIComponent(baseURL);
+
+      if (!isValidUrl(decodedBaseURL)) {
+        throw new Error('Invalid request: baseURL must be a valid URL');
+      }
+
+      let jobs = [];
+      if (hasText(processingType)) {
+        jobs = await this.scrapeSupervisor.getScrapeJobsByBaseURLAndProcessingType(
+          decodedBaseURL,
+          processingType,
+        );
+      } else {
+        jobs = await this.scrapeSupervisor.getScrapeJobsByBaseURL(decodedBaseURL);
+      }
+
+      if (!isNonEmptyArray(jobs)) {
+        return [];
+      }
+      return jobs.map((job) => ScrapeJobDto.toJSON(job));
+    } catch (error) {
+      const procType = processingType ? ` and processing type: ${processingType}` : '';
+      const msgError = `Failed to fetch scrape jobs by baseURL: ${decodedBaseURL}${procType}, ${error.message}`;
+      this.config.log.error(msgError);
+      throw new Error(msgError);
+    }
+  }
+}

package/src/clients/scrape-job-supervisor.js

@@ -0,0 +1,235 @@
+/*
+ * Copyright 2024 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+import { ScrapeJob as ScrapeJobModel } from '@adobe/spacecat-shared-data-access';
+import { isValidUUID } from '@adobe/spacecat-shared-utils';
+
+/**
+ * Scrape Supervisor provides functionality to start and manage scrape jobs.
+ * @param {object} services - The services required by the handler.
+ * @param {DataAccess} services.dataAccess - Data access.
+ * @param {object} services.sqs - AWS Simple Queue Service client.
+ * @param {object} services.s3 - AWS S3 client and related helpers.
+ * @param {object} services.log - Logger.
+ * @param {object} config - Scrape configuration details.
+ * @param {Array<string>} config.queues - Array of available scrape queues.
+ * @param {string} config.scrapeWorkerQueue - URL of the scrape worker queue.
+ * @returns {object} Scrape Supervisor.
+ */
+function ScrapeJobSupervisor(services, config) {
+  const {
+    dataAccess, sqs, log,
+  } = services;
+
+  const { ScrapeJob } = dataAccess;
+
+  const {
+    queues = [], // Array of scrape queues
+    scrapeWorkerQueue, // URL of the scrape worker queue
+  } = config;
+
+  /**
+   * Get the queue with the least number of messages.
+   */
+  async function getAvailableScrapeQueue() {
+    const countMessages = async (queue) => {
+      const count = await sqs.getQueueMessageCount(queue);
+      return { queue, count };
+    };
+
+    const arrProm = queues.map(
+      (queue) => countMessages(queue),
+    );
+    const queueMessageCounts = await Promise.all(arrProm);
+
+    if (queueMessageCounts.length === 0) {
+      return null;
+    }
+
+    // get the queue with the lowest number of messages
+    const queueWithLeastMessages = queueMessageCounts.reduce(
+      (min, current) => (min.count < current.count ? min : current),
+    );
+    log.info(`Queue with least messages: ${queueWithLeastMessages.queue}`);
+    return queueWithLeastMessages.queue;
+  }
+
+  function determineBaseURL(urls) {
+    // Initially, we will just use the domain of the first URL
+    const url = new URL(urls[0]);
+    return `${url.protocol}//${url.hostname}`;
+  }
+
+  /**
+   * Create a new scrape job by claiming one of the free scrape queues, persisting the scrape job
+   * metadata, and setting the job status to 'RUNNING'.
+   * @param {Array<string>} urls - The list of URLs to scrape.
+   * @param {string} scrapeQueueId - Name of the queue to use for this scrape job.
+   * @param {string} processingType - The scrape handler to be used for the scrape job.
+   * @param {object} options - Client provided options for the scrape job.
+   * @param {object} customHeaders - Custom headers to be sent with each request.
+   * @returns {Promise<ScrapeJob>}
+   */
+  async function createNewScrapeJob(
+    urls,
+    scrapeQueueId,
+    processingType,
+    options,
+    customHeaders = null,
+  ) {
+    const jobData = {
+      baseURL: determineBaseURL(urls),
+      scrapeQueueId,
+      processingType,
+      options,
+      urlCount: urls.length,
+      status: ScrapeJobModel.ScrapeJobStatus.RUNNING,
+      customHeaders,
+    };
+    log.info(`Creating a new scrape job. Job data: ${JSON.stringify(jobData)}`);
+    return ScrapeJob.create(jobData);
+  }
+
+  /**
+   * Get all scrape jobs between the specified start and end dates.
+   * @param {string} startDate - The start date of the range.
+   * @param {string} endDate - The end date of the range.
+   * @returns {Promise<ScrapeJob[]>}
+   */
+  async function getScrapeJobsByDateRange(startDate, endDate) {
+    return ScrapeJob.allByDateRange(startDate, endDate);
+  }
+
+  /**
+   * Get all scrape jobs by baseURL
+   * @param {string} baseURL - The baseURL of the jobs to fetch.
+   * @returns {Promise<ScrapeJob[]>}
+   */
+  async function getScrapeJobsByBaseURL(baseURL) {
+    return ScrapeJob.allByBaseURL(baseURL);
+  }
+
+  /**
+   * Get all scrape jobs by baseURL and processing type
+   * @param {string} baseURL - The baseURL of the jobs to fetch.
+   * @param {string} processingType - The processing type of the jobs to fetch.
+   * @returns {Promise<ScrapeJob[]>}
+   */
+  async function getScrapeJobsByBaseURLAndProcessingType(baseURL, processingType) {
+    return ScrapeJob.allByBaseURLAndProcessingType(baseURL, processingType);
+  }
+
+  /**
+   * Queue all URLs as a single message for processing by another function. This will enable
+   * the controller to respond with a new job ID ASAP, while the individual URLs are queued up
+   * asynchronously.
+   * @param {Array<string>} urls - Array of URL records to queue.
+   * @param {object} scrapeJob - The scrape job record.
+   * @param {object} customHeaders - Optional custom headers to be sent with each request.
+   */
+  async function queueUrlsForScrapeWorker(urls, scrapeJob, customHeaders) {
+    log.info(`Starting a new scrape job of baseUrl: ${scrapeJob.getBaseURL()} with ${urls.length}`
+      + ` URLs. This new job has claimed: ${scrapeJob.getScrapeQueueId()} `
+      + `(jobId: ${scrapeJob.getId()})`);
+
+    const options = scrapeJob.getOptions();
+    const processingType = scrapeJob.getProcessingType();
+
+    // Send a single message containing all URLs and the new job ID
+    const message = {
+      processingType,
+      jobId: scrapeJob.getId(),
+      urls,
+      customHeaders,
+      options,
+    };
+
+    await sqs.sendMessage(scrapeWorkerQueue, message);
+  }
+
+  /**
+   * Starts a new scrape job.
+   * @param {Array<string>} urls - The URLs to scrape.
+   * @param {object} options - Optional configuration params for the scrape job.
+   * @param {object} customHeaders - Optional custom headers to be sent with each request.
+   * @returns {Promise<ScrapeJob>} newly created job object
+   */
+  async function startNewJob(
+    urls,
+    processingType,
+    options,
+    customHeaders,
+  ) {
+    // Determine if there is a free scrape queue
+    const scrapeQueueId = await getAvailableScrapeQueue();
+
+    if (scrapeQueueId === null) {
+      throw new Error('Service Unavailable: No scrape queue available');
+    }
+
+    // If a queue is available, create the scrape-job record in dataAccess:
+    const newScrapeJob = await createNewScrapeJob(
+      urls,
+      scrapeQueueId,
+      processingType,
+      options,
+      customHeaders,
+    );
+
+    log.info(
+      'New scrape job created:\n'
+      + `- baseUrl: ${newScrapeJob.getBaseURL()}\n`
+      + `- urlCount: ${urls.length}\n`
+      + `- jobId: ${newScrapeJob.getId()}\n`
+      + `- scrapeQueueId: ${scrapeQueueId}\n`
+      + `- customHeaders: ${JSON.stringify(customHeaders)}\n`
+      + `- options: ${JSON.stringify(options)}`,
+    );
+
+    // Queue all URLs for scrape as a single message. This enables the controller to respond with
+    // a job ID ASAP, while the individual URLs are queued up asynchronously by another function.
+    await queueUrlsForScrapeWorker(urls, newScrapeJob, customHeaders);
+
+    return newScrapeJob;
+  }
+
+  /**
+   * Get an scrape job from the data layer.
+   * used to start the job.
+   * @param {string} jobId - The ID of the job.
+   * @returns {Promise<ScrapeJob>} requested scrape job object
+   */
+  async function getScrapeJob(jobId) {
+    if (!isValidUUID(jobId)) {
+      throw new Error('jobId must be a valid UUID');
+    }
+
+    try {
+      return ScrapeJob.findById(jobId);
+    } catch (error) {
+      if (error.message.includes('Not found')) {
+        return null;
+      }
+      throw error;
+    }
+  }
+
+  return {
+    startNewJob,
+    getScrapeJob,
+    getScrapeJobsByDateRange,
+    getScrapeJobsByBaseURL,
+    getScrapeJobsByBaseURLAndProcessingType,
+  };
+}
+
+export default ScrapeJobSupervisor;

package/src/clients/scrapeJobDto.js

@@ -0,0 +1,35 @@
+/*
+ * Copyright 2024 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+/**
+ * Data transfer object for Import Job.
+ */
+export const ScrapeJobDto = {
+  /**
+   * Converts an Import Job object into a JSON object.
+   */
+  toJSON: (scrapeJob) => ({
+    id: scrapeJob.getId(),
+    baseURL: scrapeJob.getBaseURL(),
+    processingType: scrapeJob.getProcessingType(),
+    options: scrapeJob.getOptions(),
+    startedAt: scrapeJob.getStartedAt(),
+    endedAt: scrapeJob.getEndedAt(),
+    duration: scrapeJob.getDuration(),
+    status: scrapeJob.getStatus(),
+    urlCount: scrapeJob.getUrlCount(),
+    successCount: scrapeJob.getSuccessCount(),
+    failedCount: scrapeJob.getFailedCount(),
+    redirectCount: scrapeJob.getRedirectCount(),
+    customHeaders: scrapeJob.getCustomHeaders(),
+  }),
+};

package/src/index.d.ts

@@ -0,0 +1,17 @@
+/*
+ * Copyright 2024 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+import type { ScrapeClient } from './clients';
+
+export {
+  ScrapeClient,
+};

package/src/index.js

@@ -0,0 +1,17 @@
+/*
+ * Copyright 2025 Adobe. All rights reserved.
+ * This file is licensed to you 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 REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+import ScrapeClient from './clients/scrape-client.js';
+
+export {
+  ScrapeClient,
+};