Selector Forge

Product Introduction

1. Definition: Selector Forge is an AI-powered browser extension (for Chrome and Firefox) that generates robust, semantic CSS and XPath selectors for web elements. It is a developer tool designed for tasks requiring precise element targeting, such as web scraping, browser automation, and data extraction.
2. Core Value Proposition: Selector Forge solves the core problem of brittle web selectors by creating selectors that are "forged" through AI generation, stress-testing, and semantic anchoring. Its primary purpose is to provide reliable, resilient selectors for both single elements and lists of items, significantly reducing maintenance overhead in automation scripts when webpage structures change.

Main Features

1. AI-Powered Selector Generation: The extension uses an AI model to create selectors based on a user's click. When the user selects a value, the tool intelligently identifies the element's semantic context—most importantly, its associated label—and forges a selector anchored to that relationship (e.g., //dt[normalize-space()='Solicitation Type']/following-sibling::dd). This approach produces semantic selectors that target elements by their meaning rather than fragile positional or structural attributes, making them more resilient to page layout changes.
2. Live Judging and Stress-Testing: Every generated selector undergoes immediate validation. The tool performs a live "stress-test" against the current page to verify its reliability. It then certifies the selector with a clear judgment (e.g., "✓ RELIABLE"), filtering out the "brittle ones" that would likely break. This ensures users only copy selectors that are proven to work for the given context.
3. Support for Single and List Selections: The extension handles two primary use cases. For a "Single element", it targets one specific value on the page. For a "List of items", it analyzes repeated patterns; selecting one instance (e.g., one file in a list) prompts the tool to generate a single, universal selector for all similar items, outputting the entire list. This is crucial for tasks like scraping multiple data points from a directory or table.
4. Playwright Test Integration Preview: The interface showcases a Playwright test snippet as a validation step, demonstrating the generated selector's practical application and reliability in a real automation framework (e.g., await page.locator("xpath=//dt[…]::dd").textContent()). This provides immediate proof of functionality for developers.
5. Open Source and CLI Roadmap: The project is open source on GitHub, allowing for transparency, community contribution, and self-hosting. A command-line interface (CLI) is listed as "COMING SOON" (with a command like npx intuned forge pick), indicating future support for headless, script-integrated selector generation, expanding its use in automated pipelines and CI/CD environments.

Problems Solved

1. Pain Point: Maintenance Overhead of Brittle Selectors. Traditional CSS and XPath selectors copied from browser dev tools often rely on specific element order, fragile class names, or deep DOM paths. When a website's HTML structure is updated, these selectors break, requiring manual intervention and code rewriting. This is a critical problem for maintaining web scraping pipelines and RPA (Robotic Process Automation) scripts.
2. Target Audience: The product targets QA Engineers and Test Automation Specialists (who need stable selectors for end-to-end tests), Web Scraping Developers and Data Scientists (building and maintaining data collection tools), Full-Stack and Frontend Developers (integrating automation or testing features), and Marketing/Research Analysts needing to automate data extraction from portals without coding deep technical skills.
3. Use Cases: Essential scenarios include: 1) Creating stable selectors for web scraping contracts (e.g., scraping public procurement portals, as shown in the demo); 2) Building or maintaining end-to-end test suites for web applications; 3) Automating form filling or data entry in browser-based workflows; 4) Rapid prototyping of browser automation scripts for one-off data gathering tasks.

Unique Advantages

1. Differentiation: Unlike standard browser developer tools that simply display existing selectors, Selector Forge actively generates and validates them. It differs from pure CSS/XPath generators by incorporating AI-driven semantic analysis (label anchoring) and a mandatory reliability check. Traditional methods produce raw, often unreliable selectors; Selector Forge produces certified, production-ready selectors.
2. Key Innovation: The core innovation is its "Semantic Anchoring" algorithm. By tying the target element's selector to its descriptive label (e.g., a <dt> tag preceding a <dd> tag), it creates a relationship-based selector that survives common page redesigns like reordering fields, changing wrapper divs, or modifying non-semantic attributes. This, combined with the automated stress-test, sets it apart as a proactive quality assurance tool for selectors, not just a passive generator.

Frequently Asked Questions (FAQ)

1. How does Selector Forge create more reliable selectors than manual inspection? Selector Forge uses AI to analyze the page's semantic structure, typically anchoring the target element to its associated label. This creates a relationship-based selector (e.g., "find the <dd> that comes after a <dt> with specific text") instead of a brittle positional one. Every selector is then automatically stress-tested against the live page and certified, ensuring reliability before use.
2. Can I use Selector Forge for selecting multiple similar elements, like all items in a list? Yes. The "List of items" mode is designed specifically for this. By pointing at one instance of a repeated element (e.g., one row in a table, one item in a file list), the AI detects the pattern and generates a single, universal selector that targets all similar elements on the page, no matter how many there are.
3. Is Selector Forge suitable for non-developers? While its primary audience is technical users like developers and data scientists, its point-and-click interface is accessible to anyone needing to extract data. A marketing analyst or researcher can use it to reliably identify and copy selectors for use in no-code browser automation tools or data extraction platforms.
4. How does the open-source nature of Selector Forge benefit users? Being open source on GitHub allows for complete transparency in how selectors are generated. Users can audit the code, contribute improvements, or fork the project for their own needs. It also builds trust, as the community can verify the safety and effectiveness of the AI model and testing logic.
5. What is the "CLI — COMING SOON" feature, and how will it help? The upcoming Command-Line Interface (CLI) will allow users to generate and test selectors directly from the terminal (e.g., via npx intuned forge pick). This is crucial for integrating Selector Forge into automated scripts, headless browser environments, and continuous integration pipelines, enabling fully automated selector management as part of larger software development and data workflows.