> For the complete documentation index, see [llms.txt](https://gaffa.dev/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gaffa.dev/docs/features/browser-requests/api-playground-examples/parse-html-form-to-structured-json.md). # Parse HTML Form to Structured JSON *The following example is a request we've pre-built to show you Gaffa's capabilities against our* [*demo site*](https://demo.gaffa.dev)*. **You can run this request right now in the*** [***Gaffa API Playground***](https://gaffa.dev/dashboard/playground?templateId=parse_html_form_to_structured_json)***.*** This example demonstrates how to extract structured information from HTML forms on web pages. Gaffa uses AI to identify form elements and their properties, making it perfect for form automation, testing, accessibility audits, or building form-filling assistants. ## API Request The request below uses the [POST endpoint](https://gaffa.dev/docs/api-reference/post-v1-browser-requests) to open the demo form page, wait for the modal to appear, and then parse the visible form to extract all field information, including labels, input names, placeholders, and dropdown options. ```json { "url": "https://demo.gaffa.dev/simulate/form?loadTime=3&showModal=true&modalDelay=5&formType=address", "async": false, "max_cache_age": 0, "settings": { "record_request": false, "actions": [ { "type": "wait", "selector": "form", "timeout": 10000 }, { "type": "parse_json", "data_schema": { "name": "FormFields", "description": "Extract all form input fields", "fields": [ { "type": "string", "name": "form_title", "description": "Form title" }, { "type": "array", "name": "fields", "description": "List of all input fields", "fields": [ { "type": "string", "name": "label", "description": "Field label" }, { "type": "string", "name": "field_name", "description": "Field name attribute" }, { "type": "string", "name": "field_type", "description": "Input type" }, { "type": "boolean", "name": "required", "description": "Is required?" }, { "type": "string", "name": "placeholder", "description": "Placeholder text" } ] } ] }, "instruction": "Extract all form fields with their properties", "model": "gpt-4o-mini", "output_type": "inline" } ] } } ``` ## Actions {% content-ref url="/pages/Py3syTPEzIuvQYXyaDso" %} [Wait](/docs/features/browser-requests/actions/wait.md) {% endcontent-ref %} {% content-ref url="/pages/7bb96jtp13gAqQoJ3aqV" %} [Parse JSON](/docs/features/browser-requests/actions/parse-json.md) {% endcontent-ref %} ## Response The parsed form data is returned as a structured JSON object: ```json { "data": { "id": "brq_VrwuWctcUAj75jbs5XUFkMbGGeBeLP", "url": "https://demo.gaffa.dev/simulate/form?loadTime=3&showModal=true&modalDelay=5&formType=address", "state": "completed", "credit_usage": 0, "http_status_code": 200, "from_cache": false, "started_at": "2026-07-14T16:20:29.8409557Z", "completed_at": "2026-07-14T16:20:43.1357433Z", "running_time": "00:00:13.2947876", "page_load_time": "00:00:00.5453910", "actions": [ { "id": "act_VrwuWbYiipbS2e91UHf3vokLudWjez", "type": "wait", "timestamp": "2026-07-14T16:20:37.1333682Z" }, { "id": "act_VrwuWkyuTBi8w3pBaQD98naDi9MvaK", "type": "parse_json", "timestamp": "2026-07-14T16:20:43.1357329Z", "output": { "form_title": "Form Submission Test", "fields": [ { "label": "First Name *", "field_name": "first_name", "field_type": "text", "required": true, "placeholder": "" }, { "label": "Last Name *", "field_name": "last_name", "field_type": "text", "required": true, "placeholder": "" }, { "label": "Email *", "field_name": "email", "field_type": "email", "required": true, "placeholder": "" }, { "label": "Address Line 1 *", "field_name": "address_line_1", "field_type": "text", "required": true, "placeholder": "" }, { "label": "Address Line 2", "field_name": "address_line_2", "field_type": "text", "required": false, "placeholder": "" }, { "label": "City *", "field_name": "city", "field_type": "text", "required": true, "placeholder": "" }, { "label": "State/Province *", "field_name": "state_province", "field_type": "text", "required": true, "placeholder": "" }, { "label": "ZIP/Postal Code *", "field_name": "zip_postal_code", "field_type": "text", "required": true, "placeholder": "" }, { "label": "Country *", "field_name": "country", "field_type": "text", "required": true, "placeholder": "" } ] }, "reference": "https://storage.gaffa.dev/brq/dom/brq_VrwuWctcUAj75jbs5XUFkMbGGeBeLP/act_VrwuWkyuTBi8w3pBaQD98naDi9MvaK_raw.txt" } ] } } ``` --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://gaffa.dev/docs/features/browser-requests/api-playground-examples/parse-html-form-to-structured-json.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.