Hugging Face Models Search Scraper is a BrowserAct Bot template for collecting structured public model records from Hugging Face. Configure a base URL, keyword, and result count, then run the Bot to return ranked model metadata for AI research, model discovery, competitive analysis, dataset enrichment, or automation workflows.
What Does BrowserAct Hugging Face Models Search Scraper Do?
This template opens Hugging Face's public model search API, requests full public metadata, parses model records, derives model page URLs, and returns one structured record per model.
Key Features
- Extract public Hugging Face model search results without requiring a login.
- Capture model ID, URL, author, model name, pipeline tag, library, tags, downloads, likes, created date, last modified date, private status, gated status, and keyword.
- Sort results by downloads in descending order.
- Configure base URL, keyword, and count.
- Handle empty result sets cleanly.
What Data Can I Extract from Hugging Face?
| Field | Description |
|---|---|
rank |
Search result position assigned by the Bot. |
model_id |
Full Hugging Face model ID. |
model_url |
Public model page URL. |
author |
Author or namespace. |
model_name |
Model name derived from the model ID. |
pipeline_tag |
Pipeline task when published. |
library_name |
Library name when published. |
tags |
Public model tags. |
downloads |
Download count. |
likes |
Like count. |
last_modified |
Last modified date. |
created_at |
Created date. |
private |
Whether the model is marked private in the response. |
gated |
Gated status when returned. |
search_keyword |
Keyword used for the run. |
How to Use Hugging Face Models Search Scraper
- Click Run task.
- Enter the Hugging Face base URL.
- Enter an AI model, task, library, architecture, or topic keyword.
- Set how many model records to collect.
- Run the Bot and review the structured model results.
- Reuse the Bot with another keyword or connect the output to your workflow.
Input Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
base_url |
Yes | https://huggingface.co |
Hugging Face site base URL without a trailing slash. |
keyword |
Yes | text generation |
Search keyword used to find public models. |
count |
Yes | 20 |
Maximum number of public model records to collect. |
Example Output
{
"results": [
{
"rank": 1,
"model_id": "masterful/gligen-1-4-generation-text-box",
"model_url": "https://huggingface.co/masterful/gligen-1-4-generation-text-box",
"author": "masterful",
"model_name": "gligen-1-4-generation-text-box",
"pipeline_tag": "text-to-image",
"library_name": "diffusers",
"tags": "diffusers,stable-diffusion,text-to-image",
"downloads": "1379",
"likes": "9",
"last_modified": "2023-08-18T22:32:17.000Z",
"created_at": "2023-08-08T21:16:55.000Z",
"private": "false",
"gated": "false",
"search_keyword": "text generation"
}
]
}
How Does it Work?
BrowserAct builds the public Hugging Face API URL in the format {base_url}/api/models?search={keyword}&limit={count}&sort=downloads&direction=-1&full=true. The full=true parameter exposes public metadata such as author, gated status, last modified date, tags, downloads, and likes.
For each model object in the returned JSON array, BrowserAct maps the published fields into a flat record, derives the model URL from the model ID, splits the model ID into author and model name, and keeps optional fields empty when an individual model does not publish them.
How to Build a New Scraper Bot with Agent Built
Step 1: Describe the Data You Need
Open BrowserAct and start Agent Built from the Home prompt box or from Create -> Build with Agent. Paste a clear request that includes the website, the records to collect, the filters or search conditions, the fields to return, the result limit, and the inputs you want to reuse later.
Step 2: Let BrowserAct Build and Test the Bot
BrowserAct explores the live website, works out the navigation and extraction path, and validates the result. If BrowserAct asks for clarification, reply in the same build conversation with the missing URL, condition, field, example, or expected output.
Step 3: Run the Bot and Review the Result
When the build is complete, run the Bot with the default inputs first. Review the structured records, source URLs, missing fields, and row count before reusing the Bot with new inputs or connecting it to another workflow.
Why Scrape Hugging Face Model Results?
Hugging Face model data helps teams discover AI models, compare popularity, track model activity, monitor tasks and libraries, enrich AI catalogs, and route public model metadata into research dashboards, alerts, or agent workflows.
Who Can Use This Template?
- AI researchers comparing public models.
- Product teams monitoring model ecosystems.
- ML platform teams enriching internal model catalogs.
- Developer relations teams tracking model adoption.
- Automation builders routing model metadata into spreadsheets, databases, alerts, or agents.
How Many Results Can You Scrape?
Use count to control the number of model records returned. Hugging Face returns fewer records when fewer public matches are available.
Automation and Export
BrowserAct returns structured Hugging Face model records first. You can then use the output through API JSON responses, n8n workflows, Make scenarios, Zapier automations, MCP-based agent workflows configured from the Bot's Integrations tab, or manual CSV review.
Need Help?
Contact us at
Discord: Discord Community
E-mail: service@browseract.com
