---

Huggingface Discovery Parser Spider

Introduction

The Huggingface Discovery Parser Spider is a powerful tool designed to efficiently scrape and parse data from the Hugging Face platform. It allows users to extract valuable information about AI models, including metadata such as author details, model descriptions, categories, and more. This Actor simplifies the process of gathering insights into trending and relevant AI technologies.

Features

• Comprehensive Data Extraction: Retrieves detailed information on AI models from Hugging Face.
• Customizable Search: Allows users to specify search keys for targeted data scraping.
• Flexible Item Limiting: Users can set a maximum number of items to scrape per run, including unlimited options.
• High-Quality Output: Provides structured JSON output with essential metadata fields.
• User-Friendly Configuration: Simple setup with clear input parameters and easy-to-follow instructions.

Input Parameters

Parameter	Type	Required	Description	Example
SearchKey	string	No	The search key for the spider.	"gpt"
item_limit	integer	No	Maximum items to scrape per actor run. Set to 0 for no limit.	10

Example Usage

Input JSON

{
  "SearchKey": "gpt",
  "item_limit": 10
}

Output JSON

[
  {
    "id": "lj1995/GPT-SoVITS-ProPlus",
    "author": "lj1995",
    "author_name": "lj1995",
    "author_fullname": "liu",
    "author_avatar_url": "https://huggingface.co/avatars/b9065b1db98ec504e348128f25ae93d4.svg",
    "title": "GPT SoVITS V2 Pro Plus",
    "description": "Generate speech from text using a reference voice",
    "category": "Speech Synthesis",
    "tags": ["gradio", "region:us"],
    "likes": 237,
    "created_at": "2024-08-12T09:49:49.000Z",
    "last_modified": "2026-05-17T11:29:27.000Z",
    "pinned": false,
    "private": false,
    "featured": false,
    "visibility": "public",
    "trending_score": 1,
    "semantic_relevancy_score": 0.9177493006766734,
    "sdk": "gradio",
    "repo_type": "space",
    "runtime_stage": "RUNNING",
    "runtime_hardware_current": "zero-a10g",
    "runtime_hardware_requested": "zero-a10g",
    "runtime_replicas_current": 1,
    "runtime_replicas_requested": 1,
    "runtime_domain": "lj1995-gpt-sovits-proplus.hf.space",
    "runtime_domain_stage": "READY",
    "actor_id": "8Y27cMbGfoZEN0tmM",
    "run_id": "5wu1wNUskjFyjUQXG"
  },
  {
    "id": "XXXXRT/GPT-SoVITS",
    "author": "XXXXRT",
    "author_name": "XXXXRT",
    "author_fullname": "XXXXRT",
    "author_avatar_url": "https://huggingface.co/avatars/71db5f5569c1fd60646fd2131118911b.svg",
    "title": "GPT-SoVITS-DEMO",
    "description": "Generate speech from text using reference audio",
    "category": "Speech Synthesis",
    "tags": ["gradio", "region:us"],
    "likes": 27,
    "created_at": "2025-06-27T09:15:48.000Z",
    "last_modified": "2025-09-18T21:38:23.000Z",
    "pinned": false,
    "private": false,
    "featured": false,
    "visibility": "public",
    "trending_score": 1,
    "semantic_relevancy_score": 0.86931203757813,
    "sdk": "gradio",
    "repo_type": "space",
    "runtime_stage": "RUNNING",
    "runtime_hardware_current": "zero-a10g",
    "runtime_hardware_requested": "zero-a10g",
    "runtime_replicas_current": 1,
    "runtime_replicas_requested": 1,
    "runtime_domain": "xxxxrt-gpt-sovits.hf.space",
    "runtime_domain_stage": "READY",
    "actor_id": "8Y27cMbGfoZEN0tmM",
    "run_id": "5wu1wNUskjFyjUQXG"
  },
  {
    "id": "mkmenta/try-gpt-1-and-gpt-2",
    "author": "mkmenta",
    "author_name": "mkmenta",
    "author_fullname": "Mikel Menta Garde",
    "author_avatar_url": "https://huggingface.co/avatars/92823717fb0691b7ecb3ebe42ff86d75.svg",
    "title": "Try GPT-1 and GPT-2",
    "description": "Generate creative text using GPT-1 or GPT-2 models",
    "category": "Text Generation",
    "tags": ["gradio", "region:us"],
    "likes": 26,
    "created_at": "2023-07-02T14:42:48.000Z",
    "last_modified": "2024-11-05T09:19:48.000Z",
    "pinned": false,
    "private": false,
    "featured": false,
    "visibility": "public",
    "trending_score": 2,
    "semantic_relevancy_score": 0.782433769368772,
    "sdk": "gradio",
    "repo_type": "space",
    "runtime_stage": "RUNNING",
    "runtime_hardware_current": "cpu-basic",
    "runtime_hardware_requested": "cpu-basic",
    "runtime_replicas_current": 1,
    "runtime_replicas_requested": 1,
    "runtime_domain": "mkmenta-try-gpt-1-and-gpt-2.hf.space",
    "runtime_domain_stage": "READY",
    "actor_id": "8Y27cMbGfoZEN0tmM",
    "run_id": "5wu1wNUskjFyjUQXG"
  }
]

Use Cases

• Market Research and Analysis: Identify trending AI models to understand market dynamics.
• Competitive Intelligence: Monitor competitor activities by tracking their model releases.
• Price Monitoring: Keep track of pricing changes for various AI services.
• Content Aggregation: Compile information on new AI technologies for content creation.
• Academic Research: Gather data for studies related to AI development and adoption.
• Business Automation: Automate the collection of AI-related insights for strategic planning.

Installation and Usage

1. Search for "Huggingface Discovery Parser Spider" in the Apify Store.
2. Click "Try for free" or "Run".
3. Configure input parameters as needed.
4. Click "Start" to begin extraction.
5. Monitor progress in the log.
6. Export results in your preferred format (JSON, CSV, Excel).

Output Format

The output is a JSON array where each object represents an AI model with fields such as id, author, title, description, category, and more. Each field provides specific metadata about the model, including creation dates, likes, visibility status, and technical details like runtime hardware.

Support Section

Support

For custom/simplified outputs or bug reports, please contact:

• Email: support@getdataforme.com
• Subject line: "custom support"
• Contact form: Get Data For Me

We're here to help you get the most out of this Actor!

Error Handling

The Actor is designed to handle common errors gracefully, such as network issues or invalid input parameters. If an error occurs, it will be logged in the Apify console for troubleshooting.

Rate Limiting and Best Practices

To ensure optimal performance and avoid being rate-limited by Hugging Face, adhere to best practices such as setting reasonable item limits and spacing out requests if running multiple instances of the Actor.

---

This documentation provides a comprehensive guide to using the Huggingface Discovery Parser Spider effectively. For any further assistance or customization needs, please reach out through our support channels.