ParseForge
Hugging Face Papers Scraper
parseforge/huggingface-papers-scraper
EducationDeveloper toolsOther
Scrapes Hugging Face papers by search query or trending feed. Returns each paper as a flat row with title, authors, abstract, upvotes, and URL. Export to CSV, JSON, Excel, or XML.
- Total users
- 8
- Monthly active
- 1
- Total runs
- 315
- Bookmarked
- 1
- Rating
- Not rated yet
- Last modified
- 9 days ago
Overview
Hugging Face Papers Scraper
Scrape Hugging Face papers by search query or trending feed, up to a million per run. Each paper comes with its title, authors, abstract, upvotes, and direct URL. No API key or login. Export to CSV, JSON, Excel, or XML.
Hugging Face's official API needs a token and rate-limits you. This reads the public papers feed directly, filtered by keyword or trending, and returns each match in one fixed schema. It is the fastest way to track artificial intelligence news and research papers without writing code.
| Who uses it | What they scrape Hugging Face for |
|---|---|
| AI researchers | Monitor new papers in their subfield without manually checking the site |
| Data scientists | Build datasets of paper metadata for trend analysis or literature reviews |
| Product managers | Track competitor research and emerging techniques in AI |
| Content creators | Find trending papers to write about or share with their audience |
What it does
This Actor collects Hugging Face papers by search query or trending feed, and returns each one as a flat row.
- 🔍 Search mode: enter any keyword like 'transformer', 'diffusion model', or 'LLM' to get matching papers.
- 📈 Trending mode: fetch the current trending papers on Hugging Face with one click.
- 📊 Flat output: every paper is a single row with title, authors, abstract, upvotes, and URL, ready for spreadsheets.
- ⚙️ Flexible limits: set maxItems from 1 to 1,000,000 to control how many papers you collect per run.
Results export to CSV, JSON, Excel, or XML, or straight from the API.
What you can do with Hugging Face data
📚 Build a research database.
A PhD student runs the Actor weekly with the query 'diffusion model' and exports the results to CSV to maintain a personal library of relevant papers.
📈 Track AI trends.
A market analyst uses trending mode daily to see which papers are gaining traction, then shares a summary with their team to inform product strategy.
🔎 Monitor competitor research.
A startup founder sets up a scheduled run for keywords like 'LLM' and 'RAG' to stay aware of new techniques from competitors and academic labs.
📰 Curate AI news.
A newsletter writer scrapes trending papers each morning and picks the most interesting ones to feature in their daily AI digest.
Why choose this scraper
| What you get | |
|---|---|
| No API key | Scrape public paper feeds without registering an app or dealing with OAuth. |
| Up-to-date | Get the latest papers as they appear on Hugging Face, including trending items. |
| Structured data | Each paper is a flat object with title, authors, abstract, upvotes, and URL. |
| Scalable | Collect up to a million papers per run, suitable for large-scale analysis. |
How it compares
This Actor is the only one in this group that scrapes Hugging Face papers. The others are OCR tools for receipts and PDFs, so they are not direct competitors for this use case.
| Feature | ParseForge | Receipt OCR API | Pdf OCR API | Artificial Intelligence News |
|---|---|---|---|---|
| Scrapes Hugging Face papers | Yes | Not listed | Not listed | Not listed |
| Search by keyword | Yes | Not listed | Not listed | Not listed |
| Trending papers feed | Yes | Not listed | Not listed | Not listed |
| Returns paper metadata (title, authors, abstract) | Yes | Not listed | Not listed | Not listed |
| No API key required | Yes | Not listed | Not listed | Not listed |
Configure the run
Drive the Actor with a search query or switch to trending mode, and set the maximum number of papers to collect. Results are returned in a consistent schema for easy export. The Input tab lists every parameter.
A first run with the defaults:
{
"maxItems": 10,
"searchQuery": "transformer"
}
A larger pull:
{
"maxItems": 200,
"searchQuery": "transformer"
}
Pricing
Pay-per-result: $0.0095 per result collected. You pay only for the results written to your dataset.
| Results collected | Approximate cost |
|---|---|
| 100 results | $0.95 |
| 1,000 results | $9.50 |
| 10,000 results | $95.00 |
New Apify accounts start with $5 in free credit.
Free users
Free-plan runs return up to 10 results as a preview. Upgrade your Apify plan to collect up to 1,000,000 results per run.
Run it
- Create a free Apify account with $5 in credit.
- Open the Hugging Face Papers Scraper.
- Set your inputs and any filters, then click Start.
- Export the results as CSV, Excel, JSON, or XML from the Dataset tab.
Run it programmatically through the Apify API (run-sync-get-dataset-items) or the ApifyClient for JavaScript and Python.
Use with AI agents (MCP)
Give an AI agent live access to Hugging Face through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:
claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/huggingface-papers-scraper"
Then prompt it in plain language to run the scraper and read back the results.
Troubleshooting
Why am I getting no results?
Make sure your searchQuery is spelled correctly and not too specific. Try a broader term like 'AI' or 'model'. Also check that mode is set to 'search' if you are using a query.
The Actor returns fewer papers than maxItems.
This can happen if there are not enough matching papers on Hugging Face for your query or trending feed. Try a different query or increase the time range if available.
I get an error about rate limiting.
The Actor includes automatic retries and delays to avoid rate limits. If you still see errors, reduce the frequency of your runs or contact support.
Some fields are empty in the output.
Not all papers have every field populated. For example, some may lack an abstract or upvotes. This is normal and reflects the source data.
FAQ
| Question | Answer |
|---|---|
| Do I need a Hugging Face API key? | No. This Actor reads the public papers feed directly, so no authentication or token is required. |
| What data does each paper include? | Each paper is returned as a flat object with fields like title, authors, abstract, upvotes, and URL. The exact fields are shown in the sample output. |
| Can I scrape trending papers? | Yes. Set the mode to 'trending' and the Actor will fetch the current trending papers on Hugging Face. |
| How many papers can I collect in one run? | You can set maxItems from 1 to 1,000,000. The Actor will stop after reaching that number. |
| Can I search by multiple keywords? | The searchQuery field accepts a single string. For multiple keywords, run the Actor multiple times or use a more complex query if supported by the site. |
| What export formats are supported? | You can export the results to CSV, JSON, Excel, or XML from the Apify dataset. |
| Is this Actor legal to use? | Yes, it only accesses publicly available data. However, you should respect Hugging Face's terms of service and robots.txt. |
| Can I schedule this Actor to run automatically? | Yes, you can set up a schedule in Apify to run it daily, weekly, or at any interval. |
| What if I get no results? | Check your search query for typos or try a broader term. Also ensure the mode is set correctly. |
| Does this Actor handle pagination? | Yes, it automatically paginates through results until it reaches maxItems or no more papers are available. |
Related actors
Browse the full ParseForge collection for more scrapers.
🆘 Need help? Email parseforge@protonmail.com with your run ID, your input, and what you expected.
⚠️ Disclaimer. This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by Hugging Face, Inc. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.
Input
| Field | Type | What it does | Default |
|---|---|---|---|
| maxItems | integer | How many papers to collect per run. | 10 |
| searchQuery | string | Search papers by keyword. Example: 'transformer', 'diffusion model', 'LLM'. | transformer |
| mode | string (2 options) | Search or trending. | search |
Pricing
from $9.00 per 1,000 results
| Charged for | What it is | Price each |
|---|---|---|
| result | Single result in the default dataset. | $0.009 to $0.0095 |
Tiered: the lower figure is the price on a higher Apify plan. Billing and the free credit live on Apify.
API
One POST returns the dataset directly. Same shape for every scraper in the library, so swapping the slug is the only change.
curl -X POST "https://api.apify.com/v2/acts/parseforge~huggingface-papers-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"helloWorld": 123
}' Examples
Input that runs as-is.
{
"helloWorld": 123
} Reviews
No reviews yet. Be the first.
Issues
We build and maintain this scraper, so a problem with it comes to us. Report it on the Apify listing and the thread stays attached to the scraper where the next person can find it: open an issue.
Broken and urgent, or you would rather not post in public? Write to parseforge@protonmail.com and it reaches the people who wrote it.