SEC EDGAR AI Scraper - LLM-ready filings, RAG chunks & signals

SEC EDGAR AI Scraper turns SEC filings into clean JSON, CSV, Excel, NDJSON, or Markdown. Use it to scrape SEC EDGAR data from official SEC sources without managing CIK lookup, rate limits, filing downloads, XBRL parsing, or text extraction yourself.

This Actor works like a simple SEC filings API on Apify. Pick a mode, enter one or more tickers, ciks, companies, or domains, then start the run. Results are saved to an Apify dataset or to a file in the key-value store.

What can you scrape from SEC EDGAR?

Need	Mode to start with	What you get
Company filing list	company_filings	Recent filings for a company
Annual reports	form_10k_filings	10-K filing records
Quarterly reports	form_10q_filings	10-Q filing records
Current reports	form_8k_filings	8-K items with severity tags
Insider trades	form_4_filings	Form 4 transaction rows
Fund holdings	form_13f_filings	13F holdings by CUSIP
Company facts	xbrl_facts	XBRL fact rows
Financial statements	xbrl_statements	Normalized statement rows
Filing text for AI	filing_markdown	Section-aware Markdown
Text chunks for AI search	filing_chunks	Stable filing chunks
Year-over-year changes	section_diff	Paragraph-level filing changes
Enforcement records	litigation_releases	SEC release records

Why use this SEC EDGAR scraper?

• One Actor for many SEC workflows: filings, XBRL facts, insider trades, 13F holdings, proxy data, enforcement records, and AI-ready text.
• Clean output: every row includes sha256, mode, cik, accession, filing_date, and payload.
• Easy automation: run from the Apify Console, API, schedules, webhooks, or integrations.
• Built for repeat work: use the same input daily or weekly and send results to your app, spreadsheet, database, or AI workflow.

How to scrape SEC EDGAR data

1. Open the Actor on Apify and click Try for free.
2. Choose a mode, such as form_4_filings or company_filings.
3. Enter tickers, ciks, companies, or domains.
4. Optional: add date_from, date_to, forms, or mode-specific filters.
5. Pick output_format: json, ndjson, csv, xlsx, or markdown.
6. Click Save & Start and download results from the Output tab.

For the easiest first test, keep the default mode as cik_ticker_map and use the prefilled ticker MDB.

Input example

{
  "mode": "form_4_filings",
  "tickers": ["MSFT"],
  "date_from": "2026-01-01",
  "transaction_codes": ["S", "P"],
  "output_format": "json"
}

Example for AI-ready filing text:

{
  "mode": "filing_markdown",
  "tickers": ["AAPL"],
  "form": "10-K",
  "date_from": "2025-01-01",
  "output_format": "markdown"
}

Output example

{
  "sha256": "9f1c2a...",
  "mode": "form_4_filings",
  "cik": "0000789019",
  "accession": "0001062993-26-001234",
  "filing_date": "2026-02-14",
  "payload": {
    "issuer": "Microsoft Corp",
    "reporter": "Example Officer",
    "transaction_date": "2026-02-12",
    "transaction_code": "S",
    "shares": 1200,
    "price_per_share": 415.2
  }
}

You can download SEC EDGAR data as JSON, CSV, Excel, NDJSON, or Markdown. JSON streams to the Apify dataset. Other formats are saved as files in the key-value store.

SEC EDGAR data fields

Field	Meaning
sha256	Stable fingerprint for change checks
mode	The mode that created the row
cik	SEC company identifier
accession	SEC filing accession number
filing_date	Filing date, when available
payload	The mode-specific data

How much does it cost to scrape SEC EDGAR?

This Actor uses pay-per-event pricing. The first 20 result rows in a run are not billed by result-row events. Apify start events may still apply.

Common row prices:

Data type	Example modes	Price
CIK / ticker lookup	cik_ticker_map	$0.0001 per row
Filing index row	company_filings, filings_search	$0.0004 per row
Insider trade	form_4_filings	$0.0005 per row
Holding row	form_13f_filings	$0.0005 per row
XBRL fact	xbrl_facts	$0.0002 per row
Filing record	form_10k_filings, form_8k_filings	$0.002 per row
Filing Markdown	filing_markdown	$0.003 per row
AI filing analysis	ai_summary, ai_importance	$0.04 per row

For full pricing, check the Pricing tab on the Actor page.

Tips for best results

• Start with mid-size companies such as MDB, NET, or SHOP when testing.
• Use date_from and date_to to keep runs small.
• Use output_format: "markdown" when you want text for ChatGPT, Claude, or a search index.
• Large 10-K filings can produce many rows in text-heavy modes, so test one ticker before running a long list.
• For scheduled runs, reuse the same input so row fingerprints can help detect changes.

Use from Python

from apify_client import ApifyClient

client = ApifyClient("<APIFY_TOKEN>")
run = client.actor("dominvo/sec-edgar-ai-scraper").call(run_input={
    "mode": "company_filings",
    "tickers": ["MDB"],
    "date_from": "2026-01-01",
})

for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(row["filing_date"], row["payload"])

Other Actors by this creator

Need UK company data too? Try UK Companies House API Scraper for company profiles, PSC ownership, officers, filings, charges, insolvency, and accounts.

FAQ and support

Is this an official SEC tool?

No. This is an independent Actor that reads public SEC EDGAR data from official SEC sources.

Do I need a SEC API key?

No. SEC EDGAR does not require an API key for these public endpoints.

Can I schedule SEC filing monitoring?

Yes. Use Apify schedules to run the same input daily, weekly, or monthly.

Is this legal?

SEC EDGAR data is public U.S. government data. You are responsible for how you use the results.

Where do I get help?

Open the Issues tab on the Actor page for bugs, missing modes, or feature requests.