메뉴
How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K/10-Q data, or company financials.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/anthropics/cwc-workshops --skill edgartools-sec-data명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | edgartools-sec-data |
| description | How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K/10-Q data, or company financials. |
edgartools is the desk's standard way to read SEC data. It is preinstalled in your environment. Work in Python (a script or python -c), not by fetching sec.gov pages by hand.
The SEC requires a contact identity on automated requests. Do this before any other call, every session:
from edgar import set_identity
set_identity("Research Desk workshop attendee@example.com") # use the EDGAR_IDENTITY value you were given
(Equivalently, the EDGAR_IDENTITY environment variable, exported before running Python.)
from edgar import Company
company = Company("NVDA") # by ticker (or CIK)
company.name, company.cik, company.industry
filings = company.get_filings(form="10-K") # also "10-Q", "8-K", "DEF 14A", ...
latest_10k = filings.latest() # most recent of that form
latest_10q = company.get_filings(form="10-Q").latest()
latest_10k.form, latest_10k.filing_date, latest_10k.accession_no
Pick whichever of the latest 10-K / 10-Q is more recent when asked for "the most recent filing". Foreign private issuers file 20-F instead of 10-K.
filing = latest_10k
tenk = filing.obj() # rich object for 10-K/10-Q: sections, financials
# Sections (10-K item numbers; 10-Q uses Part/Item naming)
risk_factors = tenk["Item 1A"] # Risk Factors text
mda = tenk["Item 7"] # Management's Discussion & Analysis
business = tenk["Item 1"]
# Plain text of the whole filing if you need to search it
text = filing.text()
Sections are long — extract what you need rather than pasting whole sections into your reply.
financials = tenk.financials # also: company.get_financials() for the latest annual figures
income = financials.income_statement()
balance = financials.balance_sheet()
cashflow = financials.cashflow_statement()
These return tabular objects (pandas-friendly). Typical fields: total revenue, gross profit, operating income, net income, cash and equivalents, total debt, inventory, R&D expense. The same statement usually carries the prior period's column — use it for year-over-year comparisons instead of fetching another filing.
Consolidated revenue hides the story; the segment note is where concentration and regional shifts show up. Segment data lives in the financial-statement notes (ASC 280), not the primary statements:
# The segment/geography breakdown is a note, not a primary statement.
# Search the filing text for the segment note and read the tables around it.
text = filing.text()
for marker in ["Segment Information", "revenue by geographic", "Disaggregation of Revenue"]:
idx = text.find(marker)
if idx != -1:
print(text[idx : idx + 3000]) # the note's tables follow the heading
break
Report segment/geography revenue alongside the consolidated figure and call out: any region or segment that moved more than ~20% year over year, and any customer-concentration disclosure (usually phrased "one customer accounted for X% of revenue").
company.get_filings(form="10-K") is sorted; take the first two) and compare.company.get_filings(form="4") lists Form 4 insider transaction filings.dir(obj), help(obj)) or fall back to filing.text() and targeted searching, and note the fallback in your output.value / 1e6) and label them.