SEC EDGAR 技能：Python 库使用指南与财务数据分析教程

sec-edgar-skill by eng0ai/eng0-template-skills

78 周安装量

3 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/eng0ai/eng0-template-skills --skill sec-edgar-skill

Python Web框架数据分析金融科技

🇨🇳中文介绍

SEC EDGAR 技能 - 文件分析

前提条件

关键：在任何 EdgarTools 操作之前运行此设置：

from edgar import set_identity
set_identity("Your Name your.email@example.com")  # SEC 要求身份识别

这是 SEC 的法律要求。没有它，操作将失败。

安装

必须安装 EdgarTools：

pip install edgartools

令牌效率策略

始终首先使用 .to_context() - 它提供的摘要可减少 56-89% 的令牌：

对象	`repr()` 令牌数	`.to_context()` 令牌数

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

访问文件的三种方式

1. 已发布文件 - 批量跨公司分析

from edgar import get_filings

# 获取最近的 10-K 文件
filings = get_filings(form="10-K")

# 按日期范围筛选
filings = get_filings(form="10-K", year=2024, quarter=1)

# 多种表格类型
filings = get_filings(form=["10-K", "10-Q"])

2. 当前文件 - 实时监控

from edgar import get_current_filings

# 从 RSS 源获取今天的文件
current = get_current_filings()

# 按表格类型筛选
current_10k = get_current_filings().filter(form="10-K")

3. 公司文件 - 单一实体分析

from edgar import Company

# 通过股票代码
company = Company("AAPL")

# 通过 CIK
company = Company("0000320193")

# 获取公司的文件
filings = company.get_filings(form="10-K")
latest_10k = filings.latest()

方法 1：实体事实 API（快速，多期间）

最适合跨期间比较趋势：

company = Company("AAPL")

# 获取多个期间的利润表
income = company.income_statement(periods=5)
print(income)  # 显示 5 年的数据

# 获取资产负债表
balance = company.balance_sheet(periods=3)

# 获取现金流量表
cashflow = company.cash_flow_statement(periods=3)

方法 2：文件 XBRL（详细，单期间）

最适合全面的单文件分析：

company = Company("AAPL")
filing = company.get_filings(form="10-K").latest()

# 获取 XBRL 数据
xbrl = filing.xbrl()

# 访问财务报表
statements = xbrl.statements
income_stmt = statements.income_statement
balance_sheet = statements.balance_sheet
cash_flow = statements.cash_flow_statement

工作流程 1：比较公司间收入

from edgar import Company

companies = ["AAPL", "MSFT", "GOOGL"]
for ticker in companies:
    company = Company(ticker)
    income = company.income_statement(periods=3)
    print(f"\n{ticker} 收入趋势：")
    print(income)

工作流程 2：分析最新的 10-K 文件

from edgar import Company

company = Company("NVDA")
filing = company.get_filings(form="10-K").latest()

# 获取文件元数据
print(filing.to_context())

# 获取全文（昂贵 - 50K+ 令牌）
# text = filing.text()

# 获取特定章节
# items = filing.items()  # 风险因素、管理层讨论与分析等

工作流程 3：追踪内幕交易

from edgar import Company

company = Company("TSLA")
insider_filings = company.get_filings(form="4")  # 表格 4 = 内幕交易

for filing in insider_filings[:10]:
    print(filing.to_context())

工作流程 4：按行业监控近期文件

from edgar import get_filings

# 获取最近的科技公司 10-K 文件（使用 SIC 代码）
# SIC 7370-7379 = 计算机编程、数据处理
filings = get_filings(form="10-K", year=2024)
# 检索后按公司特征筛选

工作流程 5：多年财务趋势

from edgar import Company

company = Company("AMZN")

# 5 年利润表
income = company.income_statement(periods=20)  # 20 个季度 = 5 年

# 5 年资产负债表
balance = company.balance_sheet(periods=20)

print("利润表趋势：")
print(income)
print("\n资产负债表趋势：")
print(balance)

filing = company.get_filings(form="10-K").latest()

# 在文件文档内搜索（在 10-K 中查找文本）
results = filing.search("climate risk")

# 搜索 API 文档（查找如何使用 EdgarTools）
docs_results = filing.docs.search("how to extract")

不要混淆这两者！

company = Company("AAPL")
company.to_context()  # 摘要及可用操作
company.name          # 公司名称
company.cik           # CIK 号码
company.sic           # SIC 代码
company.industry      # 行业描述
company.get_filings() # 访问文件

filing.to_context()   # 摘要
filing.form           # 表格类型 (10-K, 10-Q 等)
filing.filing_date    # 提交日期
filing.accession_number
filing.text()         # 完整文档文本（昂贵）
filing.markdown()     # Markdown 格式
filing.xbrl()         # XBRL 财务数据
filing.items()        # 文档章节

XBRL（财务数据）

xbrl = filing.xbrl()
xbrl.to_context()     # 摘要
xbrl.statements       # 所有财务报表
xbrl.facts            # 个别事实/指标

报表（财务报表）

stmt = xbrl.statements.income_statement
print(stmt)           # ASCII 表格格式
stmt.to_dataframe()   # Pandas DataFrame

反模式（避免这些）

不要：从原始文本解析财务数据

# 错误 - 昂贵且容易出错
text = filing.text()
# 尝试从文本中正则解析收入...

要：使用结构化的 XBRL 数据

# 正确 - 结构化且准确
income = company.income_statement(periods=3)

不要：当只需要元数据时加载完整文件

# 错误 - 浪费令牌
text = filing.text()  # 50K+ 令牌

要：首先使用上下文

# 正确 - 最少令牌
print(filing.to_context())  # ~50 令牌

表格类型快速参考

表格	描述	用例
10-K	年度报告	全年财务数据、业务描述
10-Q	季度报告	季度财务数据
8-K	当期报告	重大事件（并购、高管变动）
DEF 14A	委托声明书	高管薪酬、董事会信息
4	内幕交易	内部人士股票交易
13F	机构持仓	对冲基金持有的资产
S-1	IPO 注册	上市前文件
424B	招股说明书	债券/股票发行

from edgar import Company

try:
    company = Company("INVALID")
except Exception as e:
    print(f"未找到公司：{e}")

# 检查文件是否存在
filings = company.get_filings(form="10-K")
if len(filings) == 0:
    print("未找到 10-K 文件")

检索前筛选：使用表格类型、日期过滤器
使用实体事实 API 分析趋势：比解析多个文件更快
批量操作：在循环中处理多个公司
缓存结果：存储频繁访问的数据

详细文档请参阅：

或使用内置文档：

from edgar import Company
company = Company("AAPL")
company.docs.search("how to get revenue")

🇺🇸English

SEC EDGAR Skill - Filing Analysis

Prerequisites

CRITICAL: Run this setup before ANY EdgarTools operations:

from edgar import set_identity
set_identity("Your Name your.email@example.com")  # SEC requires identification

This is a SEC legal requirement. Operations will fail without it.

Installation

EdgarTools must be installed:

pip install edgartools

Token Efficiency Strategy

ALWAYS use.to_context() first - it provides summaries with 56-89% fewer tokens:

Object	`repr()` tokens	`.to_context()` tokens	Savings
Company	~750	~75	90%
Filing	~125	~50	60%
XBRL	~2,500	~275	89%
Statement	~1,250	~400	68%

Rule: Call .to_context() first to understand what's available, then drill down.

Three Ways to Access Filings

1. Published Filings - Bulk Cross-Company Analysis

from edgar import get_filings

# Get recent 10-K filings
filings = get_filings(form="10-K")

# Filter by date range
filings = get_filings(form="10-K", year=2024, quarter=1)

# Multiple form types
filings = get_filings(form=["10-K", "10-Q"])

2. Current Filings - Real-Time Monitoring

from edgar import get_current_filings

# Get today's filings from RSS feed
current = get_current_filings()

# Filter by form type
current_10k = get_current_filings().filter(form="10-K")

3. Company Filings - Single Entity Analysis

from edgar import Company

# By ticker
company = Company("AAPL")

# By CIK
company = Company("0000320193")

# Get company's filings
filings = company.get_filings(form="10-K")
latest_10k = filings.latest()

Financial Data Access

Method 1: Entity Facts API (Fast, Multi-Period)

Best for comparing trends across periods:

company = Company("AAPL")

# Get income statement for multiple periods
income = company.income_statement(periods=5)
print(income)  # Shows 5 years of data

# Get balance sheet
balance = company.balance_sheet(periods=3)

# Get cash flow
cashflow = company.cash_flow_statement(periods=3)

Method 2: Filing XBRL (Detailed, Single Period)

Best for comprehensive single-filing analysis:

company = Company("AAPL")
filing = company.get_filings(form="10-K").latest()

# Get XBRL data
xbrl = filing.xbrl()

# Access financial statements
statements = xbrl.statements
income_stmt = statements.income_statement
balance_sheet = statements.balance_sheet
cash_flow = statements.cash_flow_statement

Common Workflows

Workflow 1: Compare Revenue Across Companies

from edgar import Company

companies = ["AAPL", "MSFT", "GOOGL"]
for ticker in companies:
    company = Company(ticker)
    income = company.income_statement(periods=3)
    print(f"\n{ticker} Revenue Trend:")
    print(income)

Workflow 2: Analyze Latest 10-K

from edgar import Company

company = Company("NVDA")
filing = company.get_filings(form="10-K").latest()

# Get filing metadata
print(filing.to_context())

# Get full text (expensive - 50K+ tokens)
# text = filing.text()

# Get specific sections
# items = filing.items()  # Risk factors, MD&A, etc.

Workflow 3: Track Insider Trading

from edgar import Company

company = Company("TSLA")
insider_filings = company.get_filings(form="4")  # Form 4 = insider trades

for filing in insider_filings[:10]:
    print(filing.to_context())

Workflow 4: Monitor Recent Filings by Sector

from edgar import get_filings

# Get recent tech 10-Ks (use SIC codes)
# SIC 7370-7379 = Computer Programming, Data Processing
filings = get_filings(form="10-K", year=2024)
# Filter by company characteristics after retrieval

Workflow 5: Multi-Year Financial Trend

from edgar import Company

company = Company("AMZN")

# 5-year income statement
income = company.income_statement(periods=20)  # 20 quarters = 5 years

# 5-year balance sheet
balance = company.balance_sheet(periods=20)

print("Income Statement Trend:")
print(income)
print("\nBalance Sheet Trend:")
print(balance)

Search Within Filings

CRITICAL DISTINCTION:

filing = company.get_filings(form="10-K").latest()

# Search WITHIN the filing document (finds text in the 10-K)
results = filing.search("climate risk")

# Search API DOCUMENTATION (finds how to use EdgarTools)
docs_results = filing.docs.search("how to extract")

Do NOT mix these up!

Key Objects Reference

Company

company = Company("AAPL")
company.to_context()  # Summary with available actions
company.name          # Company name
company.cik           # CIK number
company.sic           # SIC code
company.industry      # Industry description
company.get_filings() # Access filings

Filing

filing.to_context()   # Summary
filing.form           # Form type (10-K, 10-Q, etc.)
filing.filing_date    # Date filed
filing.accession_number
filing.text()         # Full document text (EXPENSIVE)
filing.markdown()     # Markdown format
filing.xbrl()         # XBRL financial data
filing.items()        # Document sections

XBRL (Financial Data)

xbrl = filing.xbrl()
xbrl.to_context()     # Summary
xbrl.statements       # All financial statements
xbrl.facts            # Individual facts/metrics

Statement (Financial Statement)

stmt = xbrl.statements.income_statement
print(stmt)           # ASCII table format
stmt.to_dataframe()   # Pandas DataFrame

Anti-Patterns (Avoid These)

DON'T: Parse financials from raw text

# BAD - expensive and error-prone
text = filing.text()
# try to regex parse revenue from text...

DO: Use structured XBRL data

# GOOD - structured and accurate
income = company.income_statement(periods=3)

DON'T: Load full filing when you only need metadata

# BAD - wastes tokens
text = filing.text()  # 50K+ tokens

DO: Use context first

# GOOD - minimal tokens
print(filing.to_context())  # ~50 tokens

Form Types Quick Reference

Form	Description	Use Case
10-K	Annual report	Full-year financials, business description
10-Q	Quarterly report	Quarterly financials
8-K	Current report	Material events (M&A, exec changes)
DEF 14A	Proxy statement	Executive comp, board info
4	Insider trading	Stock transactions by insiders
13F	Institutional holdings	What hedge funds own
S-1	IPO registration	Pre-IPO filings
424B	Prospectus

Error Handling

from edgar import Company

try:
    company = Company("INVALID")
except Exception as e:
    print(f"Company not found: {e}")

# Check if filings exist
filings = company.get_filings(form="10-K")
if len(filings) == 0:
    print("No 10-K filings found")

Performance Tips

Filter before retrieving : Use form type, date filters
Use Entity Facts API for trends : Faster than parsing multiple filings
Batch operations : Process multiple companies in loops
Cache results : Store frequently accessed data

Reference Documentation

For detailed documentation, see:

Or use the built-in docs:

from edgar import Company
company = Company("AAPL")
company.docs.search("how to get revenue")

Weekly Installs

Repository

eng0ai/eng0-tem…e-skills

GitHub Stars

First Seen

Jan 22, 2026

Security Audits

Gen Agent Trust HubFail SocketPass SnykWarn

Installed on

codex69

gemini-cli66

opencode66

github-copilot63

cursor63

amp57

DOCX文件创建、编辑与分析完整指南 - 使用docx-js、Pandoc和Python脚本

51,800 周安装

公司	~750	~75	90%
文件	~125	~50	60%
XBRL	~2,500	~275	89%
报表	~1,250	~400	68%