Web Search Finance

Web Search for Finance Data

The container has internet access. Use Python requests to fetch data. Do NOT use fake URLs like api.example.com.

WebFetch is disabled

Do not use WebFetch. It is blocked in this environment because Claude Code's WebFetch can hang forever with no timeout (upstream bug). Use Bash + Python requests with explicit timeout=10 (or curl --max-time 30) instead. WebSearch is still available for discovery, but prefer direct API calls below once you know the data source.

1. SEC EDGAR — Financial Statements (US public companies)

import requests, json

# Step 1: Get company CIK from ticker
ticker = "HD"  # The Home Depot
r = requests.get(
    f"https://efts.sec.gov/LATEST/search-index?q=%22{ticker}%22&dateRange=custom&startdt=2024-01-01&enddt=2025-01-01&forms=10-K",
    headers={"User-Agent": "research@example.com"}
)

# Better: use the company tickers JSON
r = requests.get("https://www.sec.gov/files/company_tickers.json",
                 headers={"User-Agent": "research@example.com"})
tickers = r.json()
# Find by ticker symbol
cik = None
for entry in tickers.values():
    if entry['ticker'].upper() == ticker.upper():
        cik = str(entry['cik_str']).zfill(10)
        break
print("CIK:", cik)

# Step 2: Get company facts (all financial data)
r = requests.get(
    f"https://data.sec.gov/api/xbrl/companyfacts/CIK{cik}.json",
    headers={"User-Agent": "research@example.com"}
)
facts = r.json()

# Step 3: Extract specific metric, e.g. Cost of Goods Sold
cogs = facts['facts']['us-gaap'].get('CostOfGoodsSoldAndServicesSold') or \
       facts['facts']['us-gaap'].get('CostOfRevenue') or \
       facts['facts']['us-gaap'].get('CostOfGoodsSold')
if cogs:
    for entry in sorted(cogs['units']['USD'], key=lambda x: x.get('end',''), reverse=True):
        if entry.get('form') == '10-K' and entry.get('fp') == 'FY':
            print(entry['end'], entry['val'])
            break

# Common GAAP tags:
# Revenues / RevenueFromContractWithCustomerExcludingAssessedTax
# CostOfGoodsSoldAndServicesSold / CostOfRevenue
# InventoryNet
# NetIncomeLoss
# OperatingIncomeLoss
# Assets / Liabilities / StockholdersEquity

2. Yahoo Finance — Quick price/fundamentals lookup

import requests

def yf_get(ticker, module="incomeStatementHistory"):
    url = f"https://query1.finance.yahoo.com/v10/finance/quoteSummary/{ticker}"
    r = requests.get(url, params={"modules": module},
                     headers={"User-Agent": "Mozilla/5.0"})
    return r.json()["quoteSummary"]["result"][0][module]

# Income statement (annual)
income = yf_get("HD", "incomeStatementHistory")
for stmt in income["incomeStatementHistory"]:
    print(stmt["endDate"]["fmt"],
          "Revenue:", stmt.get("totalRevenue", {}).get("raw"),
          "Net Income:", stmt.get("netIncome", {}).get("raw"))

# Balance sheet
balance = yf_get("HD", "balanceSheetHistory")
for stmt in balance["balanceSheetStatements"]:
    print(stmt["endDate"]["fmt"],
          "Inventory:", stmt.get("inventory", {}).get("raw"))

# Key stats (market cap, P/E, etc.)
stats = yf_get("HD", "defaultKeyStatistics")

3. World Bank — Macro data (GDP, CPI, gross savings, etc.)

import requests

# GDP current USD: NY.GDP.MKTP.CD | CPI: FP.CPI.TOTL.ZG | Gross savings % GDP: NY.GNS.ICTR.ZS
def wb_get(country, indicator, start=2020, end=2024):
    url = f"https://api.worldbank.org/v2/country/{country}/indicator/{indicator}"
    r = requests.get(
        url,
        params={"format": "json", "date": f"{start}:{end}", "per_page": 100},
        timeout=10,
    )
    r.raise_for_status()
    data = r.json()[1]
    return {d["date"]: d["value"] for d in data if d["value"] is not None}

gdp = wb_get("US", "NY.GDP.MKTP.CD")
cpi = wb_get("US", "FP.CPI.TOTL.ZG")
savings = wb_get("CN", "NY.GNS.ICTR.ZS", start=2001, end=2010)

# Multi-country scan (e.g. "savings > 35% every year 2001-2010"):
def wb_countries_above_threshold(indicator, years, threshold):
    url = f"https://api.worldbank.org/v2/country/all/indicator/{indicator}"
    r = requests.get(
        url,
        params={
            "format": "json",
            "date": f"{min(years)}:{max(years)}",
            "per_page": 20000,
        },
        timeout=30,
    )
    r.raise_for_status()
    rows = r.json()[1]
    by_country = {}
    for row in rows:
        if row["value"] is None:
            continue
        by_country.setdefault(row["country"]["value"], {})[row["date"]] = row["value"]
    year_set = {str(y) for y in years}
    hits = []
    for name, series in by_country.items():
        if year_set <= set(series.keys()) and all(series[y] > threshold for y in year_set):
            hits.append(name)
    return sorted(hits)

# wb_countries_above_threshold("NY.GNS.ICTR.ZS", range(2001, 2011), 35)

4. FRED (Federal Reserve) — Interest rates, economic series

import requests

# Free API, no key needed for most series
def fred_get(series_id, start="2020-01-01"):
    url = "https://fred.stlouisfed.org/graph/fredgraph.csv"
    r = requests.get(url, params={"id": series_id, "vintage_date": start})
    lines = r.text.strip().split('\n')
    return dict(line.split(',') for line in lines[1:] if '.' in line.split(',')[1])

# Common series: FEDFUNDS, DGS10, CPIAUCSL, GDP, UNRATE, T10Y2Y
rates = fred_get("FEDFUNDS")

5. When data is unavailable — use reasonable estimates

If all sources fail for a specific number (e.g. private market size data):

# State the source and use a published estimate
market_data = {
    "us_home_improvement_market_2023_usd_bn": 567,   # HIRI / Statista estimate
    "us_home_improvement_market_2024_usd_bn": 589,
    "source": "Home Improvement Research Institute (HIRI) 2024 report estimate"
}

Quick Reference: Common Tickers & CIKs

Error Handling

try:
    r = requests.get(url, headers={"User-Agent": "research@example.com"}, timeout=10)
    r.raise_for_status()
    data = r.json()
except Exception as e:
    print(f"Fetch failed: {e}")
    # Fall back to hardcoded estimate with source citation