SEC Filing Scanner for Red Flags.py

import requests
import json
import time
from bs4 import BeautifulSoup

# ================================================
# CONFIGURATION
# ================================================

# Your SEC EDGAR user agent string
HEADERS = {'User-Agent': 'Your Name ([email protected])'}

# List of tickers you want to scan
TICKERS = ['LUCY', 'CAPR', 'PLTR']

# Red flag keywords to scan for
KEYWORDS = [
    "reversal", "reversals", "off-balance sheet", "special purpose entity",
    "related party", "nonrecurring", "inventory write-off", "EBBS",
    "insider sales", "auditor disagreement", "goodwill", "charge", "R&D write-off"
]

# SEC API base URL
SEC_TICKER_LOOKUP = "https://data.sec.gov/submissions/CIK{}.json"
SEC_FILINGS_URL = "https://www.sec.gov/Archives/edgar/data/{}/{}"

# ================================================
# UTILITY FUNCTIONS
# ================================================

def get_cik(ticker):
    """Retrieve CIK for a ticker."""
    url = f"https://www.sec.gov/files/company_tickers.json"
    r = requests.get(url, headers=HEADERS)
    data = r.json()
    for item in data.values():
        if item['ticker'].lower() == ticker.lower():
            return str(item['cik_str']).zfill(10)
    return None

def get_latest_10k_exhibit_urls(cik):
    """Fetch recent 10-K or 8-K filings and return Exhibit 99.1 URLs."""
    url = SEC_TICKER_LOOKUP.format(cik)
    r = requests.get(url, headers=HEADERS)
    data = r.json()
    filings = data['filings']['recent']
    urls = []
    for i, form in enumerate(filings['form']):
        if form in ['10-K', '8-K']:
            accession = filings['accessionNumber'][i].replace("-", "")
            full_url = f"https://www.sec.gov/Archives/edgar/data/{int(cik)}/{accession}/index.json"
            filing_data = requests.get(full_url, headers=HEADERS).json()
            for file in filing_data['directory']['item']:
                if 'ex99' in file['name'].lower() and file['name'].endswith('.htm'):
                    urls.append(f"https://www.sec.gov/Archives/edgar/data/{int(cik)}/{accession}/{file['name']}")
                    break
            time.sleep(0.2)
    return urls

def scan_filing_for_keywords(url):
    """Scan a single filing for red flag keywords."""
    r = requests.get(url, headers=HEADERS)
    soup = BeautifulSoup(r.text, 'html.parser')
    text = soup.get_text().lower()
    flags_found = [kw for kw in KEYWORDS if kw in text]
    return flags_found

# ================================================
# MAIN SCANNING LOGIC
# ================================================

watchlist = []

for ticker in TICKERS:
    cik = get_cik(ticker)
    if not cik:
        print(f"[!] CIK not found for {ticker}")
        continue

    exhibit_urls = get_latest_10k_exhibit_urls(cik)
    red_flags = []

    for url in exhibit_urls:
        flags = scan_filing_for_keywords(url)
        red_flags.extend(flags)
        time.sleep(0.5)

    score = len(set(red_flags))
    if score > 0:
        watchlist.append((ticker, score, list(set(red_flags))))

# Sort tickers by red flag score
watchlist = sorted(watchlist, key=lambda x: x[1], reverse=True)

# ================================================
# DISPLAY WATCHLIST
# ================================================

print("\n🔍 Red Flag Watchlist (Most Concerning at Top):")
for ticker, score, flags in watchlist:
    print(f"{ticker}: {score} red flags → {', '.join(flags)}")