get russell 2000 tickers in python

russell2000.py

import requests
import csv
import io

def get_russell_2000_tickers() -> list[str]:
    """
    Fetches current Russell 2000 constituents from iShares IWM ETF holdings CSV.
    Pure Python + built-in csv module. No pandas. Handles the messy header + huge disclaimer.
    Returns clean tickers ready for yfinance (BRK.B → BRK-B).
    """
    url = "https://www.ishares.com/us/products/239710/ishares-russell-2000-etf/1467271812596.ajax?fileType=csv&fileName=IWM"
    
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/csv"
    }
    
    resp = requests.get(url, headers=headers, timeout=20)
    resp.raise_for_status()
    
    text = resp.text
    lines = [line.strip() for line in text.splitlines() if line.strip()]
    
    # Find the start of the real data (header row that contains "Ticker")
    start_idx = 0
    for i, line in enumerate(lines):
        if line.startswith('"Ticker"') or ('Ticker' in line and 'Name' in line):
            start_idx = i
            break
    else:
        # Fallback: first line with many commas
        for i, line in enumerate(lines):
            if line.count(',') > 8:
                start_idx = i
                break
    
    # Parse only the data section with csv module
    data_section = '\n'.join(lines[start_idx:])
    csv_file = io.StringIO(data_section)
    reader = csv.reader(csv_file)
    
    tickers = []
    header = next(reader, None)  # skip header row
    
    if header:
        # Find Ticker column index (handles slight column name variations)
        ticker_col = next((i for i, col in enumerate(header) if col and ('Ticker' in col or 'Symbol' in col)), 0)
        
        for row in reader:
            if not row or len(row) <= ticker_col:
                continue
            
            ticker = row[ticker_col].strip()
            
            # Stop when we hit the legal disclaimer text
            if (ticker.startswith('The content contained herein') or
                ticker.startswith('©') or
                ticker.startswith('Holdings subject to change') or
                'BlackRock' in ticker):
                break
            
            # Skip junk rows
            if (not ticker or 
                ticker == '-' or 
                ticker.startswith('RTYM') or          # futures
                len(ticker) < 2):
                continue
            
            # Clean for yfinance
            ticker = ticker.replace('.', '-')
            tickers.append(ticker)
    
    clean_tickers = sorted(set(tickers))
    print(f"✅ Successfully parsed {len(clean_tickers)} Russell 2000 tickers")
    return clean_tickers
print(get_russell_2000_tickers())