snippets to get ticker lists from ishares catalogue CSVs

any_tickers_ishares.py

import requests
import csv
import io

def get_ishares_tickers(etf_ticker: str = "IVV") -> list[str]:
    """
    Fetches current constituents from any major iShares US equity ETF via their 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).
    
    Supported ETFs (add more easily!):
        IVV  → S&P 500
        IWM  → Russell 2000
        IWB  → Russell 1000
        IWV  → Russell 3000
        IJH  → Core S&P Mid-Cap
        IJR  → Core S&P Small-Cap
        ITOT → Core S&P Total U.S. Stock Market
    """
    etf_ticker = etf_ticker.upper().strip()
    
    # ticker -> (product_id, slug, filename_base)
    # To add a new ETF: go to its iShares product page → the URL contains /products/XXXXX/slug-here/
    etf_map = {
        "IVV":  ("239726", "ishares-core-sp-500-etf",          "IVV"),
        "IWM":  ("239710", "ishares-russell-2000-etf",         "IWM"),
        "IWB":  ("239707", "ishares-russell-1000-etf",         "IWB"),
        "IWV":  ("239714", "ishares-russell-3000-etf",         "IWV"),
        "IJH":  ("239763", "ishares-core-sp-midcap-etf",       "IJH"),
        "IJR":  ("239774", "ishares-core-sp-smallcap-etf",     "IJR"),
        "ITOT": ("239724", "ishares-core-sp-total-us-stock-market-etf", "ITOT"),
        # Example of how to add more:
        # "IWF": ("239706", "ishares-russell-1000-growth-etf", "IWF"),
    }
    
    if etf_ticker not in etf_map:
        supported = ", ".join(sorted(etf_map.keys()))
        raise ValueError(
            f"ETF '{etf_ticker}' not in mapping yet.\n"
            f"Currently supported: {supported}\n"
            "Add it to the etf_map dict (product ID + slug from the iShares product page URL)."
        )
    
    product_id, slug, base = etf_map[etf_ticker]
    
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/csv"
    }
    
    # Modern format (most ETFs)
    url = (
        f"https://www.ishares.com/us/products/{product_id}/{slug}/"
        f"1467271812596.ajax?fileType=csv&fileName={base}_holdings&dataType=fund"
    )
    
    resp = requests.get(url, headers=headers, timeout=20)
    
    # Fallback for a few older-style ETFs (e.g. original IWM)
    if resp.status_code != 200:
        url = (
            f"https://www.ishares.com/us/products/{product_id}/{slug}/"
            f"1467271812596.ajax?fileType=csv&fileName={base}"
        )
        resp = requests.get(url, headers=headers, timeout=20)
    
    resp.raise_for_status()
    
    # === Exact same robust parsing you already had ===
    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
        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
                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)} {etf_ticker} tickers")
    return clean_tickers

sp500_ishares_tickers.py

def get_sp500_tickers() -> list[str]:
    """
    Fetches current S&P 500 constituents from iShares IVV 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/239726/ishares-core-sp-500-etf/1467271812596.ajax?fileType=csv&fileName=IVV_holdings&dataType=fund"
   
    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)} S&P 500 tickers")
    return clean_tickers