Implement Ken French factor download and cache fallback

factor_attribution.py

@@ -4,12 +4,32 @@ import io
 import zipfile
 from pathlib import Path
 from urllib.error import URLError
+from urllib.request import Request, urlopen
 
 import pandas as pd
 
+KEN_FRENCH_DAILY_FF5_ZIP_URL = (
+    "https://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/"
+    "F-F_Research_Data_5_Factors_2x3_daily_CSV.zip"
+)
+
+SOURCE_PARSE_EXCEPTIONS = (
+    zipfile.BadZipFile,
+    UnicodeDecodeError,
+    StopIteration,
+    KeyError,
+    ValueError,
+    pd.errors.ParserError,
+)
+
 
 def _download_kf_zip_bytes() -> bytes:
-    raise NotImplementedError
+    request = Request(
+        KEN_FRENCH_DAILY_FF5_ZIP_URL,
+        headers={"User-Agent": "quant-factor-attribution/0.1"},
+    )
+    with urlopen(request, timeout=30) as response:
+        return response.read()
 
 
 def _parse_kf_daily_csv(raw_bytes: bytes) -> pd.DataFrame:
@@ -46,6 +66,12 @@ def load_external_us_factors(cache_dir: Path | str = "data/factors") -> pd.DataF
             return pd.read_csv(cache_path, index_col=0, parse_dates=True)
         raise
 
-    factors = _parse_kf_daily_csv(raw_bytes)
+    try:
+        factors = _parse_kf_daily_csv(raw_bytes)
+    except SOURCE_PARSE_EXCEPTIONS:
+        if cache_path.exists():
+            return pd.read_csv(cache_path, index_col=0, parse_dates=True)
+        raise
+
     factors.to_csv(cache_path)
     return factors