replaces standard requests with curl_cffi to avoid 403 errors in BLS_CPI_Category

import-automation/executor/requirements.txt

@@ -6,6 +6,7 @@ beautifulsoup4
 chardet
 chromedriver_py
 croniter
+curl_cffi
 dataclasses
 datacommons
 datacommons_client

statvar_imports/us_bls/cpi_category/cpi_category_download.py

@@ -19,7 +19,7 @@
 '''
 
 
-import requests
+from curl_cffi import requests
 import os
 import zipfile
 import re
@@ -64,7 +64,7 @@ def download_file(url: str, save_path: str ,timeout: int = 60):
     }
     try:
         logging.info(f"Attempting to download: {url} with timeout {timeout} seconds.")
-        response = requests.get(url, stream=True, headers=headers, timeout=timeout)
+        response = requests.get(url, stream=True, headers=headers, timeout=timeout, impersonate="chrome124") # To avoid 403 errors, we use impersonate to mimic a real browser's TLS fingerprint.
         response.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx)
 
         # Ensure the directory for save_path exists