.

scrapers/document_to_markdown.py

@@ -511,12 +511,13 @@ def find_title_in_capture_index(docid: str, base_dir: str) -> str | None:
     return None
 
 
-def process_file(path: str, out_dir: str, overwrite: bool = False) -> tuple[bool, str]:
+def process_file(path: str, out_dir: str, overwrite: bool = False, verbose: bool = False) -> tuple[bool, str]:
     """Process one JSON file. Returns (success, output_path_or_error)."""
     base = os.path.basename(path)
     name, _ = os.path.splitext(base)
 
-    logger.debug(f"Processing file: {path}")
+    if verbose:
+        logger.debug(f"Processing file: {path}")
 
     # attempt to extract article name for nicer filenames
     try:
@@ -698,8 +699,9 @@ def process_file(path: str, out_dir: str, overwrite: bool = False) -> tuple[bool
                             # could be list or simple string
                             ddx_list = ddx_entry
                     else:
-                        logger.debug(f"No cached DDX entry for docid {docid}")
-                        logger.debug(f"DDX keys available: {list(DDX.keys())}")
+                        if verbose:
+                            logger.debug(f"No cached DDX entry for docid {docid}")
+                            logger.debug(f"DDX keys available: {list(DDX.keys())}")
 
                     if ddx_list:
                         # render list representation