Merge pull request 'feat: add structured logging to serp_api.py' (#54) from feature/structured-logging into main

SPARC/serp_api.py

@@ -1,3 +1,4 @@
+import logging
 import os
 import re
 from datetime import datetime, timedelta
@@ -10,6 +11,8 @@ import serpapi
 from SPARC import config
 from SPARC.types import Patent, Patents
 
+logger = logging.getLogger(__name__)
+
 
 class SERP:
   def query(company: str, days_back: int = None) -> Patents:
@@ -44,6 +47,7 @@ class SERP:
       "tbs": date_filter,
       "api_key": config.api_key,
     }
+    logger.info("Querying Google Patents for '%s' (last %d days)", company, days_back)
     search = serpapi.search(params)
     # Convert results to Patent objects, skipping any without PDF links
     patent_ids = []
@@ -52,8 +56,10 @@ class SERP:
         pdf_link = patent.get("pdf")
         if pdf_link:
             patent_ids.append(Patent(patent_id=patent["publication_number"], pdf_link=pdf_link, summary=None))
-        # Patents without PDF links are skipped (see docstring for details)
+        else:
+            logger.debug("Skipping patent %s (no PDF link)", patent.get("publication_number", "unknown"))
 
+    logger.info("Found %d patents with PDF links for '%s'", len(patent_ids), company)
     return Patents(patents=patent_ids)
 
   def save_patents(patent: Patent) -> Patent:
@@ -70,9 +76,13 @@ class SERP:
     os.makedirs("patents", exist_ok=True)
 
     if not (os.path.exists(pdf_path) and os.path.getsize(pdf_path) > 0):
+      logger.info("Downloading PDF for %s", patent.patent_id)
       response = requests.get(patent.pdf_link)
       with open(pdf_path, "wb") as f:
         f.write(response.content)
+      logger.debug("Saved %d bytes to %s", len(response.content), pdf_path)
+    else:
+      logger.debug("Using cached PDF for %s at %s", patent.patent_id, pdf_path)
 
     patent.pdf_path = pdf_path
     return patent
@@ -90,11 +100,13 @@ class SERP:
       Dictionary containing all extracted sections
     """
 
+    logger.debug("Parsing patent PDF: %s", pdf_path)
     with pdfplumber.open(pdf_path) as pdf:
       # Extract all text
       full_text = ""
       for page in pdf.pages:
         full_text += page.extract_text() + "\n"
+      logger.debug("Extracted text from %d pages (%d chars)", len(pdf.pages), len(full_text))
 
     # Define section patterns (common in patents)
     sections = {