Update linkedin_follower_stats.py

linkedin_follower_stats.py

@@ -172,49 +172,85 @@ def _parse_urn_to_id(urn_string):
 
 # --- Follower Data Fetching Functions ---
 
-def fetch_monthly_follower_gains(session, org_urn):
+def fetch_monthly_follower_gains(session, org_urn, api_rest_base):
     """
-    Fetches monthly follower gains using URL-concatenated timeInterval param,
-    matching the old working approach.
+    Fetches monthly follower gains for the last 12 full months.
+    The start date is set to the first day of the month, 12 months prior to the current month, at midnight UTC.
     """
     now = datetime.now(timezone.utc)
-    thirteen_months_ago = now - relativedelta(months=13)
-    start_of_period = thirteen_months_ago.replace(day=1, tzinfo=timezone.utc)
+
+    # Calculate the first day of the month, 12 months ago.
+    # For example, if now is 2025-05-13:
+    # - twelve_months_ago_date becomes 2024-05-13.
+    # - start_of_period becomes 2024-05-01 00:00:00 UTC.
+    twelve_months_ago_date = now - relativedelta(months=12)
+    start_of_period = twelve_months_ago_date.replace(day=1, hour=0, minute=0, second=0, microsecond=0, tzinfo=timezone.utc)
+    
     start_ms = int(start_of_period.timestamp() * 1000)
 
     # Build URL with explicit query string
     url = (
-        f"{API_REST_BASE}/organizationalEntityFollowerStatistics"
+        f"{api_rest_base}/organizationalEntityFollowerStatistics"
         f"?q=organizationalEntity"
         f"&organizationalEntity={org_urn}"
         f"&timeIntervals.timeGranularityType=MONTH"
         f"&timeIntervals.timeRange.start={start_ms}"
+        # LinkedIn defaults the end of the timeRange to the current time if not specified.
     )
     logging.info(f"Fetching monthly follower gains from URL: {url}")
 
     results = []
     try:
         response = session.get(url)
-        response.raise_for_status()
+        response.raise_for_status()  # Raises an HTTPError for bad responses (4XX or 5XX)
         data = response.json()
-        for item in data.get('elements', []):
-            ts = item.get('timeRange', {}).get('start')
+        
+        elements = data.get('elements', [])
+        if not elements:
+            logging.info(f"No 'elements' found in API response for {org_urn} for start_ms {start_ms}.")
+
+        for item in elements:
+            time_range = item.get('timeRange', {})
+            ts = time_range.get('start')
             if ts is None:
+                logging.warning(f"Skipping item due to missing 'start' timestamp: {item}")
                 continue
-            date_str = datetime.fromtimestamp(ts/1000, tz=timezone.utc).strftime('%Y-%m-%d')
+            
+            # Convert timestamp (milliseconds) to YYYY-MM-DD date string in UTC
+            date_obj = datetime.fromtimestamp(ts / 1000, tz=timezone.utc)
+            date_str = date_obj.strftime('%Y-%m-%d')
+            
             gains = item.get('followerGains', {})
+            # It's possible 'followerGains' itself is missing or None
+            if gains is None: 
+                gains = {} # Ensure gains is a dict to prevent error on .get()
+
             results.append({
-                'category_name': date_str,
+                'category_name': date_str, # This is the start date of the month's data
                 'follower_count_organic': gains.get('organicFollowerGain', 0),
                 'follower_count_paid': gains.get('paidFollowerGain', 0),
                 'follower_count_type': 'follower_gains_monthly',
                 'organization_urn': org_urn
             })
-        logging.info(f"Fetched {len(results)} monthly follower entries for {org_urn}")
+        logging.info(f"Fetched {len(results)} monthly follower entries for {org_urn} starting from {start_of_period.strftime('%Y-%m-%d')}.")
+    
+    except requests.exceptions.HTTPError as http_err:
+        # More specific error for HTTP errors
+        code = getattr(http_err.response, 'status_code', 'N/A')
+        text = getattr(http_err.response, 'text', str(http_err))
+        logging.error(f"HTTP error fetching monthly gains for {org_urn}: {code} - {text}")
+        logging.error(f"Request URL: {url}")
     except requests.exceptions.RequestException as e:
-        code = getattr(e.response, 'status_code', 'N/A')
-        text = getattr(e.response, 'text', str(e))
-        logging.error(f"Error fetching monthly gains: {code} - {text}")
+        # Catch other request-related errors (e.g., connection issues)
+        code = getattr(e.response, 'status_code', 'N/A') if e.response is not None else 'N/A'
+        text = getattr(e.response, 'text', str(e)) if e.response is not None else str(e)
+        logging.error(f"Error fetching monthly gains for {org_urn}: {code} - {text}")
+        logging.error(f"Request URL: {url}")
+    except Exception as ex:
+        # Catch any other unexpected errors (e.g., JSON parsing if response is not JSON)
+        logging.error(f"An unexpected error occurred while fetching monthly gains for {org_urn}: {str(ex)}")
+        logging.error(f"Request URL: {url}")
+        
     return results