Scanner debug part 1

src/beaky/scanner/scanner.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from typing import Iterator, List, Optional
+from typing import Any, Iterator, List, Optional
 
 from openpyxl import load_workbook
 from pydantic.dataclasses import dataclass
@@ -9,7 +9,15 @@ from beaky.config import Config
 
 @dataclass
 class Link:
-    id: str
+    """Represents a single link row from an Excel sheet.
+
+    Attributes:
+        id: identifier from the sheet (kept as string)
+        url: link to the web page
+        date: optional creation date (datetime or None)
+    """
+
+    id: int
     url: str
     date: Optional[datetime] = None
 
@@ -26,15 +34,16 @@ class Links:
         """Read the Excel file at self._path and populate self.links.
 
         Expects the first sheet to contain a header row with columns that include
-        at least: 'id', 'link' (or 'url'), and 'date' (case-insensitive). The
+        at least: 'id', 'link' (or 'url'), and optionally 'date' (case-insensitive).
-        method will attempt to parse dates and will store them as datetime when
+        Returns the list of Link objects (also stored in self.links).
-        possible; missing or unparsable dates become None.
         """
+        print("started ret_links()")
         wb = load_workbook(filename=self._path, read_only=True, data_only=True)
         ws = wb.active
 
         # Read header row
-        rows = ws.iter_rows(values_only=True)
+        rows = ws.rows
+
         try:
             header = next(rows)
         except StopIteration:
@@ -44,10 +53,9 @@ class Links:
             return []
 
         # Normalize header names -> index map
-        header_map = {(str(h).strip().lower() if h is not None else ""): i for i, h in enumerate(header) }
+        header_map = {(str(h).strip().lower() if h is not None else ""): i for i, h in enumerate(header)}
 
-        # Helper to parse date-like values
+        def parse_date(v: Any) -> Optional[datetime]:
-        def parse_date(v: None | datetime) -> Optional[datetime]:
             if v is None:
                 return None
             if isinstance(v, datetime):
@@ -71,12 +79,14 @@ class Links:
 
         # Find the column indices we care about
         id_idx = header_map.get("id")
-        url_idx = header_map.get("link")
+        url_idx = header_map.get("url")
         date_idx = header_map.get("date")
 
         if id_idx is None or url_idx is None:
             # Required columns missing
+            print("Required 'id' or 'url' column missing in header")
             return []
+
         print(rows)
         for row in rows:
             print(row)
@@ -89,8 +99,11 @@ class Links:
                     # skip empty rows
                     continue
 
-                link = Link(id=str(raw_id).strip() if raw_id is not None else "",
+                link = Link(
-                             url=str(raw_url).strip() if raw_url is not None else "", date=parse_date(raw_date))
+                    id=str(raw_id).strip() if raw_id is not None else "",
+                    url=str(raw_url).strip() if raw_url is not None else "",
+                    date=parse_date(raw_date),
+                )
                 self.links.append(link)
             except Exception:
                 # Skip problematic rows silently
@@ -107,3 +120,10 @@ class Links:
 
 # Backwards-compatible alias in case other modules referenced Linker
 Linker = Links
+
+
+if __name__ == "__main__":
+    links_obj = Links("data/odkazy.xlsx")
+    links = links_obj.ret_links()
+    if not links:
+        print("No links returned.")