SPlit up

pipeline/download/rental_prices.py

@@ -30,13 +30,31 @@ AREA_CODE_ALIASES = {
 }
 
 
+def _data_rows(df: pl.DataFrame) -> pl.DataFrame:
+    """Rows below Table 1's header row.
+
+    The preamble length varies (title, optional "This worksheet contains..."
+    note, then the header row starting with "Time period"), so locate the
+    header by content instead of counting rows — a fixed slice leaves the
+    header in the data whenever ONS adds or removes a note line.
+    """
+    header_marker = (
+        pl.col("column_1").cast(pl.String).str.strip_chars().str.to_lowercase()
+        == "time period"
+    )
+    header_rows = df.with_row_index("_row").filter(header_marker)
+    if header_rows.is_empty():
+        raise ValueError("PIPR Table 1: no 'Time period' header row found")
+    return df.slice(int(header_rows["_row"][0]) + 1)
+
+
 def _latest_rents_long(df: pl.DataFrame) -> pl.DataFrame:
-    # Table 1 layout: row 0 = title, row 1 = column headers, row 2+ = data.
-    # 40 columns in repeating blocks of 4 (index, monthly change, annual change,
-    # rental price) for each category. Rental price columns (0-indexed):
+    # Table 1 layout below the header: 40 columns in repeating blocks of 4
+    # (index, monthly change, annual change, rental price) for each category.
+    # Rental price columns (0-indexed):
     #   7 = All categories, 11 = One bed, 15 = Two bed, 19 = Three bed,
     #   23 = Four or more bed
-    df = df.slice(2)  # Skip title and header rows
+    df = _data_rows(df)
 
     df = df.select(
         pl.col("column_1").alias("time_period"),