z230

70 PDF read ZPMVCR.py

@@ -0,0 +1,31 @@
+
+import pdfplumber
+import pandas as pd
+from pathlib import Path
+
+pdf_path = Path(r"u:\Dropbox\!!!Days\Downloads Z230\prehled 09_2025 zpmvcr.pdf")
+xlsx_path = pdf_path.with_suffix(".xlsx")
+
+all_tables = []
+
+with pdfplumber.open(pdf_path) as pdf:
+    for i, page in enumerate(pdf.pages, start=1):
+        tables = page.extract_tables()
+        if not tables:
+            continue
+        table = tables[0]
+        # Convert to DataFrame, first row = header
+        df = pd.DataFrame(table[1:], columns=table[0])
+        df["page"] = i
+        all_tables.append(df)
+
+if not all_tables:
+    print("❌ No tables found.")
+else:
+    df_all = pd.concat(all_tables, ignore_index=True)
+    print("✅ Combined shape:", df_all.shape)
+    print(df_all.head())
+
+    # Save to Excel
+    df_all.to_excel(xlsx_path, index=False)
+    print(f"💾 Saved to: {xlsx_path}")