Feat: extract "remise commercial" from 1st page

pdf_oralia/extract.py

@@ -1,9 +1,10 @@
 import logging
 from pathlib import Path
 
+import pandas as pd
 import pdfplumber
 
-from .extract_charge import extract_charge
+from .extract_charge import extract_charge, extract_remise_com
 from .extract_locataire import extract_situation_loc
 
 charge_table_settings = {
@@ -16,6 +17,11 @@ def extract_from_pdf(pdf, charge_dest, location_dest):
     """Build charge_dest and location_dest xlsx file from pdf"""
     loc_tables = []
     charge_table = []
+
+    df_1st_charge = extract_remise_com(
+        pdf.pages[0].extract_table(charge_table_settings)
+    )
+
     for page in pdf.pages[1:]:
         page_text = page.extract_text()
         situation_loc_line = [
@@ -35,7 +41,8 @@ def extract_from_pdf(pdf, charge_dest, location_dest):
                 charge_table = page.extract_table(charge_table_settings)
 
     df_charge = extract_charge(charge_table)
-    df_charge.to_excel(charge_dest, sheet_name="Charges", index=False)
+    df_charge_with_1st = pd.concat([df_1st_charge, df_charge])
+    df_charge_with_1st.to_excel(charge_dest, sheet_name="Charges", index=False)
     logging.info(f"{charge_dest} saved")
 
     df_loc = extract_situation_loc(loc_tables, mois=mois, annee=annee)

pdf_oralia/extract_charge.py

@@ -51,3 +51,13 @@ def extract_charge(table):
     )
 
     return df
+
+
+def extract_remise_com(table):
+    """Extract "remise commercial" from first page"""
+    df = pd.DataFrame(table[1:], columns=table[0]).replace("", np.nan)
+    return df[
+        df["RECAPITULATIF DES OPERATIONS"].str.contains(
+            "Remise commerciale gérance", case=False, na=False
+        )
+    ]