pdf_oralia/extract.py

@@ -45,7 +45,7 @@ def from_pdf(pdf):
     charge_tables = []
     patrimoie_tables = []
 
-    for page_number, page in enumerate(pdf.pages):
+    for page in pdf.pages:
         page_text = page.extract_text()
         date = extract_date(page_text)
         additionnal_fields = {
@@ -76,7 +76,7 @@ def from_pdf(pdf):
             pass
 
         else:
-            logging.warning(f"Page {page_number+1} non reconnu. Page ignorée.")
+            raise ValueError("Page non reconnu")
 
     df_charge = charge.table2df(recapitulatif_tables + charge_tables)
     df_loc = locataire.table2df(loc_tables)

pdf_oralia/pages/charge.py

@@ -32,10 +32,7 @@ def is_it(page_text):
 def get_lot(txt):
     """Return lot number from "RECAPITULATIF DES OPERATIONS" """
     regex = r"[BSM](\d+)(?=\s*-)"
-    try:
+    result = re.findall(regex, txt)
-        result = re.findall(regex, txt)
-    except TypeError:
-        return "*"
     if result:
         return "{:02d}".format(int(result[0]))
     return "*"