Added functions, new regular expressions and changed the library

projekt.py

@@ -1,50 +1,71 @@
-import fitz
 import re
+from pdfminer.high_level import extract_text
 
-my_path = r"C:\Users\DELL\Downloads\A-24VU-00511.PDF.pdf"
+
+my_path = r"C:\Users\DELL\Downloads\Kopia 1_240014-333-361-389-399-433-441-448-464-481_2024_06_20_CE240143 (INVOICE - ERD-FVZ%i9210621%i922024%i92NZ-1 - 1 - A1) - 1.pdf.pdf"
+#my_path = r"C:/Users/DELL/Downloads/A-24VU-00511.PDF.pdf"
+
+
+#regex
 postal_code_pattern = r"(?<!\S)(?:(?:[A-Za-z]{3,}\s+)(\d{5}|\d{2}-\d{3})|(\d{5}|\d{2}-\d{3})(?:\s+[A-Za-z]{3,}))(?!\S)"
-with fitz.open(my_path) as doc:
+postal_code_pattern2 = r"(?<!\S)(?:[A-Za-z]{3,}\s+-?\s+(\d{5}|\d{2}-\d{3})|(\d{5}|\d{2}-\d{3})\s+-?\s+[A-Za-z]{3,})(?!\S)"
-    order_numbers = []
+date_pattern = r'\b\d{2}/\d{2}/\d{2,4}\b'
-    order_dates = []
+reference_pattern = r"ref\.\s*[^0-9]*?([1-9]\d{4,})"
-    buyers = []
 
-    for page in doc:
+order_numbers = []
-        text = page.get_text("text")
+order_dates = set()
+buyers = []
 
-        if "Your ref. no. PO" in text:
+text = extract_text(my_path).lower()
-            parts = text.split("Your ref. no. PO") 
-            for part in parts[1:]:
-                order_number = part.split()[0].strip()
-                order_numbers.append(order_number)
 
-        date_pattern = r'\b\d{2}/\d{2}/\d{2,4}\b'
+def dates(text):
     matches = re.findall(date_pattern, text)
-        order_dates.extend(matches)
+    for match in matches:
+        order_dates.add(match)
+
+def ref_numbers(text):
+    matches = re.findall(reference_pattern, text)
+    for match in matches:
+        order_numbers.append(match)
 
 
+def company(text):
     lines = text.splitlines()
-        for i in range(1, len(lines)):  
+    for i in range(len(lines)):
         line = lines[i]
         
-            if re.search(postal_code_pattern, line):
+        # Sprawdzenie, czy linia zawiera kod pocztowy
+        if re.search(postal_code_pattern, line) or re.search(postal_code_pattern2, line):
+            # Szukanie linii powyżej
+            line_above = next((lines[j].strip() for j in range(i - 1, -1, -1) if len(lines[j].strip()) > 0), '')
+            # Szukanie linii z nazwą firmy
+            line_2 = next((lines[j].strip() for j in range(i - 1, -1, -1) if len(lines[j].strip()) > 0 and 'ul.' not in lines[j].strip() and lines[j].strip() != line_above), '')
+            # Szukanie linii poniżej
+            line_below = next((lines[j].strip() for j in range(i + 1, len(lines)) if len(lines[j].strip()) > 0), '')
 
-                line_2 = lines[i-2] if i>0 else ''
+            if line_2 and line_above and line and line_below:  
-                line_above = lines[i - 1] if i > 0 else ''
+                buyer = {
-                line_below = lines[i + 1] if i + 1 < len(lines) else ''
-            
-                buyers.append({
                     'line_2': line_2,
                     'line_above': line_above,
                     'postal_code_line': line,
                     'line_below': line_below
-                })
+                }
+                if buyer not in buyers:
+                    buyers.append(buyer)
+
+dates(text)
+ref_numbers(text)
+company(text)
+
+order_dates = list(order_dates)
 
 print("Reference numbers:", order_numbers)
 print("Document dates:", order_dates)
 print("Buyers: ")
+
 for context in buyers:
-    print("Company: ", context['line_2'])
+    print("Company:", context['line_2'])
-    print("St. :", context['line_above'])
+    print("St.:", context['line_above'])
-    print("City: ", context['postal_code_line'])
+    print("City:", context['postal_code_line'])
     print("Country:", context['line_below'])
     print()