Notes

class DocumentProcessor:
def __init__(self):
self.documents = []
self.setup_ui()

def setup_ui(self):
window = tk.Tk()
window.title("Document Processor")
window.geometry("500x250")

tk.Label(window, text="Document Quote Review Automation", font=("Arial", 14)).pack(pady=10)

upload_btn = tk.Button(window, text="Upload Documents", command=self.upload_documents, height=2, width=20)
upload_btn.pack(pady=10)

process_btn = tk.Button(window, text="Process & Save to Excel", command=self.process_and_save, height=2, width=20)
process_btn.pack(pady=10)

window.mainloop()

def upload_documents(self):
file_paths = fd.askopenfilenames(title='Select documents', filetypes=[("PDF files", "*.pdf")])
self.documents.extend(file_paths)
print(f"{len(file_paths)} file(s) uploaded.")

def process_and_save(self):
workbook = Workbook()
sheet = workbook.active
sheet.append(["Document Path", "Type", "Quote Number", "Total", "Quote Date", "Solution ID"])

for doc_path in self.documents:
doc_type, data = self.process_document(doc_path)
sheet.append([doc_path, doc_type] + list(data.values()))

workbook.save("DocumentAnalysis.xlsx")
print("Analysis saved to DocumentAnalysis.xlsx.")

def process_document(self, doc_path):
try:
with open(doc_path, 'rb') as pdf_file:
pdf_reader = PyPDF2.PdfReader(pdf_file)
all_text = " ".join(page.extract_text() for page in pdf_reader.pages)

if "Quote No." in all_text:
return "USQuote", self.extract_us_quote_data(all_text)
elif "Quote Date:" in all_text:
return "EMEAQuote", self.extract_emea_quote_data(all_text)
elif "Solution ID" in all_text:
return "SolutionID", self.extract_solution_id_data(all_text)
except Exception as e:
print(f"Error processing {doc_path}: {e}")
return "Unknown", {}

def extract_us_quote_data(self, text):
data = {
"Quote Number": self.find_with_regex(text, r"Quote No. n([d|,|.]+) n"),
"Total": self.find_with_regex(text, r"Totaln$([d|,|.]+)n"),
"Quote Date": self.find_with_regex(text, r"Quoted Onn([a-zA-Z]+. [0-9]+, [0-9]+) n"),
"Solution ID": self.find_with_regex(text, r"Solution IDn([d|,|.]+)"),
}
return data

def extract_emea_quote_data(self, text):
data = {
"Quote Number": self.find_with_regex(text, r"Quote/Source Ref: ([0-9]+.? [0-9]+?)"),
"Total": self.find_with_regex(text, r"Total ([d|,|.]+)"),
"Quote Date": self.find_with_regex(text, r"Quote Date: ([0-9]+- [0-9]+- [0-9]+)"),
"Solution ID": "", # Assuming EMEA quotes might not have a Solution ID directly mentioned
}
return data

def extract_solution_id_data(self, text):
# Assuming a pattern for Solution IDs, though not specified in the example
data = {
"Solution ID": self.find_with_regex(text, r"Solution ID: ([wd]+)"),
"Quote Number": "",
"Total": "",
"Quote Date": "",
}
return data

@staticmethod
def find_with_regex(text, pattern):
match = re.search(pattern, text, re.MULTILINE)
return match.group(1) if match else ""

if __name__ == "__main__":
DocumentProcessor()