Mar-26-2023, 07:41 AM
Hello. I have a lots of ANSI docx files. I made this Python code, and I got an error of codec:
import re import os from pathlib import Path from docx import Document from docx.shared import Inches import sys from docx2pdf import convert # The location where the files are located input_path = r'c:\Folder7\input' # The location where we will write the PDF files output_path = r'c:\Folder7\output' # Creeaza structura de foldere daca nu exista os.makedirs(output_path, exist_ok=True) # Verifica existenta folder-ului directory_path = Path(input_path) if directory_path.exists() and directory_path.is_dir(): print(directory_path, "exists") else: print(directory_path, "is invalid") sys.exit(1) for file_path in directory_path.glob("*"): # file_path is a Path object print("Procesez fisierul:", file_path) document = Document() # file_path.name is the name of the file as str without the Path document.add_heading(file_path.name, 0) file_content = file_path.read_text(encoding='UTF-8') document.add_paragraph(file_content) # build the new path where we store the files output_file_path = os.path.join(output_path, file_path.name + ".pdf") document.save(output_file_path) print("Am convertit urmatorul fisier:", file_path, "in: ", output_file_path)This is the error:
Traceback (most recent call last): File "D:\Convert docx to pdf.py", line 32, in <module> file_content = file_path.read_text(encoding='UTF-8') File "C:\Program Files\Python39\lib\pathlib.py", line 1133, in read_text return f.read() File "C:\Program Files\Python39\lib\codecs.py", line 322, in decode (result, consumed) = self._buffer_decode(data, self.errors, final) UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd2 in position 16: invalid continuation byteCan anyone update my code, so that it can read ANSI and save as UTF-8 into PDF?