pandoc akhlaq.docx -t html -o akhlaq.html

import os
import sys
import pandas as pd
from bs4 import BeautifulSoup
from pathlib import Path
import io

book_name = 'Kitab al-Zuhd al-Kabir'
book_language = 'French'
book_author = 'Abu Bakr al-Bayhaqi'
file_no = "1"
book = "zohd"

# Define file path
path = rf'organized/books/{book}/{file_no}.html'

# Parse the HTML using BeautifulSoup
with open(path, 'r', encoding='utf-8') as file:
    soup = BeautifulSoup(file, 'html.parser')

# Extract table headers
try:
    table = soup.find("table")
    header = [th.get_text(strip=True) for th in table.find("tr").find_all("th")]
except AttributeError:
    raise ValueError("Table or headers not found in the HTML file.")

# Extract row data
data = []
for row in table.find_all("tr")[1:]:  # Skip header row
    row_data = [td.get_text(strip=True) for td in row.find_all("td")]
    data.append(row_data)

# Convert to Pandas DataFrame
dataFrame = pd.DataFrame(data=data, columns=header)

# Drop unnecessary columns
df = dataFrame.drop(columns=[0, 2, 4])

# Rename columns
df.rename(columns={3: 'Original', 1: 'Translation'}, inplace=True)

# Define patterns to escape or replace
patterns = [
    ('"', '\\"'),      # Escape double quotes
    ('“', '\\"'),      # Escape left double quote
    ('”', '\\"'),      # Escape right double quote
    (':', '\\"'),      # Escape colon
    (r'\]', '\\"'),    # Escape right square bracket
    (r'\[', '\\"'),    # Escape left square bracket
    (r'\n', ' ')       # Replace newlines with spaces
]

# Apply cleaning to both columns
for column in ['Original', 'Translation']:
    for pattern, replacement in patterns:
        df[column] = df[column].str.replace(pattern, replacement, regex=True)