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 = 'كتاب الزهد الكبير'
book_language = 'الفرنسية'
book_author = 'أبو بكر البيهقي'
file_no = "1"
book = "zohd"

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

# empty list
data = []

# for getting the header from
# the HTML file
list_header = []
soup = BeautifulSoup(open(path),'html.parser')
header = soup.find_all("table")[0].find("tr")

for items in header:
    try:
        list_header.append(items.get_text())
    except:
        continue

# for getting the data
HTML_data = soup.find_all("table")[0].find_all("tr")[1:]

for element in HTML_data:
    sub_data = []
    for sub_element in element:
        try:
            sub_data.append(sub_element.get_text())
        except:
            continue
    data.append(sub_data)

# Storing the data into Pandas
# DataFrame
dataFrame = pd.DataFrame(data = data)

df = dataFrame.drop(columns=[0,2, 4])
df.rename(columns = {3:'Original', 1: 'Translation'}, inplace = True)
df_final['Original']= df_final['Original'].str.replace('\"', '\\\"', regex=True)
df_final['Original']= df_final['Original'].str.replace('“', '\\\"', regex=True)
df_final['Original']= df_final['Original'].str.replace('”', '\\\"', regex=True)
df_final['Original']= df_final['Original'].str.replace(':', '\\\"', regex=True)
df_final['Original']= df_final['Original'].str.replace('\]', '\\\"', regex=True)
df_final['Original']= df_final['Original'].str.replace('\[', '\\\"', regex=True)
df_final['Original']= df_final['Original'].str.replace('\n', ' ', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace('\"', '\\\"', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace('“', '\\\"', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace('”', '\\\"', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace(':', '\\\"', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace('\]', '\\\"', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace('\[', '\\\"', regex=True)
df_final['Translation'] = df_final['Translation'].str.replace('\n', ' ', regex=True)