1

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

1
2
3
4
5
6

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

1
2
3
4
5

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

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22

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

# Parse the HTML file with 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 table rows
data = []
for row in table.find_all("tr")[1:]:  # Skip the header row
    row_data = [td.get_text(strip=True) for td in row.find_all("td")]
    data.append(row_data)

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

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21

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

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

# Define patterns to replace
patterns = [
    ('\"', '\\\"'),  # Escape double quotes
    ('“', '\\\"'),   # Escape left double quotation mark
    ('”', '\\\"'),   # Escape right double quotation mark
    (':', '\\\"'),   # Escape colon
    (r'\]', '\\\"'), # Escape closing square bracket
    (r'\[', '\\\"'), # Escape opening square bracket
    (r'\n', ' ')     # Replace newline with space
]

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