Ebook Chunk Splitter - python

EbookChunkSplitter.py

"""
Script: Ebook Chunk Splitter
Description: This script takes an input text file of an ebook and splits it into smaller chunks based on a specified character limit. It ensures that paragraphs are not split and creates an output directory with the split chunks of the ebook.

Input: Replace `<input_file>` with the path to the input text file of the ebook.
Output: Replace `<output_folder>` with the path to the output directory where the split ebook chunks will be stored.
"""

import os
import datetime

# Define input and output paths
input_file = "/path/to/input/ebook.txt"
output_folder = "/path/to/output/"

# Set maximum character limit for each output file
max_characters = 90000

# Create output folder if it doesn't exist
if not os.path.exists(output_folder):
    os.makedirs(output_folder)

# Get the base filename without extension
base_filename = os.path.splitext(os.path.basename(input_file))[0]

# Generate unique datetime stamp
timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")

# Create a new folder with the source file name and timestamp
output_directory = os.path.join(output_folder, f"{base_filename}_{timestamp}")
os.makedirs(output_directory)

# Read the input ebook text file
with open(input_file, "r") as f:
    lines = f.readlines()

# Split the text into chunks of maximum length without splitting paragraphs
chunks = []
current_chunk = ""
for line in lines:
    if len(current_chunk) + len(line) <= max_characters:
        current_chunk += line
    else:
        chunks.append(current_chunk)
        current_chunk = line
chunks.append(current_chunk)

# Write each chunk to a separate output file
for i, chunk in enumerate(chunks):
    output_file = os.path.join(output_directory, f"{base_filename}_{i+1}.txt")
    with open(output_file, "w") as f:
        f.write(chunk)