Build a Python script to check spelling in bulk documents

Here’s a complete Python script that checks spelling in bulk documents (like .txt, .docx, or .pdf files) within a specified directory. It uses pyspellchecker for spell-checking and python-docx / PyPDF2 for reading .docx and .pdf files.

python
CopyEdit
import os
from spellchecker import SpellChecker
from docx import Document
import PyPDF2

def extract_text_from_txt(file_path):
    with open(file_path, 'r', encoding='utf-8', errors='ignore') as file:
        return file.read()

def extract_text_from_docx(file_path):
    doc = Document(file_path)
    return 'n'.join([para.text for para in doc.paragraphs])

def extract_text_from_pdf(file_path):
    text = ""
    with open(file_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        for page in reader.pages:
            text += page.extract_text() or ''
    return text

def get_text_from_file(file_path):
    if file_path.endswith('.txt'):
        return extract_text_from_txt(file_path)
    elif file_path.endswith('.docx'):
        return extract_text_from_docx(file_path)
    elif file_path.endswith('.pdf'):
        return extract_text_from_pdf(file_path)
    else:
        return None

def spell_check_text(text):
    spell = SpellChecker()
    words = text.split()
    misspelled = spell.unknown(words)
    return {word: spell.correction(word) for word in misspelled}

def process_documents(directory):
    report = {}
    for filename in os.listdir(directory):
        if filename.endswith(('.txt', '.docx', '.pdf')):
            file_path = os.path.join(directory, filename)
            print(f"Processing: {filename}")
            text = get_text_from_file(file_path)
            if text:
                errors = spell_check_text(text)
                if errors:
                    report[filename] = errors
    return report

if __name__ == "__main__":
    folder_path = input("Enter the path to the folder containing documents: ").strip()
    results = process_documents(folder_path)
    
    if not results:
        print("No spelling errors found.")
    else:
        for file, errors in results.items():
            print(f"nFile: {file}")
            for wrong, suggestion in errors.items():
                print(f"  {wrong} -> {suggestion}")

Required Libraries Installation

Install the dependencies via pip before running:

bash
CopyEdit
pip install pyspellchecker python-docx PyPDF2

Features:

• Supports .txt, .docx, and .pdf.

• Automatically extracts and checks words.

• Suggests corrections for each misspelled word.

• Displays a report file-wise.

Let me know if you want the output saved to a CSV or text file.