Summarizing-Academic-Export-to-Excel Independently

import os
import glob
import time
import sys
from transformers import pipeline
import tqdm
from datetime import datetime
import openpyxl
from openpyxl.styles import Alignment, Font, Border, Side, PatternFill
import nltk

nltk.download("punkt")

def progress_bar(current, total, message):
    bar_length = 50
    progress = current / total
    arrow = "=" * int(bar_length * progress) + ">"
    spaces = " " * (bar_length - len(arrow))
    sys.stdout.write(f"\r{message}: [{arrow + spaces}] {int(progress * 100)}%")
    sys.stdout.flush()

summarizer = pipeline("summarization", model="lidiya/bart-large-xsum-samsum")
text_files = glob.glob("*.txt")

for text_file in text_files:
    author, title, year, journal = text_file[:-4].split("-")

    summary_file = f"summary_of_{author}-{title}-{year}-{journal}.xlsx"
    if os.path.exists(summary_file):
        print(f"Summary file for {text_file} already exists. Skipping summarization.")
        continue
    
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    
    header_font = Font(bold=True)
    header_fill = PatternFill(start_color="ADD8E6", end_color="ADD8E6", fill_type="solid")
    header_border = Border(left=Side(style="thin"),
                           right=Side(style="thin"),
                           top=Side(style="thin"),
                           bottom=Side(style="thin"))

    headers = ["ID", "Author", "Title", "Year", "Journal", "Summary ID", "Summary", "Date"]
    for col_num, value in enumerate(headers, 1):
        cell = sheet.cell(row=1, column=col_num)
        cell.value = value
        cell.font = header_font
        cell.fill = header_fill
        cell.border = header_border
        cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=True)

    with open(text_file, "r", encoding="utf-8") as f:
        content = f.read()

    chunk_size = 1024
    sentences = nltk.sent_tokenize(content)

    chunks = []
    chunk = []
    chunk_length = 0
    for sentence in sentences:
        sentence_length = len(sentence)
        if chunk_length + sentence_length <= chunk_size:
            chunk.append(sentence)
            chunk_length += sentence_length
        else:
            chunks.append(" ".join(chunk))
            chunk = [sentence]
            chunk_length = sentence_length

    if chunk:
        chunks.append(" ".join(chunk))

    summaries = []
    for i, chunk in enumerate(chunks):
        for j in tqdm.tqdm(range(100)):
            time.sleep(0.02)
            progress_bar(j + 1, 100, f"Summarizing chunk {i+1}/{len(chunks)} of {text_file}")
        summary = summarizer(chunk)
        summaries.append(summary[0]["summary_text"])

    current_date = datetime.today().strftime('%Y-%m-%d')

    file_id = "1"

    for i, summary in enumerate(summaries):
        summary_id = f"{file_id}-{i + 1}"
        new_row = [file_id, author, title, year, journal, summary_id, summary, current_date]
        sheet.append(new_row)

        row_number = sheet.max_row
        for col_number, cell in enumerate(new_row, 1):
            sheet_cell = sheet.cell(row=row_number, column=col_number)
            sheet_cell.border = Border(left=Side(style="thin"),
                                       right=Side(style="thin"),
                                       top=Side(style="thin"),
                                       bottom=Side(style="thin"))
            sheet_cell.alignment = Alignment(vertical="top", wrap_text=True)
            if col_number == 7:  # Summary column
                sheet_cell.font = Font(size=11)
                sheet.row_dimensions[row_number].height = 80  # Adjust row height

    print(f"Summary of {text_file} added to the Excel file.")

    # Adjust the width of the "Summary" column
    sheet.column_dimensions["G"].width = 80

    # Freeze the first row
    sheet.freeze_panes = "A2"

    # Save the workbook with a unique name based on the text file
    excel_file = summary_file
    workbook.save(excel_file)