This script processes a range of PDF files and identifies those with a character count exceeding a specified threshold.

countcharacter_in_pdf_range.py

#!/usr/bin/env python3

# ------------------------------------------------------------------
# Script Name:   pdfcwcount_range.py
# Description:   This script processes a range of PDF files and
#                identifies those with a character count exceeding
#                a specified threshold.
# Website:       https://gist.github.com/ostechnix
# Version:       1.0
# Usage:         py pdf_processor.py <range_param> <char_threshold>
#                in a PDF File.
# Use Gist:      curl -s https://gist.githubusercontent.com/alsiesta/07dcded8b0a2e05c0306d0922ad5c9bb/raw/countcharacter_in_pdf_range.py | py - "output_chunk_1.pdf-output_chunk_30.pdf" 40000
# ------------------------------------------------------------------

import sys
import os
from PyPDF2 import PdfReader

def count_characters_in_pdf(pdf_path):
    reader = PdfReader(pdf_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text() or ""
    return len(text)

def generate_pdf_list(range_param):
    start_pdf, end_pdf = range_param.split('-')
    
    start_index = int(start_pdf.split('_')[-1].replace('.pdf', ''))
    end_index = int(end_pdf.split('_')[-1].replace('.pdf', ''))
    
    prefix = start_pdf.rsplit('_', 1)[0]  # Extract the prefix (e.g., "output_chunk")

    pdf_list = [f"{prefix}_{i}.pdf" for i in range(start_index, end_index + 1)]
    return pdf_list

def process_pdfs(input_pdfs, char_threshold):
    pdfs_over_threshold = []
    for pdf_path in input_pdfs:
        if os.path.isfile(pdf_path):
            char_count = count_characters_in_pdf(pdf_path)
            if char_count > char_threshold:
                pdfs_over_threshold.append((pdf_path, char_count))
        else:
            print(f"File not found: {pdf_path}")
    
    if pdfs_over_threshold:
        return pdfs_over_threshold
    else:
        return f"No PDF has more than {char_threshold} characters"

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: py pdf_processor.py <range_param> <char_threshold>")
        sys.exit(1)
    
    range_param = sys.argv[1]
    char_threshold = int(sys.argv[2])  # Character count threshold passed as a command-line argument
    input_pdfs = generate_pdf_list(range_param)
    
    result = process_pdfs(input_pdfs, char_threshold)
    
    if isinstance(result, list):
        for pdf, count in result:
            print(f"PDF: {pdf} has {count} characters.")
    else:
        print(result)