create_pdfs.py

from fpdf import FPDF
import os

def create_pdf_from_txt(txt_path, pdf_path):
    with open(txt_path, 'r') as file:
        content = file.read()
    
    # Replace bullets and other special characters
    content = content.replace('•', '*')
    content = content.replace('–', '-')
    
    pdf = FPDF()
    pdf.add_page()
    pdf.set_auto_page_break(auto=True, margin=15)
    pdf.set_font("Arial", size=12)
    
    # Split content into lines and encode to handle special characters
    for line in content.split('\n'):
        try:
            # Try to encode the line to latin1
            encoded_line = line.encode('latin-1', 'replace').decode('latin-1')
            pdf.cell(0, 10, txt=encoded_line, ln=True)
        except Exception:
            # If encoding fails, skip the line
            continue
    
    pdf.output(pdf_path)

def main():
    # Convert job descriptions
    job_desc_dir = "JOB_DESCRIPTIONS"
    txt_files = [f for f in os.listdir(job_desc_dir) if f.endswith('.txt')]
    
    for txt_file in txt_files:
        txt_path = os.path.join(job_desc_dir, txt_file)
        pdf_path = os.path.join(job_desc_dir, txt_file.replace('.txt', '.pdf'))
        create_pdf_from_txt(txt_path, pdf_path)
        os.remove(txt_path)

    # Convert remaining resumes if any
    resume_dir = "DATA_resume"
    txt_files = [f for f in os.listdir(resume_dir) if f.endswith('.txt')]
    
    for txt_file in txt_files:
        txt_path = os.path.join(resume_dir, txt_file)
        pdf_path = os.path.join(resume_dir, txt_file.replace('.txt', '.pdf'))
        create_pdf_from_txt(txt_path, pdf_path)
        os.remove(txt_path)  # Remove the txt file after creating PDF

if __name__ == "__main__":
    main()