# Function to read the first page of a PDF and extract the abstract
def extract_abstract(pdf_path):

    # Open the PDF file and grab text from the 1st page
    with fitz.open(pdf_path) as pdf:
        first_page = pdf[0]
        text = first_page.get_text("text")

    # Extract the abstract (assuming the abstract starts with 'Abstract')

    # find where abstract starts
    start_idx = text.lower().find('abstract') 

    # end abstract at introduction if it exists on 1st page
    if 'introduction' in text.lower():
        end_idx = text.lower().find('introduction')  
    else:
        end_idx = None

    # extract abstract text
    abstract = text[start_idx:end_idx].strip()

    # if abstract appears on 1st page return it, if not resturn None
    if start_idx != -1:
        abstract = text[start_idx:end_idx].strip()
        return abstract
    else:
        return None