import PyPDF2
from pathlib import Path
import re
import os

search_terms = ["DATA AVAILABILITY STATEMENT",
                "open source",
                "open-source",
                "opensource",
                "open science",
                "github",
                " git "
                "osf",
                "jupyter",
                "notebook",
                "octave",
                "available online",
                "released",
                "shared",
                " code ",
                "numerical phantom",
                "bitbucket",
                "sourceforge",
                "xnat",
                "reproducible research",
                "julia",
                "image set",
                "image sets",
                "raw k-space data",
                "SHA-1",
                "gitlab",
                "Docker",
                "container",
                "MyBinder",
                "Binder",
                "mrhub",
                "MR-Hub",
                "codeocean",
                "Code Ocean"]

folder_path = '.'

for filename in sorted(os.listdir(Path(folder_path))):
    if filename.endswith(".pdf"):
        # open the pdf file
        object = PyPDF2.PdfFileReader(filename)

        # get number of pages
        num_pages = object.getNumPages()
        
        found_keywords = []
        # search through keywords
        for keyword in search_terms:
            # extract text and do the search
            for page_index in range(0, num_pages):
                page_obj = object.getPage(page_index)
                page_text = page_obj.extractText() 

                search_result = re.search(keyword, page_text)

                if search_result is not None:
                    found_keywords.append(keyword)
                    break
        
        if found_keywords:
            print(filename + " contains " + str(found_keywords))