from io import StringIO
from pdfminer3.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer3.converter import TextConverter
from pdfminer3.layout import LAParams
from pdfminer3.pdfpage import PDFPage
import os
from PyPDF2 import PdfFileReader
import sys, getopt

#converts pdf, returns its text content as a string
def convert(fname, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)

    output = StringIO()
    manager = PDFResourceManager()
    converter = TextConverter(manager, output, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)

    infile = open(fname, 'rb')
    for page in PDFPage.get_pages(infile, pagenums):
        interpreter.process_page(page)
    infile.close()
    converter.close()
    text = output.getvalue()
    output.close
    return text

#converts all pdfs in directory pdfDir, saves all resulting txt files to txtdir
def convertMultiple(pdfDir, txtDir):
    if pdfDir == "": pdfDir = os.getcwd() + "\\" #if no pdfDir passed in
    for pdf in os.listdir(pdfDir): #iterate through pdfs in pdf directory
        fileExtension = pdf.split(".")[-1]
        if fileExtension == "pdf":
            pdfFilename = pdfDir + pdf
            text = convert(pdfFilename) #get string of text content of pdf
            textFilename = txtDir + pdf + ".txt"
            textFile = open(textFilename, "w") #make text file
            textFile.write(text) #write text to text file

# Counts the number of pages in all pdfs in a folder
def count_pages(pdf_dir):

    page_count = 0

    for pdf in os.listdir(pdf_dir): #iterate through pdfs in pdf directory
        pdfFilename = pdf_dir + pdf
        print("Reading: " + pdfFilename)
        try:
            pdf_object = PdfFileReader(open(pdfFilename, "rb"))
            page_count = page_count + pdf_object.getNumPages()
        except:
            print("No EOF! Yeesh")

    print(page_count)

pdfDir = "C:/Users/thech/Data/IRB Website PDFs/"
txtDir = "C:/Users/thech/Data/IRB Texts - Unmerged/"
#convertMultiple(pdfDir, txtDir)
count_pages("C:/Users/thech/Data/IRB Website PDFs/")