from PyPDF2 import PdfReader
import codecs

def createTestFile(link):
    reader = PdfReader(link)
    number_of_pages = len(reader.pages)
    page = reader.pages[0]
    f = codecs.open('output.txt', 'w', encoding='utf-8')
    for page in reader.pages:
        text = page.extract_text()
        f.write(text)


createTestFile("trainingsdata/data1.pdf")