Tesseract ocr PDF as input

Just for documentation reasons, here is an example of OCR using tesseract and pdf2image to extract text from an image pdf.

import pdf2image
try:
    from PIL import Image
except ImportError:
    import Image
import pytesseract


def pdf_to_img(pdf_file):
    return pdf2image.convert_from_path(pdf_file)


def ocr_core(file):
    text = pytesseract.image_to_string(file)
    return text


def print_pages(pdf_file):
    images = pdf_to_img(pdf_file)
    for pg, img in enumerate(images):
        print(ocr_core(img))


print_pages('sample.pdf')