Tesseract OCR Engine

ocr.py

import pytesseract
import requests
from PIL import Image
from PIL import ImageFilter
from StringIO import StringIO


def process_image(url):
    image = _get_image(url)
    # image = image.resize( [int(2 * s) for s in image.size] )
    # image.filter(ImageFilter.SHARPEN)
    # image.filter(ImageFilter.EDGE_ENHANCE)
    # image.filter(ImageFilter.FIND_EDGES)
    return pytesseract.image_to_string(image)


def _get_image(url):
    return Image.open(StringIO(requests.get(url).content))

# edit 5/12/16: image filters and resizing needs to be tested to see what works best.
# adapted from https://realpython.com/blog/python/setting-up-a-simple-ocr-server/

Yay that works! Thanks Sarah!

np