Last active
March 29, 2021 13:57
-
-
Save rlskoeser/4cc5f2bb6c2da67da3fd0036e74166b8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| # pip install google-cloud-vision | |
| # Follow quick start instructions to set up access to the API and authentication | |
| # https://pypi.org/project/google-cloud-vision/ | |
| import glob | |
| import io | |
| import os | |
| from google.cloud import vision | |
| IMAGE_DIR = 'images' | |
| def get_image_ocr(): | |
| # Instantiate google vision client | |
| client = vision.ImageAnnotatorClient() | |
| for imagefile in glob.iglob('%s/*/*.jpg' % IMAGE_DIR): | |
| basepath = os.path.splitext(imagefile)[0] | |
| textfile = '%s.txt' % basepath | |
| # if text file already exists, skip | |
| if os.path.isfile(textfile): | |
| continue | |
| # if text file does not exist, request ocr | |
| # Load the image into memory | |
| with io.open(imagefile, 'rb') as image_file: | |
| content = image_file.read() | |
| image = vision.Image(content=content) | |
| # Performs ocr and handwriting detection on the image file | |
| response = client.document_text_detection(image=image) | |
| # save plain text output to local file; | |
| # even if text is empty, create text file so we don't request again | |
| with open(textfile, 'w') as textfilehandle: | |
| textfilehandle.write(response.full_text_annotation.text) | |
| if response.error.message: | |
| raise Exception( | |
| '{}\nFor more info on error messages, check: ' | |
| 'https://cloud.google.com/apis/design/errors'.format( | |
| response.error.message)) | |
| if __name__ == '__main__': | |
| get_image_ocr() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment