Last active
November 28, 2023 07:41
-
-
Save lobstrio/8010d0a21c48b8c807f0c3820467ee0c to your computer and use it in GitHub Desktop.
Solving (simple) Captcha, using PyTesseract, PIL, and Python 3
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/python3 | |
# coding: utf-8 | |
import pytesseract | |
import os | |
import argparse | |
try: | |
import Image, ImageOps, ImageEnhance, imread | |
except ImportError: | |
from PIL import Image, ImageOps, ImageEnhance | |
def solve_captcha(path): | |
""" | |
Convert a captcha image into a text, | |
using PyTesseract Python-wrapper for Tesseract | |
Arguments: | |
path (str): | |
path to the image to be processed | |
Return: | |
'textualized' image | |
""" | |
image = Image.open(path).convert('RGB') | |
image = ImageOps.autocontrast(image) | |
filename = "{}.png".format(os.getpid()) | |
image.save(filename) | |
text = pytesseract.image_to_string(Image.open(filename)) | |
return text | |
if __name__ == '__main__': | |
argparser = argparse.ArgumentParser() | |
argparser.add_argument("-i", "--image", required=True, help="path to input image to be OCR'd") | |
args = vars(argparser.parse_args()) | |
path = args["image"] | |
print('-- Resolving') | |
captcha_text = solve_captcha(path) | |
print('-- Result: {}'.format(captcha_text)) |
doesn't work even for easy captchas
Not working
Good enough. Working for simple captchas. Thanks.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
im going to try this today loll.