Wednesday, February 7, 2018

Image captcha recognizing and extract string for captcha bypass

Install pytesseract and images,
sudo pip install pytesseract
sudo pip install pillow

Install Google Tesseract OCR in the machine. In Linux,
apt-get install tesseract-ocr

type in the terminal 'tesseract' and see whether its working.

Then the following is the code for captcha recognize.

Code :

from PIL import Image
import pytesseract

print pytesseract.image_to_string(Image.open('/home/ubuntu/Desktop/index.jpeg'))


Instead of the indicated path put the captcha image path.

Source:
https://pypi.python.org/pypi/pytesseract

No comments:

Post a Comment