amazoncaptcha 0.1.0

Solving captchas never ends...

Amazon Captcha Solver

Pure Python, non-OCR, lightweight, Pillow-based solver for the Amazon image captcha.

Installation

pip install amazoncaptcha

Quick Snippet

from amazoncaptcha import AmazonCaptcha

solution = AmazonCaptcha('captcha.jpg').solve()

Popular Usage

from amazoncaptcha import AmazonCaptcha
from selenium import webdriver

driver = webdriver.Chrome()
driver.get('https://www.amazon.com/errors/validateCaptcha')

captcha = AmazonCaptcha.from_webdriver(driver)
solution = captcha.solve()

For Whom?

• Data extraction and web scraping specialists could use this tool, obviously, to bypass the Amazon captcha.
• Machine learning developers could use captchas folder (currently contains 15000 solved captchas) based on a demand.

Contribution

• If you checked the code and you know the way or have any ideas, how to make it better, feel free to fork-n-pull or contact me. Thank you!
• If you want to help with current problems, please check this file.

Changes

• Version 0.0.10:
  1. Reached 10000 training samples.
  2. Reached 90%+ accuracy.
• Version 0.0.11:
  1. Fixed error with captcha images that were taken from BytesIO.
• Version 0.0.12:
  1. Code adjustments and improvements.
  2. Program can now solve images where last letter is corrupted.
• Version 0.0.13:
  1. Added and tested 'from_webdriver' classmethod.
• Version 0.1.0:
  1. 100,000 captchas crash test, accuracy is 98.5%.