Solve Captcha Using Selenium Python

Question

This is the website(https://appext20.dos.ny.gov/corp_public/CORPSEARCH.ENTITY_SEARCH_ENTRY). I just want to solve the captcha that appear in that website? Anybody have any idea.

Thanks in Advance

Answer 1

You can't. CAPTCHA means Completely Automated Public Turing test to tell Computers and Humans Apart. So, by definition, resolving a CAPTCHA cannot be automated, Otherwise, it could not tell computers and humans apart and hence fails to be a CAPTCHA. So you have to human to complete CAPTCHA and access website.

Answer 2

The captcha at this site is meant to be not solvable by computers, but nowadays this kind of captcha can be solved automatically.

How? There are several approaches:

1. training a neural network (usually a CNN) to solve the captcha. This requires several 1000 captchas and their solutions for training, but this can be achieved easily by the third approach

2. these captchas are very simple, it might even be possible to solve them by first doing some smart image preprocessing and then tinkering with some standard OCR libraries.

3. for quick results there are third party services that provide an API where you basically send the image and get back the solved captcha. Internally they use either one of the above approaches or click workers who are getting paid to solve the captchas manually.