Skip to main content

ReCaptaBreaker

Auto Solve Google's Recaptcha Image Challenge with near human performance!



This is one of the first library that breaks google recaptcha image challenge using autmoated system right in your device, with near human accuracy!

Installing

You can use pypi distribution:

pip install recaptchabreaker

or install locally from source:

git clone https://github.com/Hackear2041/ReCaptchaBreaker.git
python setup.py install

Models will be downloaded on first use.

Usage

  1. You can use the solver in selenium based drivers
from recaptchabreaker import ReCaptchaBreaker
breaker = RecaptchBreaker() 

# Load the page, where recaptcha needs to be solved.
# The method will automatically find the captcha and solve it.
breaker.solve_captcha(driver)
  1. You can directly classify on images as well
from recaptchabreaker import ReCaptchaBreaker
breaker = RecaptchBreaker() 

# Load the list of images
image_list : List[PIL.Image] = ...

for pred in breaker.solve_images():
    print(pred) # Prints dictionary of label:score

Hardware Requirements

Any device with python support and atleast 1GB RAM and 500MB free space should be supported. Expected classification time is ~1sec for 4*4 recaptcha Grid, and is dependent on number of CPU cores available. Faster Models Coming Soon!

How it Works?

I train Clip model for classification and Diffusion models for synthetic dataset generation. Further, using an iterative procedure, new annotated data points are collected by applying a week classifier to a real recaptcha system. The classifier model is further trained on the collected and augmented dataset resulting in a better classifier. The method is easily extendible to other forms of image captcha tasks such as hCaptcha.

Citing

If you find this repo useful, please consider citing the following paper:

@software{Anonymous_ReCaptchaBreaker_Breaking_Google_s_2022,
	author = {Anonymous},
	month = {12},
	title = {{ReCaptchaBreaker: Breaking Google's Recaptcha Image Challenge with near human performance}},
	url = {https://github.com/Hackear2041/ReCaptchaBreaker},
	version = {1.0.0},
	year = {2022}
}

Disclaimer⚠️

This repo is for educational and research purposes only. Any actions and/or activities related to the material contained on this repo is solely your responsibility. The misuse of the information in this repo can result in criminal charges brought against the persons in question. The author will not be held responsible in the event any criminal charges be brought against any individuals misusing the information in this repo to break the law. However, if you think this repo violates any of your terms of usage or policies, feel free to contact me.

Release files for ReCaptchaBreaker 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ReCaptchaBreaker 0.2.0
File Size Uploaded
ReCaptchaBreaker-0.2.0.tar.gz 7.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ReCaptchaBreaker 0.2.0
File Interpreter ABI Platform
ReCaptchaBreaker-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 15.9 kB

Release files / ReCaptchaBreaker-0.2.0.tar.gz

Download URL ReCaptchaBreaker-0.2.0.tar.gz
Size 7.4 kB
Tags Source
SHA-256 checksum
How to use checksums
abcf468c8fd2990038ba7463573e8fc1fd553d76c8d1edc9d6abc750eaad7532
BLAKE2b-256 checksum
How to use checksums
e06979eaeafbf7ce677abdd2c8534aefd17ff546adc61c71c0f60578afd1ab4f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.13

Release files / ReCaptchaBreaker-0.2.0-py3-none-any.whl

Download URL ReCaptchaBreaker-0.2.0-py3-none-any.whl
Size 8.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6aa9cf030c9ed65baa23d00f53ed82811e91804e3c27cd5958432d0b94c1eafd
BLAKE2b-256 checksum
How to use checksums
b7d47fcc7ec2657196325b6281828088ccf43bf11cbd5a9d93fc624c5e043580
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.13

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page