finding anwsers to kbc questions using image processing and web scrapping.
- Python : Python >= 3.0 ( including 3.6 🎉 )
$ pip install pytesseract
$ pip install pillow
$ pip install mechanize
$ pip install nltk
$ pip install BeautifulSoup
$ pip install html2text
Installing Via GitHub
$ git clone https://github.com/kartikeyangupta/KBC-Hack.git
$ cd KBC-Hack
$ python process_the_image.py
- change the path to tesseract in main.py to the directory you have cloned the repository.
pytesseract.pytesseract.tesseract_cmd = 'C://Users//Mr-Robot//Desktop//Image2Text//Tesseract-OCR/tesseract'
-
Select your Image set the image location in the code.
-
Run the code and enjoy.
Easy.
If you're having issues with the packaged executable or using this tool in general, I recommend you to upload your issues on the issue page .Once the software gets stable and 90% efficient I will upload a .exe file for the software.