Last active
September 26, 2024 12:37
-
-
Save scrapehero/b85a280dc0d993f665c91e0332cf618f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pytesseract | |
import sys | |
import argparse | |
try: | |
import Image | |
except ImportError: | |
from PIL import Image | |
from subprocess import check_output | |
def resolve(path): | |
print("Resampling the Image") | |
check_output(['convert', path, '-resample', '600', path]) | |
return pytesseract.image_to_string(Image.open(path)) | |
if __name__=="__main__": | |
argparser = argparse.ArgumentParser() | |
argparser.add_argument('path',help = 'Captcha file path') | |
args = argparser.parse_args() | |
path = args.path | |
print('Resolving Captcha') | |
captcha_text = resolve(path) | |
print('Extracted Text',captcha_text) |
sudo apt-get install tesseract-ocr
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
I got below error.
Please help.
Resolving Captcha
Resampling the Image
Traceback (most recent call last):
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pytesseract\pytesseract.py", line 226, in run_tesseract
proc = subprocess.Popen(cmd_args, **subprocess_args())
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\subprocess.py", line 854, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\subprocess.py", line 1307, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] The system cannot find the file specified
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "OCR_image_processing.py", line 22, in
captcha_text = resolve(path)
File "OCR_image_processing.py", line 14, in resolve
return pytesseract.image_to_string(Image.open(path))
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pytesseract\pytesseract.py", line 344, in image_to_string
return {
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pytesseract\pytesseract.py", line 347, in
Output.STRING: lambda: run_and_get_output(*args),
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pytesseract\pytesseract.py", line 258, in run_and_get_output
run_tesseract(**kwargs)
File "C:\Users\yenag\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pytesseract\pytesseract.py", line 230, in run_tesseract
raise TesseractNotFoundError()
pytesseract.pytesseract.TesseractNotFoundError: tesseract is not installed or it's not in your path