shihaam/recipt-ocr-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

i tried python, i dont like python but this works

Browse Source
This commit is contained in:
Shihaam Abdul Rahman 2024-08-02 23:14:28 +05:00
parent c35ff9d1dd
commit 1f5b32029e
Signed by: shihaam
GPG Key ID: 6DA2E87EBC227636
4 changed files with 5 additions and 120 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
bml.py
View File

@ -1,25 +0,0 @@
import sys
import pytesseract
from PIL import Image
import json
def ocr_image_to_json(image_path):
try:
# Open the image file
image = Image.open(image_path)
# Perform OCR on the image
ocr_result = pytesseract.image_to_data(image, output_type=pytesseract.Output.DICT)
# Convert the OCR result to JSON
ocr_json = json.dumps(ocr_result, indent=4)
print(ocr_json)
except Exception as e:
print(f"Error: {e}")
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python ocr_to_json.py <image_path>")
else:
image_path = sys.argv[1]
ocr_image_to_json(image_path)

5
ocr.sh Executable file
View File

@ -0,0 +1,5 @@
#!/bin/bash
INPUT_IMAGE=$1
tesseract $INPUT_IMAGE stdout

25
printall.py
View File

@ -1,25 +0,0 @@
import sys
import pytesseract
from PIL import Image
def ocr_image_to_text(image_path):
try:
# Open the image file
image = Image.open(image_path)
# Perform OCR on the image
ocr_result = pytesseract.image_to_data(image, output_type=pytesseract.Output.DICT)
# Extract and print the text portion
text = [word for word in ocr_result['text'] if word.strip() != ""]
print(" ".join(text))
except Exception as e:
print(f"Error: {e}")
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python ocr_to_text.py <image_path>")
else:
image_path = sys.argv[1]
ocr_image_to_text(image_path)

70
processed.py
View File

@ -1,70 +0,0 @@
import sys
import pytesseract
from PIL import Image
import re
import json
def ocr_image_to_json(image_path):
try:
# Open the image file
image = Image.open(image_path)
# Perform OCR on the image
ocr_result = pytesseract.image_to_data(image, output_type=pytesseract.Output.DICT)
text = " ".join([word for word in ocr_result['text'] if word.strip() != ""])
# Debug: Print the extracted text
print("Extracted Text:", text)
# Regex patterns
reference_pattern = r"BLAZ\d{12}"
date_pattern = r"\d{2}/\d{2}/\d{4}\s?\d{2}:\d{2}"
amount_pattern = r"MVR\s?(\d+\.\d{2})"
to_address_pattern = r"(9\d{17}|7\d{13})"
# Extracting data using regex
reference = re.search(reference_pattern, text)
transaction_date = re.search(date_pattern, text)
amount = re.search(amount_pattern, text)
to_address = re.search(to_address_pattern, text)
# Debug: Print the matched regex groups
print("Reference:", reference.group() if reference else "Not found")
print("Transaction Date:", transaction_date.group() if transaction_date else "Not found")
print("Amount:", amount.group(1) if amount else "Not found")
print("To Address:", to_address.group() if to_address else "Not found")
# Find 'from' and 'to' names
names_pattern = re.compile(r"([A-Z]+\s?[A-Z.]+)")
names = names_pattern.findall(text)
# Debug: Print the names found
print("Names Found:", names)
from_name, to_name = "", ""
if len(names) > 1:
from_name, to_name = names[0], names[1]
# Prepare the result in JSON format
result = {
"status": "SUCCESS",
"message": "Thank you. Transfer transaction is successful.",
"reference": reference.group() if reference else "",
"transaction_date": transaction_date.group() if transaction_date else "",
"from": from_name,
"to_name": to_name,
"to_account": to_address.group() if to_address else "",
"amount": amount.group(1) if amount else ""
}
# Print the result as JSON
print(json.dumps(result, indent=4))
except Exception as e:
print(f"Error: {e}")
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python ocr_to_json.py <image_path>")
else:
image_path = sys.argv[1]
ocr_image_to_json(image_path)