Notes

Write a note in this area. It's really easy to share with others. Click here ...import cv2
import pytesseract
import pandas as pd

# Load the image
image_path = 'table_image.png' # Replace with your image file path
img = cv2.imread(image_path)

# Convert the image to grayscale for OCR
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Perform OCR to extract text from the image
text = pytesseract.image_to_string(gray)

# Split the extracted text into lines
lines = text.split('n')

# Initialize variables to store table data
table_data = []
current_row = []

# Define a function to check if a line contains tabular data
def is_tabular_data(line):
# You may need to customize this function based on your specific table format
# For example, you can check for the presence of columns, separators, etc.
return True if line.strip() else False

# Process each line of extracted text
for line in lines:
if is_tabular_data(line):
current_row.append(line.strip())
elif current_row:
table_data.append(current_row.copy())
current_row.clear()

# Convert the table data into a DataFrame
table_df = pd.DataFrame(table_data)

# Define the output CSV file path
csv_output_path = 'table_data.csv'

# Save the DataFrame as a CSV file
table_df.to_csv(csv_output_path, index=False)

print(f'Table data saved to {csv_output_path}')