Spaces:
Sleeping
Sleeping
File size: 1,774 Bytes
3dc4059 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
import tabula
from docx import Document
import cv2
import pytesseract
import pandas as pd
pytesseract.pytesseract.tesseract_cmd = r'./tesseract.exe' # Change the path accordingly
def extract_tables_from_pdf(file_path):
return tabula.read_pdf(file_path, pages="all", multiple_tables=True)
def extract_tables_from_image(image_path):
image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
text = pytesseract.image_to_string(image)
# Convert the extracted text to a dataframe (assuming one table in the image)
# The logic may vary based on the nature of your table
rows = text.split('\n')
data = [row.split() for row in rows if row]
df = pd.DataFrame(data[1:], columns=data[0])
return [df] # Returning as a list to be consistent with the PDF extraction function
# Decide extractor based on file extension
file_path = "./1234.jpg" # Change the extension to test
file_extension = file_path.split('.')[-1].lower()
if file_extension == "pdf":
tables = extract_tables_from_pdf(file_path)
elif file_extension in ["jpg", "jpeg", "png"]:
tables = extract_tables_from_image(file_path)
else:
raise ValueError(f"Unsupported file format: {file_extension}")
# Create a new Word document
doc = Document()
# Iterate through the extracted tables
for table_df in tables:
# Add table to Word document
t = doc.add_table(rows=1, cols=table_df.shape[1])
hdr_cells = t.rows[0].cells
for i, column in enumerate(table_df.columns):
hdr_cells[i].text = str(column)
for index, row in table_df.iterrows():
cells = t.add_row().cells
for i, value in enumerate(row):
cells[i].text = str(value)
# Save the Word document
doc.save("output.docx")
print("Tables exported to output.docx!")
|