Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -2,28 +2,30 @@ import fitz # PyMuPDF
|
|
| 2 |
import pandas as pd
|
| 3 |
import gradio as gr
|
| 4 |
import tempfile
|
|
|
|
| 5 |
|
| 6 |
def extract_po_to_excel(pdf_file):
|
| 7 |
try:
|
| 8 |
-
#
|
|
|
|
| 9 |
with fitz.open(pdf_file.name) as pdf:
|
| 10 |
data = []
|
|
|
|
|
|
|
| 11 |
for page_num in range(pdf.page_count):
|
| 12 |
page = pdf[page_num]
|
| 13 |
text = page.get_text("text")
|
|
|
|
| 14 |
|
| 15 |
# Simple example of extraction (customize parsing as needed)
|
| 16 |
lines = text.splitlines()
|
| 17 |
for line in lines:
|
| 18 |
-
# Only extract lines with known keywords (sample logic; adjust as necessary)
|
| 19 |
if "Pos." in line or "Item Code" in line:
|
| 20 |
data.append(line)
|
| 21 |
|
| 22 |
# Example structure, parse `data` into structured format
|
| 23 |
structured_data = []
|
| 24 |
for line in data:
|
| 25 |
-
# Custom parsing logic goes here; here's a basic split by spaces
|
| 26 |
-
# Adjust parsing to match your actual data needs
|
| 27 |
parts = line.split()
|
| 28 |
if len(parts) > 1:
|
| 29 |
structured_data.append({
|
|
@@ -34,16 +36,20 @@ def extract_po_to_excel(pdf_file):
|
|
| 34 |
|
| 35 |
# Create DataFrame and export to Excel
|
| 36 |
df = pd.DataFrame(structured_data)
|
| 37 |
-
|
|
|
|
| 38 |
# Save to temporary file
|
| 39 |
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
|
| 40 |
df.to_excel(temp_file.name, index=False)
|
| 41 |
temp_file.close()
|
|
|
|
| 42 |
|
| 43 |
return temp_file.name
|
| 44 |
|
| 45 |
except Exception as e:
|
| 46 |
-
print
|
|
|
|
|
|
|
| 47 |
return None
|
| 48 |
|
| 49 |
def main(pdf_file):
|
|
@@ -66,3 +72,4 @@ if __name__ == "__main__":
|
|
| 66 |
interface.launch()
|
| 67 |
|
| 68 |
|
|
|
|
|
|
| 2 |
import pandas as pd
|
| 3 |
import gradio as gr
|
| 4 |
import tempfile
|
| 5 |
+
import traceback
|
| 6 |
|
| 7 |
def extract_po_to_excel(pdf_file):
|
| 8 |
try:
|
| 9 |
+
# Attempt to open and read the PDF file
|
| 10 |
+
print("Starting PDF extraction process.")
|
| 11 |
with fitz.open(pdf_file.name) as pdf:
|
| 12 |
data = []
|
| 13 |
+
print("PDF opened successfully.")
|
| 14 |
+
|
| 15 |
for page_num in range(pdf.page_count):
|
| 16 |
page = pdf[page_num]
|
| 17 |
text = page.get_text("text")
|
| 18 |
+
print(f"Extracted text from page {page_num + 1}")
|
| 19 |
|
| 20 |
# Simple example of extraction (customize parsing as needed)
|
| 21 |
lines = text.splitlines()
|
| 22 |
for line in lines:
|
|
|
|
| 23 |
if "Pos." in line or "Item Code" in line:
|
| 24 |
data.append(line)
|
| 25 |
|
| 26 |
# Example structure, parse `data` into structured format
|
| 27 |
structured_data = []
|
| 28 |
for line in data:
|
|
|
|
|
|
|
| 29 |
parts = line.split()
|
| 30 |
if len(parts) > 1:
|
| 31 |
structured_data.append({
|
|
|
|
| 36 |
|
| 37 |
# Create DataFrame and export to Excel
|
| 38 |
df = pd.DataFrame(structured_data)
|
| 39 |
+
print("DataFrame created successfully.")
|
| 40 |
+
|
| 41 |
# Save to temporary file
|
| 42 |
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
|
| 43 |
df.to_excel(temp_file.name, index=False)
|
| 44 |
temp_file.close()
|
| 45 |
+
print(f"Excel file saved at {temp_file.name}")
|
| 46 |
|
| 47 |
return temp_file.name
|
| 48 |
|
| 49 |
except Exception as e:
|
| 50 |
+
# Capture and print the full traceback for debugging
|
| 51 |
+
print("An error occurred during PDF to Excel conversion.")
|
| 52 |
+
traceback.print_exc()
|
| 53 |
return None
|
| 54 |
|
| 55 |
def main(pdf_file):
|
|
|
|
| 72 |
interface.launch()
|
| 73 |
|
| 74 |
|
| 75 |
+
|