Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from tempfile import TemporaryDirectory, NamedTemporaryFile | |
| from pdf2image import convert_from_path | |
| from PIL import Image | |
| import os | |
| from io import BytesIO | |
| import base64 | |
| import requests | |
| import pandas as pd | |
| import json | |
| import logging | |
| os.system("apt-get update") | |
| os.system("apt-get install poppler-utils") | |
| logging.basicConfig(level=logging.ERROR, format='%(asctime)s - %(levelname)s - %(message)s') | |
| # Function to convert PDF to images or open a single image | |
| def get_images(file_path): | |
| images = [] | |
| extension = os.path.splitext(file_path)[-1].lower() | |
| if extension == ".pdf": | |
| images = convert_from_path(file_path) | |
| elif extension in [".tiff", ".tif", ".png", ".jpg", ".jpeg"]: | |
| image = Image.open(file_path) | |
| images.append(image) | |
| return images | |
| # Function to encode image to base64 | |
| def encode_image_to_base64(image): | |
| # Ensure the image is in a format compatible with JPEG | |
| if image.mode in ["P", "RGBA"]: | |
| image = image.convert("RGB") | |
| buffered = BytesIO() | |
| image.save(buffered, format="JPEG") | |
| return base64.b64encode(buffered.getvalue()).decode("utf-8") | |
| def process_files_fixed(image_path, page_identifier, error_pages): | |
| api_key = os.getenv('OPENAI_API_KEY') | |
| headers = { | |
| "Content-Type": "application/json", | |
| "Authorization": f"Bearer {api_key}" | |
| } | |
| try: | |
| image = Image.open(image_path) | |
| base64_image = encode_image_to_base64(image) | |
| except Exception as e: | |
| logging.error(f"Failed to process image at {image_path}: {e}") | |
| error_pages.append(page_identifier) | |
| return [] | |
| prompt = """Perform OCR on this image. Analyze the table in the provided image, focusing on the first five columns labeled S.No, Reg #, Roll No. and Marks. Get the marks from the 6th column and write them in fifth column in integers, make sure to check them as well for correct integer number, I don't want any mistakes in the obtained marks. In case the table headers are not visible or not present, assume the mentioned order for the columns. Extract and list the data only from these columns, omitting any additional columns that may be present. But DO NOT skip any row from the table, extract all the rows present in the table. The obtained marks are written in both integral and written format as well. Verify both for better ocr in integers. | |
| Return the response in the following JSON response format: | |
| { | |
| "data": [ | |
| { | |
| "S_No": "1", | |
| "Reg": "059287", | |
| "Roll_No": "2345234", | |
| "Marks": "20" | |
| }, | |
| ... | |
| ] | |
| }""" | |
| payload = { | |
| "model": "gpt-4-vision-preview", | |
| "messages": [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| { | |
| "type": "text", | |
| "text": prompt | |
| }, | |
| { | |
| "type": "image_url", | |
| "image_url": f"data:image/jpeg;base64,{base64_image}" | |
| } | |
| ] | |
| } | |
| ], | |
| "max_tokens": 4096 | |
| } | |
| try: | |
| response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload) | |
| logging.info(f"Full API response: {response.text}") | |
| if response.status_code == 200: | |
| json_response = response.json() | |
| response_content = json_response["choices"][0]["message"]["content"] | |
| if response_content: | |
| try: | |
| json_string = response_content[response_content.find("{"): response_content.rfind("}") + 1] | |
| json_data = json.loads(json_string) | |
| if "data" in json_data and json_data["data"]: | |
| return json_data["data"] | |
| else: | |
| logging.error(f"No records found in page/file: {page_identifier}") | |
| error_pages.append(page_identifier) | |
| return [] | |
| except json.JSONDecodeError: | |
| logging.error(f"JSON parsing error in response for page/file {page_identifier}") | |
| error_pages.append(page_identifier) | |
| return [] | |
| else: | |
| logging.error(f"No content in JSON response for page/file {page_identifier}") | |
| error_pages.append(page_identifier) | |
| return [] | |
| else: | |
| logging.error(f"Error in API call for page/file {page_identifier}: HTTP {response.status_code} - {response.text}") | |
| error_pages.append(page_identifier) | |
| return [] | |
| except requests.exceptions.RequestException as e: | |
| logging.error(f"Network or API error when processing page/file {page_identifier}: {e}") | |
| error_pages.append(page_identifier) | |
| return [] | |
| def process_pdf_and_generate_csv(file_path): | |
| error_pages = [] # Initialize the list to track error pages or files | |
| images = get_images(file_path) | |
| structured_data = [] | |
| for i, image in enumerate(images, start=1): | |
| with TemporaryDirectory() as temp_dir: | |
| image_path = os.path.join(temp_dir, "image.jpg") | |
| image.save(image_path) | |
| data = process_files_fixed(image_path, i, error_pages) | |
| structured_data.extend(data or []) | |
| if structured_data: | |
| df = pd.DataFrame(structured_data) | |
| # Save to a temporary file to return through Gradio | |
| tmp_file = NamedTemporaryFile(delete=False, suffix='.csv') | |
| df.to_csv(tmp_file.name, index=False) | |
| return tmp_file.name, f"Errors or no records found in {len(error_pages)} pages/files: {error_pages}" | |
| else: | |
| return None, "No data to save or an error occurred." | |
| def gradio_interface(pdf_file): | |
| result_csv, message = process_pdf_and_generate_csv(pdf_file.name) | |
| if result_csv: | |
| return result_csv, message | |
| else: | |
| return None, message | |
| iface = gr.Interface(fn=gradio_interface, | |
| inputs=gr.File(label="Please upload your PDF file"), | |
| outputs=[gr.File(label="Download the generated CSV file"), gr.Textbox(label="Messages")], | |
| title="PDF to CSV Table Extractor", | |
| description="Upload a PDF file to extract tables into a CSV format.") | |
| iface.queue().launch(share=False) | |