Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import PyPDF2 | |
| import pandas as pd | |
| import io | |
| import traceback | |
| import tempfile # Import the tempfile module | |
| import os # Import the os module | |
| def find_keywords_in_pdf(pdf_file, keywords_str): | |
| """Extracts text from a PDF, finds keyword occurrences, and returns a CSV file path.""" | |
| try: | |
| keywords = [k.strip() for k in keywords_str.split(",")] | |
| keyword_page_numbers = {} | |
| try: | |
| pdf_reader = PyPDF2.PdfReader(pdf_file) | |
| num_pages = len(pdf_reader.pages) | |
| for keyword in keywords: | |
| keyword_page_numbers[keyword] = [] | |
| for page_number in range(num_pages): | |
| try: | |
| page = pdf_reader.pages[page_number] | |
| text = page.extract_text() | |
| for keyword in keywords: | |
| if keyword.lower() in text.lower(): | |
| keyword_page_numbers[keyword].append(page_number + 1) | |
| except Exception as e: | |
| print(f"Error processing page {page_number + 1}: {e}") | |
| traceback.print_exc() | |
| data = [] | |
| for keyword, page_numbers in keyword_page_numbers.items(): | |
| data.append({'Species Name': keyword, 'Page Number': ','.join(map(str, page_numbers))}) | |
| df = pd.DataFrame(data) | |
| csv_output = df.to_csv(index=False) | |
| # Create a temporary file to store the CSV data | |
| with tempfile.NamedTemporaryFile(mode="w+t", suffix=".csv", delete=False) as tmpfile: | |
| tmpfile.write(csv_output) | |
| csv_path = tmpfile.name # Get the path to the temporary file | |
| return csv_path # Return the file path to Gradio | |
| except PyPDF2.errors.PdfReadError as e: | |
| return f"Error: Could not read PDF. The file might be corrupted or use an unsupported format. Details: {e}" | |
| except Exception as e: | |
| print("General PDF processing error:", e) | |
| traceback.print_exc() | |
| return f"Error: Could not process PDF. Details: {e}. Check console for traceback." | |
| except Exception as e: | |
| print("Outer error:", e) | |
| traceback.print_exc() | |
| return f"Error: An unexpected error occurred. Details: {e}. Check console for traceback." | |
| def gradio_interface(pdf_file, keywords): | |
| """Gradio interface for the PDF keyword search.""" | |
| result = find_keywords_in_pdf(pdf_file, keywords) | |
| return result | |
| iface = gr.Interface( | |
| fn=gradio_interface, | |
| inputs=[ | |
| gr.File(label="Upload PDF File", file_types=[".pdf"]), | |
| gr.Textbox(lines=1, label="Enter Keywords (comma-separated)", placeholder="e.g., Nepal, India, China") | |
| ], | |
| outputs=gr.File(label="Download CSV of Keyword Page Numbers", file_types=[".csv"]), | |
| title="PDF Keyword Page Finder", | |
| description="Upload a PDF and enter keywords to find the page numbers where they appear. The output will be a CSV file." | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() |