Spaces:
Sleeping
Sleeping
| #!/usr/bin/env python | |
| # coding: utf-8 | |
| # In[ ]: | |
| import gradio as gr | |
| from selenium import webdriver | |
| from selenium.webdriver.chrome.options import Options | |
| from bs4 import BeautifulSoup | |
| from transformers import pipeline | |
| import time | |
| # Set up Selenium with headless Chrome | |
| def setup_driver(): | |
| options = Options() | |
| options.headless = True | |
| driver = webdriver.Chrome(options=options) # Make sure you have 'chromedriver' installed | |
| return driver | |
| # Function to extract text from the URL using Selenium | |
| def extract_text(url): | |
| try: | |
| driver = setup_driver() | |
| driver.get(url) | |
| time.sleep(3) # Wait for page to load completely | |
| page_source = driver.page_source | |
| driver.quit() | |
| soup = BeautifulSoup(page_source, "html.parser") | |
| text = ' '.join(soup.stripped_strings) | |
| return text | |
| except Exception as e: | |
| return f"Error extracting text from URL: {str(e)}" | |
| # Load Hugging Face model (for extracting named entities or QA) | |
| try: | |
| ner_model = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english") | |
| except Exception as e: | |
| ner_model = None | |
| print(f"Error loading model: {str(e)}") | |
| # Function to extract information using Hugging Face model | |
| def extract_info_with_model(text): | |
| if not ner_model: | |
| return { | |
| "Keytags": "Model loading failed.", | |
| "Amenities": "Model loading failed.", | |
| "Facilities": "Model loading failed.", | |
| "Seller Name": "Model loading failed.", | |
| "Location Details": "Model loading failed." | |
| } | |
| try: | |
| # Apply named entity recognition (NER) to extract entities from the text | |
| ner_results = ner_model(text) | |
| # Initialize variables | |
| keytags = [] | |
| seller_name = "" | |
| location_details = "" | |
| amenities = "" | |
| facilities = "" | |
| # Search for relevant named entities | |
| for entity in ner_results: | |
| if entity['label'] == 'ORG': | |
| keytags.append(entity['word']) # Example: Company or key term (this can be changed) | |
| elif entity['label'] == 'PERSON': | |
| seller_name = entity['word'] # If a person is mentioned, consider it the seller name | |
| elif entity['label'] == 'GPE': | |
| location_details = entity['word'] # Geopolitical entity as location | |
| # For amenities and facilities, you can modify the logic or use additional models (e.g., question-answering models) | |
| amenities = "No amenities found" # Placeholder for the amenities | |
| facilities = "No facilities found" # Placeholder for the facilities | |
| return { | |
| "Keytags": ", ".join(keytags) if keytags else "No keytags found", | |
| "Amenities": amenities, | |
| "Facilities": facilities, | |
| "Seller Name": seller_name if seller_name else "No seller name found", | |
| "Location Details": location_details if location_details else "No location details found" | |
| } | |
| except Exception as e: | |
| return { | |
| "Keytags": f"Error processing text: {str(e)}", | |
| "Amenities": f"Error processing text: {str(e)}", | |
| "Facilities": f"Error processing text: {str(e)}", | |
| "Seller Name": f"Error processing text: {str(e)}", | |
| "Location Details": f"Error processing text: {str(e)}" | |
| } | |
| # Function to combine the extraction process (from URL + model processing) | |
| def get_info(url): | |
| text = extract_text(url) | |
| if "Error" in text: | |
| return text, text, text, text, text # Return the error message for all outputs | |
| extracted_info = extract_info_with_model(text) | |
| return ( | |
| extracted_info["Keytags"], | |
| extracted_info["Amenities"], | |
| extracted_info["Facilities"], | |
| extracted_info["Seller Name"], | |
| extracted_info["Location Details"] | |
| ) | |
| # Gradio Interface to allow user input and display output | |
| demo = gr.Interface( | |
| fn=get_info, | |
| inputs="text", # Input is a URL | |
| outputs=["text", "text", "text", "text", "text"], # Outputs for each field (Keytags, Amenities, etc.) | |
| title="Real Estate Info Extractor", | |
| description="Extract Keytags, Amenities, Facilities, Seller Name, and Location Details from a real estate article URL." | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch(show_api=False) | |