Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from urllib.request import urlopen, Request | |
| from bs4 import BeautifulSoup | |
| from transformers import pipeline | |
| import os | |
| # Function to extract text from the URL | |
| def extract_text(url): | |
| req = Request(url, headers={'User-Agent': 'Mozilla/5.0'}) | |
| html = urlopen(req).read() | |
| text = ' '.join(BeautifulSoup(html, "html.parser").stripped_strings) | |
| return text | |
| # Load Hugging Face model (for extracting named entities or QA) | |
| # Here we use a named entity recognition model, but you can use a question answering model if needed | |
| ner_model = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english") | |
| # Function to extract information using Hugging Face model | |
| def extract_info_with_model(text): | |
| # Apply named entity recognition (NER) to extract entities from the text | |
| ner_results = ner_model(text) | |
| # You can refine this based on the type of entity or information you want to extract | |
| 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) | |
| # For now, we'll just return a placeholder for these | |
| amenities = "No amenities found" | |
| facilities = "No facilities found" | |
| 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" | |
| } | |
| # Function to combine the extraction process (from URL + model processing) | |
| def get_info(url): | |
| text = extract_text(url) | |
| extracted_info = extract_info_with_model(text) | |
| return extracted_info | |
| # 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) | |