Spaces:
Sleeping
Sleeping
File size: 4,350 Bytes
5c6ed8c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
#!/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)
|