Spaces:
Sleeping
Sleeping
Delete app.py
Browse files
app.py
DELETED
@@ -1,121 +0,0 @@
|
|
1 |
-
#!/usr/bin/env python
|
2 |
-
# coding: utf-8
|
3 |
-
|
4 |
-
# In[ ]:
|
5 |
-
|
6 |
-
|
7 |
-
import gradio as gr
|
8 |
-
from selenium import webdriver
|
9 |
-
from selenium.webdriver.chrome.options import Options
|
10 |
-
from bs4 import BeautifulSoup
|
11 |
-
from transformers import pipeline
|
12 |
-
import time
|
13 |
-
|
14 |
-
# Set up Selenium with headless Chrome
|
15 |
-
def setup_driver():
|
16 |
-
options = Options()
|
17 |
-
options.headless = True
|
18 |
-
driver = webdriver.Chrome(options=options) # Make sure you have 'chromedriver' installed
|
19 |
-
return driver
|
20 |
-
|
21 |
-
# Function to extract text from the URL using Selenium
|
22 |
-
def extract_text(url):
|
23 |
-
try:
|
24 |
-
driver = setup_driver()
|
25 |
-
driver.get(url)
|
26 |
-
time.sleep(3) # Wait for page to load completely
|
27 |
-
page_source = driver.page_source
|
28 |
-
driver.quit()
|
29 |
-
|
30 |
-
soup = BeautifulSoup(page_source, "html.parser")
|
31 |
-
text = ' '.join(soup.stripped_strings)
|
32 |
-
return text
|
33 |
-
except Exception as e:
|
34 |
-
return f"Error extracting text from URL: {str(e)}"
|
35 |
-
|
36 |
-
# Load Hugging Face model (for extracting named entities or QA)
|
37 |
-
try:
|
38 |
-
ner_model = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english")
|
39 |
-
except Exception as e:
|
40 |
-
ner_model = None
|
41 |
-
print(f"Error loading model: {str(e)}")
|
42 |
-
|
43 |
-
# Function to extract information using Hugging Face model
|
44 |
-
def extract_info_with_model(text):
|
45 |
-
if not ner_model:
|
46 |
-
return {
|
47 |
-
"Keytags": "Model loading failed.",
|
48 |
-
"Amenities": "Model loading failed.",
|
49 |
-
"Facilities": "Model loading failed.",
|
50 |
-
"Seller Name": "Model loading failed.",
|
51 |
-
"Location Details": "Model loading failed."
|
52 |
-
}
|
53 |
-
|
54 |
-
try:
|
55 |
-
# Apply named entity recognition (NER) to extract entities from the text
|
56 |
-
ner_results = ner_model(text)
|
57 |
-
|
58 |
-
# Initialize variables
|
59 |
-
keytags = []
|
60 |
-
seller_name = ""
|
61 |
-
location_details = ""
|
62 |
-
amenities = ""
|
63 |
-
facilities = ""
|
64 |
-
|
65 |
-
# Search for relevant named entities
|
66 |
-
for entity in ner_results:
|
67 |
-
if entity['label'] == 'ORG':
|
68 |
-
keytags.append(entity['word']) # Example: Company or key term (this can be changed)
|
69 |
-
elif entity['label'] == 'PERSON':
|
70 |
-
seller_name = entity['word'] # If a person is mentioned, consider it the seller name
|
71 |
-
elif entity['label'] == 'GPE':
|
72 |
-
location_details = entity['word'] # Geopolitical entity as location
|
73 |
-
|
74 |
-
# For amenities and facilities, you can modify the logic or use additional models (e.g., question-answering models)
|
75 |
-
amenities = "No amenities found" # Placeholder for the amenities
|
76 |
-
facilities = "No facilities found" # Placeholder for the facilities
|
77 |
-
|
78 |
-
return {
|
79 |
-
"Keytags": ", ".join(keytags) if keytags else "No keytags found",
|
80 |
-
"Amenities": amenities,
|
81 |
-
"Facilities": facilities,
|
82 |
-
"Seller Name": seller_name if seller_name else "No seller name found",
|
83 |
-
"Location Details": location_details if location_details else "No location details found"
|
84 |
-
}
|
85 |
-
except Exception as e:
|
86 |
-
return {
|
87 |
-
"Keytags": f"Error processing text: {str(e)}",
|
88 |
-
"Amenities": f"Error processing text: {str(e)}",
|
89 |
-
"Facilities": f"Error processing text: {str(e)}",
|
90 |
-
"Seller Name": f"Error processing text: {str(e)}",
|
91 |
-
"Location Details": f"Error processing text: {str(e)}"
|
92 |
-
}
|
93 |
-
|
94 |
-
# Function to combine the extraction process (from URL + model processing)
|
95 |
-
def get_info(url):
|
96 |
-
text = extract_text(url)
|
97 |
-
if "Error" in text:
|
98 |
-
return text, text, text, text, text # Return the error message for all outputs
|
99 |
-
|
100 |
-
extracted_info = extract_info_with_model(text)
|
101 |
-
|
102 |
-
return (
|
103 |
-
extracted_info["Keytags"],
|
104 |
-
extracted_info["Amenities"],
|
105 |
-
extracted_info["Facilities"],
|
106 |
-
extracted_info["Seller Name"],
|
107 |
-
extracted_info["Location Details"]
|
108 |
-
)
|
109 |
-
|
110 |
-
# Gradio Interface to allow user input and display output
|
111 |
-
demo = gr.Interface(
|
112 |
-
fn=get_info,
|
113 |
-
inputs="text", # Input is a URL
|
114 |
-
outputs=["text", "text", "text", "text", "text"], # Outputs for each field (Keytags, Amenities, etc.)
|
115 |
-
title="Real Estate Info Extractor",
|
116 |
-
description="Extract Keytags, Amenities, Facilities, Seller Name, and Location Details from a real estate article URL."
|
117 |
-
)
|
118 |
-
|
119 |
-
if __name__ == "__main__":
|
120 |
-
demo.launch(show_api=False)
|
121 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|