Spaces:
Sleeping
Sleeping
Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
# coding: utf-8
|
3 |
+
|
4 |
+
# In[ ]:
|
5 |
+
|
6 |
+
|
7 |
+
import gradio as gr
|
8 |
+
from urllib.request import urlopen, Request
|
9 |
+
from bs4 import BeautifulSoup
|
10 |
+
from transformers import pipeline
|
11 |
+
import os
|
12 |
+
|
13 |
+
# Function to extract text from the URL
|
14 |
+
def extract_text(url):
|
15 |
+
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
|
16 |
+
html = urlopen(req).read()
|
17 |
+
text = ' '.join(BeautifulSoup(html, "html.parser").stripped_strings)
|
18 |
+
return text
|
19 |
+
|
20 |
+
# Load Hugging Face model (for extracting named entities or QA)
|
21 |
+
ner_model = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english")
|
22 |
+
|
23 |
+
# Function to extract information using Hugging Face model
|
24 |
+
def extract_info_with_model(text):
|
25 |
+
# Apply named entity recognition (NER) to extract entities from the text
|
26 |
+
ner_results = ner_model(text)
|
27 |
+
|
28 |
+
# Initialize variables
|
29 |
+
keytags = []
|
30 |
+
seller_name = ""
|
31 |
+
location_details = ""
|
32 |
+
amenities = ""
|
33 |
+
facilities = ""
|
34 |
+
|
35 |
+
# Search for relevant named entities
|
36 |
+
for entity in ner_results:
|
37 |
+
if entity['label'] == 'ORG':
|
38 |
+
keytags.append(entity['word']) # Example: Company or key term (this can be changed)
|
39 |
+
elif entity['label'] == 'PERSON':
|
40 |
+
seller_name = entity['word'] # If a person is mentioned, consider it the seller name
|
41 |
+
elif entity['label'] == 'GPE':
|
42 |
+
location_details = entity['word'] # Geopolitical entity as location
|
43 |
+
|
44 |
+
# For amenities and facilities, you can modify the logic or use additional models (e.g., question-answering models)
|
45 |
+
amenities = "No amenities found" # Placeholder for the amenities
|
46 |
+
facilities = "No facilities found" # Placeholder for the facilities
|
47 |
+
|
48 |
+
return {
|
49 |
+
"Keytags": ", ".join(keytags) if keytags else "No keytags found",
|
50 |
+
"Amenities": amenities,
|
51 |
+
"Facilities": facilities,
|
52 |
+
"Seller Name": seller_name if seller_name else "No seller name found",
|
53 |
+
"Location Details": location_details if location_details else "No location details found"
|
54 |
+
}
|
55 |
+
|
56 |
+
# Function to combine the extraction process (from URL + model processing)
|
57 |
+
def get_info(url):
|
58 |
+
text = extract_text(url)
|
59 |
+
extracted_info = extract_info_with_model(text)
|
60 |
+
|
61 |
+
# Print debug to understand what's being returned
|
62 |
+
print(extracted_info)
|
63 |
+
|
64 |
+
# Ensure the information is returned in the expected format
|
65 |
+
return (
|
66 |
+
extracted_info["Keytags"],
|
67 |
+
extracted_info["Amenities"],
|
68 |
+
extracted_info["Facilities"],
|
69 |
+
extracted_info["Seller Name"],
|
70 |
+
extracted_info["Location Details"]
|
71 |
+
)
|
72 |
+
|
73 |
+
# Gradio Interface to allow user input and display output
|
74 |
+
demo = gr.Interface(
|
75 |
+
fn=get_info,
|
76 |
+
inputs="text", # Input is a URL
|
77 |
+
outputs=["text", "text", "text", "text", "text"], # Outputs for each field (Keytags, Amenities, etc.)
|
78 |
+
title="Real Estate Info Extractor",
|
79 |
+
description="Extract Keytags, Amenities, Facilities, Seller Name, and Location Details from a real estate article URL."
|
80 |
+
)
|
81 |
+
|
82 |
+
if __name__ == "__main__":
|
83 |
+
demo.launch(show_api=False)
|
84 |
+
|