Create app.py

app.py

@@ -0,0 +1,99 @@
+import gradio as gr
+import torch
+from flair.data import Sentence
+from flair.models import SequenceTagger
+import requests
+import re
+from bs4 import BeautifulSoup
+
+# Load FashionNLP (Flair-based NER model)
+tagger = SequenceTagger.load("flair/ner-english-large")
+
+# Regex for extracting price
+price_pattern = re.compile(r'(\bunder\b|\babove\b|\bbelow\b|\bbetween\b)?\s?(\d{1,5})\s?(AED|USD|EUR)?', re.IGNORECASE)
+
+# Keywords for gender extraction
+gender_keywords = ["men", "male", "women", "female", "unisex"]
+
+def extract_fashion_entities(text):
+    """
+    Extracts fashion-related entities (Brand, Category, Material, Price, Gender) from text.
+    """
+    sentence = Sentence(text)
+    tagger.predict(sentence)
+
+    extracted_entities = {"Brand": "Unknown", "Category": "Unknown", "Material": "Unknown", "Price": "Unknown", "Gender": "Unknown"}
+
+    for entity in sentence.get_spans('ner'):
+        entity_text = entity.text
+        entity_label = entity.tag
+
+        if entity_label in ["ORG", "BRAND", "HOUSE"]:
+            extracted_entities["Brand"] = entity_text
+        elif entity_label in ["PRODUCT", "CATEGORY"]:
+            extracted_entities["Category"] = entity_text
+        elif entity_label in ["MATERIAL"]:
+            extracted_entities["Material"] = entity_text
+        elif entity_label in ["PRICE"]:
+            extracted_entities["Price"] = entity_text
+        elif entity_label in ["GENDER"]:
+            extracted_entities["Gender"] = entity_text
+
+    # Extract gender
+    for gender in gender_keywords:
+        if gender in text.lower():
+            extracted_entities["Gender"] = gender.capitalize()
+            break
+
+    # Extract price if not found by NER
+    price_match = price_pattern.search(text)
+    if price_match and extracted_entities["Price"] == "Unknown":
+        condition, amount, currency = price_match.groups()
+        extracted_entities["Price"] = f"{condition.capitalize() if condition else ''} {amount} {currency if currency else 'AED'}".strip()
+
+    return extracted_entities
+
+def scrape_fashion_trends(url):
+    """
+    Scrapes fashion trend articles from a given URL and extracts key entities.
+    """
+    headers = {'User-Agent': 'Mozilla/5.0'}
+    response = requests.get(url, headers=headers)
+    
+    if response.status_code != 200:
+        return {"Error": "Unable to fetch data"}
+    
+    soup = BeautifulSoup(response.text, 'html.parser')
+    
+    # Extract article text
+    paragraphs = soup.find_all("p")
+    text = " ".join([p.text for p in paragraphs])
+
+    # Run entity extraction
+    extracted_trends = extract_fashion_entities(text)
+    
+    return extracted_trends
+
+# Define Gradio UI
+def parse_fashion_query(user_query):
+    """
+    Parses a fashion search query and extracts structured attributes.
+    """
+    return extract_fashion_entities(user_query)
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🛍️ Luxury Fashion Query Parser using FashionNLP")
+
+    with gr.Tab("Search Query Parser"):
+        query_input = gr.Textbox(label="Enter your search query", placeholder="e.g., Gucci men’s perfume under 200AED")
+        output_box = gr.JSON(label="Parsed Output")
+        parse_button = gr.Button("Parse Query")
+        parse_button.click(parse_fashion_query, inputs=[query_input], outputs=[output_box])
+
+    with gr.Tab("Fashion Trends Analyzer"):
+        url_input = gr.Textbox(label="Enter Fashion News URL", placeholder="e.g., https://www.vogue.com/fashion")
+        trends_output = gr.JSON(label="Extracted Trends")
+        scrape_button = gr.Button("Analyze Trends")
+        scrape_button.click(scrape_fashion_trends, inputs=[url_input], outputs=[trends_output])
+
+demo.launch()