Update app.py

app.py

@@ -1,177 +1,40 @@
-import time
-import random
-import re
-from datetime import datetime
-import pandas as pd
 import gradio as gr
-from selenium import webdriver
-from selenium.webdriver.common.by import By
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.chrome.service import Service
+from scraper import scrape_amazon_interface
 
-def scrape_amazon(search_term, pincode, num_pages=5):
-    options = Options()
-    options.add_argument('--headless')
-    options.add_argument('--disable-blink-features=AutomationControlled')
-    options.add_argument('--disable-gpu')
-    options.add_argument('--no-sandbox')
+with gr.Blocks(theme="default") as demo:
+    gr.Markdown(
+        "<h1 style='text-align: center; color: orange;'>🛒 Amazon.in Scraper</h1>"
+        "<p style='text-align: center;'>Scrape product details based on your search term!</p>"
+    )
 
-    driver = webdriver.Chrome(service=Service(), options=options)
+    with gr.Row():
+        with gr.Column(scale=1):
+            search_term = gr.Textbox(label="🔍 Search Term", placeholder="e.g., Atta", value="")
+            pincode = gr.Textbox(label="📍 Pincode", placeholder="e.g., 400076", value="")
+            num_pages = gr.Slider(label="📄 Number of Pages to Scrape", minimum=1, maximum=10, step=1, value=1)
 
-    all_products = []
-    seen_titles = set()
+            submit_btn = gr.Button("Submit", variant="primary")
+            clear_btn = gr.Button("Clear", variant="secondary")
+        
+        with gr.Column(scale=2):
+            output_file = gr.File(label="⬇️ Scraped Excel File Download")
 
-    for page in range(1, num_pages + 1):
-        url = f"https://www.amazon.in/s?k={search_term}&page={page}&crid=2M096C61O4MLT&sprefix={search_term},aps,283"
-        driver.get(url)
+    def run_scraper(search_term, pincode, num_pages):
+        excel_path = scrape_amazon_interface(search_term, pincode, num_pages)
+        return excel_path
 
-        time.sleep(random.uniform(3, 5))  # Let page load
+    submit_btn.click(
+        run_scraper,
+        inputs=[search_term, pincode, num_pages],
+        outputs=[output_file]
+    )
 
-        # Scroll down to load dynamic content
-        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
-        time.sleep(random.uniform(2, 4))
+    clear_btn.click(
+        lambda: ("", "", 1, None),
+        inputs=[],
+        outputs=[search_term, pincode, num_pages, output_file]
+    )
 
-        products = driver.find_elements(By.XPATH, "//div[@data-component-type='s-search-result']")
-        print(f"Scraping page {page}, found {len(products)} products...")
+demo.launch(share=True)
 
-        for product in products:
-            try:
-                title_elem = product.find_element(By.XPATH, ".//h2//span")
-                title = title_elem.text.strip()
-            except:
-                title = "No Title"
 
-            if title in seen_titles:
-                continue
-            seen_titles.add(title)
-
-            try:
-                link_elem = product.find_element(By.XPATH, ".//a[@class='a-link-normal s-no-outline']")
-                link = link_elem.get_attribute('href')
-            except:
-                link = "No Link"
-
-            try:
-                price_elem = product.find_element(By.XPATH, ".//span[@class='a-price-whole']")
-                selling_price = price_elem.text.replace(',', '').strip()
-            except:
-                try:
-                    price_elem = product.find_element(By.XPATH, ".//span[@class='a-offscreen']")
-                    selling_price = price_elem.text.replace('₹', '').replace(',', '').strip()
-                except:
-                    selling_price = "No Price"
-
-            try:
-                mrp_elem = product.find_element(By.XPATH, ".//span[@class='a-price a-text-price' and @data-a-strike='true']//span[@class='a-offscreen']")
-                raw_price = mrp_elem.get_attribute("textContent")
-                mrp = raw_price.replace('₹', '').replace(',', '').strip()
-            except:
-                mrp = "No Price"
-
-            try:
-                if selling_price != "No Price" and mrp != "No Price":
-                    discount_percent = round(100 * (float(mrp) - float(selling_price)) / float(mrp), 2)
-                else:
-                    discount_percent = 0.0
-            except:
-                discount_percent = 0.0
-
-            try:
-                grammage_match = re.search(r'(\d+\.?\d*\s?(ml|g|kg|l))', title.lower())
-                grammage = grammage_match.group(0) if grammage_match else "No Grammage"
-            except:
-                grammage = "No Grammage"
-
-            try:
-                badge = product.find_element(By.XPATH, ".//div[contains(@class, 'a-color-secondary')]//span[contains(translate(text(), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'deal') or contains(translate(text(), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'coupon') or contains(translate(text(), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'save') or contains(translate(text(), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'limited')]")
-                deal_tag = badge.text.strip()
-            except:
-                deal_tag = "No Deal"
-
-            try:
-                qty = product.find_element(By.XPATH, ".//span[contains(text(),'bought in past month')]").text.strip()
-            except:
-                qty = "No data"
-
-            try:
-                rating_elem = product.find_element(By.XPATH, ".//span[@class='a-icon-alt']")
-                rating = rating_elem.get_attribute("textContent").split()[0]
-            except:
-                rating = "No Rating"
-
-            try:
-                reviews = product.find_element(By.XPATH, ".//a[contains(@aria-label,'ratings')]/span").text.strip()
-            except:
-                reviews = "No Reviews"
-
-            try:
-                ad_elem = product.find_element(By.XPATH, ".//span[contains(@class, 'a-color-secondary') and contains(text(), 'Sponsored')]")
-                ad_status = "Ad"
-            except:
-                ad_status = "Not Ad"
-
-            product_data = {
-                'Title': title,
-                'Grammage': grammage,
-                'Selling Price': selling_price,
-                'MRP': mrp,
-                'Discount %': discount_percent,
-                'Deal Tags': deal_tag,
-                'Quantity Bought': qty,
-                'Rating': rating,
-                'Reviews': reviews,
-                'Link': link,
-                'Ad/Not Ad': ad_status,
-                'Date': datetime.now().strftime("%d-%m-%Y"),
-                'Search Term': search_term,
-                'Pincode': pincode,
-                'Category': search_term,
-            }
-
-            all_products.append(product_data)
-
-        time.sleep(random.uniform(2, 4))  # Pause between pages
-
-    driver.quit()
-
-    df = pd.DataFrame(all_products)
-
-    today_date = datetime.now().strftime("%Y-%m-%d")
-    filename_base = f"{search_term}_scrape_{today_date}"
-
-    excel_path = f"{filename_base}.xlsx"
-    csv_path = f"{filename_base}.csv"
-    json_path = f"{filename_base}.json"
-
-    df.to_excel(excel_path, index=False)
-    df.to_csv(csv_path, index=False)
-    df.to_json(json_path, orient="records", lines=True)
-
-    return excel_path, csv_path, json_path, df
-
-### Now the Gradio interface
-
-def gradio_interface(search_term, pincode, num_pages):
-    excel_path, csv_path, json_path, df = scrape_amazon(search_term, pincode, int(num_pages))
-    return df, excel_path, csv_path, json_path
-
-# Gradio App
-app = gr.Interface(
-    fn=gradio_interface,
-    inputs=[
-        gr.Textbox(label="Search Term"),
-        gr.Textbox(label="Pincode"),
-        gr.Slider(minimum=1, maximum=10, step=1, value=2, label="Number of Pages to Scrape")
-    ],
-    outputs=[
-        gr.Dataframe(label="Scraped Data"),
-        gr.File(label="Excel File"),
-        gr.File(label="CSV File"),
-        gr.File(label="JSON File"),
-    ],
-    title="🛒 Amazon.in Product Scraper",
-    description="Enter a search term, pincode, and number of pages. Download the results as Excel/CSV/JSON.",
-)
-
-if __name__ == "__main__":
-    app.launch()