#!/usr/bin/env python3 """E-Commerce Daily Report Scraper""" import requests import re import json import sys from datetime import datetime from html.parser import HTMLParser HEADERS = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36', 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'en-US,en;q=0.9', } CATEGORIES = { 'electronics': 'https://www.amazon.com/Best-Sellers-Electronics/zgbs/electronics/', 'computers': 'https://www.amazon.com/Best-Sellers-Computers-Accessories/zgbs/computers/', 'home_kitchen': 'https://www.amazon.com/Best-Sellers-Kitchen-Small-Appliances/zgbs/kitchen/', 'smart_home': 'https://www.amazon.com/Best-Sellers-Smart-Home-Discovery/zgbs/industrial/', } class AmazonParser(HTMLParser): def __init__(self): super().__init__() self.products = [] self.in_product = False self.current_product = {} self.skip_tags = ['style', 'script', 'noscript', 'iframe'] self.in_skip = False self.tag_stack = [] def handle_starttag(self, tag, attrs): if tag in self.skip_tags: self.in_skip = True return self.tag_stack.append(tag) attrs_dict = dict(attrs) if 'class' in attrs_dict: cls = attrs_dict['class'].lower() # Amazon product container classes if any(x in cls for x in ['zg-item-immersion', 'p13n-asin', 'a-section', 'a-spacing']): if not self.in_product: self.in_product = True self.current_product = {} def handle_endtag(self, tag): if tag in self.skip_tags: self.in_skip = False return if self.tag_stack and self.tag_stack[-1] == tag: self.tag_stack.pop() if self.in_product and tag in ['div', 'li', 'span']: if self.current_product and len(self.products) < 20: self.products.append(self.current_product) self.in_product = False def handle_data(self, data): if self.in_skip or not self.in_product: return data = data.strip() if len(data) > 2 and len(data) < 200: if 'current_product' in dir() and self.current_product: if 'title' not in self.current_product: self.current_product['title'] = data def parse_amazon_page(html): """Extract products from Amazon bestsellers page""" products = [] # Try multiple patterns # Pattern 1: data-asin asins = re.findall(r'data-asin="([A-Z0-9]{10})"', html) # Pattern 2: Product title in links titles = re.findall(r'class="p13n-asin-title[^"]*"[^>]*>([^<]+)<', html) # Pattern 3: Price prices = re.findall(r'class="p13n-asin-price[^"]*"[^>]*>([^<]+)<', html) # Pattern 4: Rank ranks = re.findall(r'class="zg-item-number[^"]*">#(\d+)', html) # Pattern 5: Links links = re.findall(r'href="(/dp/[^"?]+)', html) # Combine for i in range(min(len(titles), 20)): p = { 'rank': ranks[i] if i < len(ranks) else str(i+1), 'title': titles[i].strip() if i < len(titles) else '', 'price': prices[i].strip() if i < len(prices) else 'N/A', 'link': f"https://www.amazon.com{links[i]}" if i < len(links) else '', } if p['title']: products.append(p) # Alternative: parse JSON data if not products: json_data = re.findall(r'window\.DSPData\s*=\s*({[^<]+})', html) return products[:20] def scrape_amazon_category(url, category_name): """Scrape a single Amazon category""" try: resp = requests.get(url, headers=HEADERS, timeout=15) resp.encoding = 'utf-8' html = resp.text products = parse_amazon_page(html) # Also try to extract from script tags if not products: # Look for JSON data script_content = re.findall(r']*type="application/json"[^>]*>([^<]+)', html) return { 'category': category_name, 'url': url, 'products': products, 'success': len(products) > 0, 'count': len(products) } except Exception as e: return {'category': category_name, 'url': url, 'error': str(e), 'products': [], 'success': False} def get_trending_searches(): """Get trending searches (alternative data source)""" try: url = 'https://completion.amazon.com/search/complete?method=1&marketplace=ATVPDKIKX0DER&query=trending+products&searchalias=aps&client=amazon-search-ui&x-asrc=search' resp = requests.get(url, headers=HEADERS, timeout=10) data = resp.json() return [s[0] for s in data.get('results', [])[:10]] except: return [] def format_report(results): """Format results into markdown report""" today = datetime.now().strftime('%Y-%m-%d') now = datetime.now().strftime('%Y-%m-%d %H:%M:%S') md = f"""## 🛒 E-Commerce Daily Report — {today} **Sources: Amazon Best Sellers, eBay Deals** --- ## 📦 Amazon Best Sellers by Category """ for r in results: if not r.get('success'): continue md += f"""### {r['category'].replace('_', ' ').title()} | # | Product | Price | |--|---------|-------| """ for p in r.get('products', [])[:10]: title = p.get('title', 'N/A')[:60] price = p.get('price', 'N/A') rank = p.get('rank', '-') md += f"| {rank} | {title} | {price} |\n" md += "\n" md += f""" ## 🔥 Trending Products (Amazon) """ trending = get_trending_searches() if trending: for i, t in enumerate(trending[:10], 1): md += f"{i}. {t}\n" else: md += "_No data available_\n" md += f""" --- ## 💡 Report Notes - Data collected from Amazon Best Sellers pages - Categories: Electronics, Computers, Home & Kitchen Small Appliances - Updated daily --- *Report generated: {now}* """ return md def main(): print("Scraping Amazon categories...") results = [] for cat_name, url in CATEGORIES.items(): print(f" - {cat_name}...", end=" ") r = scrape_amazon_category(url, cat_name) results.append(r) print(f"✓ {r.get('count', 0)} products" if r.get('success') else f"✗ {r.get('error', 'failed')}") report = format_report(results) print(f"\nReport length: {len(report)} chars") print(report) if __name__ == '__main__': main()