#!/usr/bin/env python3 from playwright.sync_api import sync_playwright from bs4 import BeautifulSoup import sys import random import csv import re import os from datetime import datetime def user_agent_rotator(): user_agents = [ "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Safari/605.1.15", "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:124.0) Gecko/20100101 Firefox/124.0", "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:123.0) Gecko/20100101 Firefox/123.0" ] return random.choice(user_agents) def store_link(link): # Extract store name from link match = re.search(r'/str/([^/?]+)', link) if match: return match.group(1) return None def main(): # Check if user provided ID if len(sys.argv) < 2: print("Usage: python ebay_seller_csv.py [--save] [--debug] [--headless]") print("Example: python ebay_seller_csv.py 123456789,987654321 --save") print("Options:") print(" --save Save output to TSV file") print(" --debug Show debug information") print(" --headless Run in headless mode (default)") print(" --no-headless Run with visible browser") sys.exit(1) # Check for flags save_to_file = False headless_mode = True # Default to headless for CSV extraction debug_mode = False args = sys.argv[1:] if '--save' in args: save_to_file = True args.remove('--save') if '--debug' in args: debug_mode = True args.remove('--debug') if '--headless' in args: headless_mode = True args.remove('--headless') if '--no-headless' in args: headless_mode = False args.remove('--no-headless') if len(args) == 0: print("Please provide the item ID(s)") sys.exit(1) item_ids = args[0].strip().split(",") if debug_mode: print(f"Processing {len(item_ids)} item(s)...", file=sys.stderr) sellers_data = [] with sync_playwright() as p: # Configure browser arguments for stability browser_args = [ '--no-first-run', '--disable-default-apps', '--disable-dev-shm-usage', '--no-sandbox', '--disable-gpu' ] browser = p.firefox.launch( headless=headless_mode, args=browser_args ) context = browser.new_context( user_agent=user_agent_rotator(), ignore_https_errors=True, bypass_csp=True, java_script_enabled=True, extra_http_headers={ 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', 'Accept-Language': 'en-US,en;q=0.5', 'Accept-Encoding': 'gzip, deflate', 'DNT': '1', 'Connection': 'keep-alive', 'Upgrade-Insecure-Requests': '1', 'Sec-Fetch-Dest': 'document', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-Site': 'none', 'Sec-Fetch-User': '?1' } ) page = context.new_page() # Add stealth settings page.add_init_script(""" Object.defineProperty(navigator, 'webdriver', { get: () => undefined, }); """) try: for i, item_id in enumerate(item_ids): url = f"https://www.ebay.com/itm/{item_id}" if debug_mode: print(f"Processing item {i+1}/{len(item_ids)}: {item_id}", file=sys.stderr) # Add delay between requests if i > 0: page.wait_for_timeout(500) # 0.5 seconds try: # Allow redirects and wait for network idle - comprehensive loading response = page.goto( url, wait_until="networkidle", timeout=30000 ) # Wait for any additional redirects and network activity to settle completely page.wait_for_load_state("networkidle", timeout=15000) # Ensure DOM content is fully loaded page.wait_for_load_state("domcontentloaded", timeout=10000) # Wait for JavaScript to fully render seller elements page.wait_for_timeout(3000) # Try to extract seller info using JavaScript like in login.py seller_info = {} # find first that has data-clientpresentationmetadata and grab its value/text/href meta_anchor = page.query_selector(".x-sellercard-atf__info__about-seller>a[data-clientpresentationmetadata]") # print(f"{meta_anchor.inner_html() if meta_anchor else 'No meta anchor found'}") # Add item_id to the result seller_info['item_id'] = item_id # Populate expected fields seller_info['seller_name'] = meta_anchor.inner_text().strip() if meta_anchor else None seller_info['seller_link'] = store_link(meta_anchor.get_attribute('href') if meta_anchor else None) # Debug output (only if debug mode is enabled) if debug_mode: print(f"Item {item_id}: seller_name='{seller_info['seller_name']}', seller_link='{seller_info['seller_link']}'", file=sys.stderr) sellers_data.append(seller_info) except Exception as e: if debug_mode: print(f"Error processing item {item_id}: {e}", file=sys.stderr) # Add empty entry for failed items sellers_data.append({ 'item_id': item_id, 'seller_name': None, 'seller_link': None }) finally: browser.close() # Output CSV data if save_to_file: # Create files directory if it doesn't exist files_dir = os.path.join(os.getcwd(), 'files') os.makedirs(files_dir, exist_ok=True) # Generate filename with timestamp timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") filename = f"ebay_sellers_{timestamp}.tsv" file_path = os.path.join(files_dir, filename) # Save TSV to file (tab-separated) with open(file_path, 'w', newline='', encoding='utf-8') as csvfile: fieldnames = ['item_id', 'seller_name', 'seller_link'] writer = csv.DictWriter(csvfile, fieldnames=fieldnames, delimiter='\t') writer.writeheader() for seller in sellers_data: writer.writerow(seller) if debug_mode: print(f"TSV saved to: {file_path}", file=sys.stderr) print(f"Processed {len(sellers_data)} items", file=sys.stderr) else: # Print TSV to stdout (tab-separated) fieldnames = ['item_id', 'seller_name', 'seller_link'] writer = csv.DictWriter(sys.stdout, fieldnames=fieldnames, delimiter='\t') writer.writeheader() for seller in sellers_data: writer.writerow(seller) if __name__ == "__main__": main()