import requests from bs4 import BeautifulSoup import json import re from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.chrome.options import Options import time from urllib.parse import urljoin, urlparse import logging class AliExpressParser: def __init__(self, use_selenium=True): self.use_selenium = use_selenium self.session = requests.Session() self.session.headers.update({ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' }) if self.use_selenium: self.setup_selenium() def setup_selenium(self): """Настройка Selenium WebDriver""" chrome_options = Options() chrome_options.add_argument('--headless') chrome_options.add_argument('--no-sandbox') chrome_options.add_argument('--disable-dev-shm-usage') chrome_options.add_argument('--disable-gpu') chrome_options.add_argument('--window-size=1920,1080') chrome_options.add_argument('--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36') try: self.driver = webdriver.Chrome(options=chrome_options) self.wait = WebDriverWait(self.driver, 10) except Exception as e: logging.error(f"Ошибка инициализации Selenium: {e}") self.use_selenium = False def parse_product(self, url): """Основной метод парсинга товара""" try: if self.use_selenium: return self._parse_with_selenium(url) else: return self._parse_with_requests(url) except Exception as e: logging.error(f"Ошибка парсинга: {e}") return None def _parse_with_selenium(self, url): """Парсинг с использованием Selenium""" try: self.driver.get(url) time.sleep(3) # Ждем загрузки основных элементов self.wait.until(EC.presence_of_element_located((By.TAG_NAME, "body"))) # Получаем HTML после загрузки JavaScript soup = BeautifulSoup(self.driver.page_source, 'html.parser') return self._extract_data(soup, url) except Exception as e: logging.error(f"Ошибка Selenium парсинга: {e}") return None def _parse_with_requests(self, url): """Парсинг с использованием requests""" try: response = self.session.get(url, timeout=10) response.raise_for_status() soup = BeautifulSoup(response.content, 'html.parser') return self._extract_data(soup, url) except Exception as e: logging.error(f"Ошибка requests парсинга: {e}") return None def _extract_data(self, soup, url): """Извлечение данных из HTML""" result = { "title": "", "price": 0, "aliexpress_link": url, "category": "", "rating": 0, "orders_count": 0, "images": [], "ai_description": "" } # Извлечение названия товара title_selectors = [ 'h1[data-pl="product-title"]', 'h1.product-title-text', 'h1[class*="title"]', '.product-title h1', 'h1' ] result["title"] = self._extract_text_by_selectors(soup, title_selectors) # Извлечение цены price_selectors = [ '.product-price-current', '[class*="price-current"]', '.price-current', '[data-spm-anchor-id*="price"]', '.price' ] price_text = self._extract_text_by_selectors(soup, price_selectors) result["price"] = self._parse_price(price_text) # Извлечение рейтинга rating_selectors = [ '.overview-rating-average', '[class*="rating-average"]', '.rating-average', '.star-rating' ] rating_text = self._extract_text_by_selectors(soup, rating_selectors) result["rating"] = self._parse_rating(rating_text) # Извлечение количества заказов orders_selectors = [ '.product-reviewer-reviews', '[class*="sold"]', '.sold-count', '.order-count' ] orders_text = self._extract_text_by_selectors(soup, orders_selectors) result["orders_count"] = self._parse_orders_count(orders_text) # Извлечение категории category_selectors = [ '.breadcrumb a', '.nav-breadcrumb a', '[class*="breadcrumb"] a' ] result["category"] = self._extract_category(soup, category_selectors) # Извлечение изображений result["images"] = self._extract_images(soup) # Генерация AI описания result["ai_description"] = self._generate_ai_description(result) return result def _extract_text_by_selectors(self, soup, selectors): """Извлечение текста по списку CSS селекторов""" for selector in selectors: try: element = soup.select_one(selector) if element: return element.get_text(strip=True) except: continue return "" def _parse_price(self, price_text): """Парсинг цены из текста""" if not price_text: return 0 # Извлекаем числа из текста numbers = re.findall(r'[\d,]+\.?\d*', price_text.replace(',', '')) if numbers: try: return float(numbers[0]) except: return 0 return 0 def _parse_rating(self, rating_text): """Парсинг рейтинга из текста""" if not rating_text: return 0 # Ищем число от 0 до 5 match = re.search(r'([0-4]\.?\d*|5\.?0*)', rating_text) if match: try: return float(match.group(1)) except: return 0 return 0 def _parse_orders_count(self, orders_text): """Парсинг количества заказов из текста""" if not orders_text: return 0 # Ищем числа, возможно с k, K для тысяч match = re.search(r'(\d+(?:,\d+)*(?:\.\d+)?)\s*[kK]?', orders_text) if match: try: number = float(match.group(1).replace(',', '')) if 'k' in orders_text.lower() or 'K' in orders_text: number *= 1000 return int(number) except: return 0 return 0 def _extract_category(self, soup, selectors): """Извлечение категории товара""" for selector in selectors: try: elements = soup.select(selector) if elements and len(elements) > 1: # Берем предпоследний элемент breadcrumb return elements[-2].get_text(strip=True) except: continue return "unknown" def _extract_images(self, soup): """Извлечение изображений товара""" images = [] # Различные селекторы для изображений image_selectors = [ 'img[class*="image-item"]', '.image-item img', '.product-image img', '.gallery-image img', 'img[src*="alicdn"]' ] for selector in image_selectors: try: img_elements = soup.select(selector) for img in img_elements: src = img.get('src') or img.get('data-src') if src and src.startswith('http'): # Убираем параметры размера для получения оригинала clean_src = re.sub(r'_\d+x\d+\.', '_', src) if clean_src not in images: images.append(clean_src) if images: break except: continue return images[:10] # Ограничиваем до 10 изображений def _generate_ai_description(self, product_data): """Генерация AI описания товара""" # Простое описание на основе доступных данных title = product_data.get("title", "") price = product_data.get("price", 0) rating = product_data.get("rating", 0) orders = product_data.get("orders_count", 0) category = product_data.get("category", "") description = f"Товар '{title}' из категории '{category}' по цене ${price:.2f}." if rating > 0: description += f" Рейтинг: {rating} звезд." if orders > 0: description += f" Уже заказано: {orders} раз." return description def close(self): """Закрытие драйвера""" if self.use_selenium and hasattr(self, 'driver'): self.driver.quit() def parse_aliexpress_product(url): """Функция для парсинга товара AliExpress""" parser = AliExpressParser(use_selenium=True) try: result = parser.parse_product(url) return result finally: parser.close() # Пример использования if __name__ == "__main__": # Тестовый URL test_url = "https://pl.aliexpress.com/item/1005007191149791.html" print("Парсинг товара AliExpress...") result = parse_aliexpress_product(test_url) if result: print(json.dumps(result, indent=2, ensure_ascii=False)) else: print("Ошибка при парсинге товара")