0cf3297290
- Краулеры: smart_crawler.py, regional_crawler.py - Аудит: audit_orel_to_excel.py, audit_chukotka_to_excel.py - РКН проверка: check_rkn_registry.py, recheck_unclear_rkn.py - Отчёты: create_orel_horizontal_report.py - Обработка: process_all_hotels_embeddings.py - Документация: README.md, DB_SCHEMA_REFERENCE.md
320 lines
12 KiB
Python
Executable File
320 lines
12 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
"""
|
||
Массовый краулинг всех отелей в фоновом режиме
|
||
Обрабатывает все отели с сайтами, которые ещё не скраулены
|
||
"""
|
||
|
||
import asyncio
|
||
import psycopg2
|
||
from psycopg2.extras import Json
|
||
from urllib.parse import unquote, urlparse
|
||
from playwright.async_api import async_playwright
|
||
from bs4 import BeautifulSoup
|
||
import re
|
||
import logging
|
||
from datetime import datetime
|
||
from typing import Set, List, Dict
|
||
import sys
|
||
|
||
# Конфигурация БД
|
||
DB_CONFIG = {
|
||
'host': "147.45.189.234",
|
||
'port': 5432,
|
||
'database': "default_db",
|
||
'user': "gen_user",
|
||
'password': unquote("2~~9_%5EkVsU%3F2%5CS")
|
||
}
|
||
|
||
# Настройки краулинга
|
||
MAX_PAGES_PER_SITE = 20 # Максимум страниц с одного сайта
|
||
PAGE_TIMEOUT = 20000 # Уменьшено с 30 до 20 секунд
|
||
BATCH_SIZE = 50 # Обрабатывать пачками по 50 отелей
|
||
MAX_CONCURRENT = 5 # Увеличено с 3 до 5 браузеров одновременно
|
||
|
||
# Логирование
|
||
log_filename = f'mass_crawler_{datetime.now().strftime("%Y%m%d_%H%M%S")}.log'
|
||
logging.basicConfig(
|
||
level=logging.INFO,
|
||
format='%(asctime)s - %(levelname)s - %(message)s',
|
||
handlers=[
|
||
logging.FileHandler(log_filename),
|
||
logging.StreamHandler()
|
||
]
|
||
)
|
||
logger = logging.getLogger(__name__)
|
||
|
||
|
||
class TextCleaner:
|
||
"""Очистка HTML"""
|
||
|
||
@classmethod
|
||
def clean_html(cls, html: str) -> str:
|
||
"""Простая очистка HTML"""
|
||
if not html:
|
||
return ""
|
||
|
||
soup = BeautifulSoup(html, 'html.parser')
|
||
|
||
# Удаляем скрипты и стили
|
||
for tag in soup.find_all(['script', 'style', 'noscript']):
|
||
tag.decompose()
|
||
|
||
# Получаем чистый текст
|
||
text = soup.get_text()
|
||
|
||
# Очистка текста
|
||
text = re.sub(r'\s+', ' ', text)
|
||
text = re.sub(r'\n\s*\n', '\n', text)
|
||
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
||
|
||
return '\n'.join(lines)
|
||
|
||
|
||
async def crawl_hotel(hotel: Dict, semaphore: asyncio.Semaphore, browser):
|
||
"""Краулинг одного отеля"""
|
||
async with semaphore:
|
||
hotel_id = hotel['id']
|
||
hotel_name = hotel['full_name']
|
||
website = hotel['website_address']
|
||
region = hotel['region_name']
|
||
|
||
logger.info(f"🏨 Начинаю краулинг: {hotel_name} ({region})")
|
||
logger.info(f" URL: {website}")
|
||
|
||
try:
|
||
# Нормализация URL
|
||
if not website.startswith(('http://', 'https://')):
|
||
website = 'https://' + website
|
||
|
||
context = await browser.new_context(
|
||
user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
|
||
viewport={'width': 1920, 'height': 1080}
|
||
)
|
||
page = await context.new_page()
|
||
|
||
visited_urls = set()
|
||
pages_data = []
|
||
|
||
# Главная страница
|
||
try:
|
||
response = await page.goto(website, wait_until='domcontentloaded', timeout=PAGE_TIMEOUT)
|
||
|
||
if response and response.ok:
|
||
await page.wait_for_timeout(2000) # Ждём JS
|
||
|
||
html = await page.content()
|
||
cleaned_text = TextCleaner.clean_html(html)
|
||
|
||
pages_data.append({
|
||
'url': page.url,
|
||
'html': html,
|
||
'text': cleaned_text,
|
||
'status': response.status
|
||
})
|
||
visited_urls.add(page.url)
|
||
|
||
logger.info(f" ✅ Главная: {len(cleaned_text)} символов")
|
||
|
||
# Собираем ссылки
|
||
links = await page.eval_on_selector_all(
|
||
'a[href]',
|
||
'''elements => elements.map(e => e.href).filter(h => h && h.startsWith('http'))'''
|
||
)
|
||
|
||
# Фильтруем внутренние ссылки
|
||
base_domain = urlparse(website).netloc
|
||
internal_links = [
|
||
link for link in links
|
||
if urlparse(link).netloc == base_domain and link not in visited_urls
|
||
][:MAX_PAGES_PER_SITE - 1]
|
||
|
||
logger.info(f" 📄 Найдено {len(internal_links)} внутренних ссылок")
|
||
|
||
# Обходим внутренние страницы
|
||
for link in internal_links:
|
||
if len(pages_data) >= MAX_PAGES_PER_SITE:
|
||
break
|
||
|
||
try:
|
||
response = await page.goto(link, wait_until='domcontentloaded', timeout=PAGE_TIMEOUT)
|
||
|
||
if response and response.ok:
|
||
await page.wait_for_timeout(1000)
|
||
|
||
html = await page.content()
|
||
cleaned_text = TextCleaner.clean_html(html)
|
||
|
||
pages_data.append({
|
||
'url': page.url,
|
||
'html': html,
|
||
'text': cleaned_text,
|
||
'status': response.status
|
||
})
|
||
visited_urls.add(page.url)
|
||
|
||
logger.info(f" ✅ Страница {len(pages_data)}: {len(cleaned_text)} символов")
|
||
|
||
except Exception as e:
|
||
logger.warning(f" ⚠️ Ошибка страницы {link}: {e}")
|
||
continue
|
||
|
||
else:
|
||
logger.warning(f" ⚠️ Главная страница недоступна: {response.status if response else 'No response'}")
|
||
|
||
except Exception as e:
|
||
logger.error(f" ❌ Ошибка загрузки главной: {e}")
|
||
|
||
await context.close()
|
||
|
||
# Сохраняем в БД
|
||
if pages_data:
|
||
save_to_db(hotel_id, hotel_name, region, website, pages_data)
|
||
logger.info(f" 💾 Сохранено {len(pages_data)} страниц для {hotel_name}")
|
||
return True
|
||
else:
|
||
logger.warning(f" ⚠️ Нет данных для {hotel_name}")
|
||
return False
|
||
|
||
except Exception as e:
|
||
logger.error(f" ❌ Критическая ошибка для {hotel_name}: {e}")
|
||
return False
|
||
|
||
|
||
def save_to_db(hotel_id: str, hotel_name: str, region: str, website: str, pages_data: List[Dict]):
|
||
"""Сохранение в PostgreSQL"""
|
||
try:
|
||
conn = psycopg2.connect(**DB_CONFIG)
|
||
cur = conn.cursor()
|
||
|
||
# Сохраняем метаданные
|
||
from urllib.parse import urlparse
|
||
domain = urlparse(website).netloc
|
||
|
||
cur.execute("""
|
||
INSERT INTO hotel_website_meta (hotel_id, domain, main_url, pages_crawled, crawl_status, crawl_finished_at)
|
||
VALUES (%s, %s, %s, %s, %s, NOW())
|
||
ON CONFLICT (hotel_id) DO UPDATE SET
|
||
pages_crawled = EXCLUDED.pages_crawled,
|
||
crawl_status = EXCLUDED.crawl_status,
|
||
crawl_finished_at = EXCLUDED.crawl_finished_at
|
||
""", (hotel_id, domain, website, len(pages_data), 'completed'))
|
||
|
||
# Сохраняем сырой HTML
|
||
for page in pages_data:
|
||
cur.execute("""
|
||
INSERT INTO hotel_website_raw (hotel_id, url, html, status_code, crawled_at)
|
||
VALUES (%s, %s, %s, %s, NOW())
|
||
ON CONFLICT ON CONSTRAINT hotel_website_raw_hotel_id_url_key DO UPDATE SET
|
||
html = EXCLUDED.html,
|
||
status_code = EXCLUDED.status_code,
|
||
crawled_at = EXCLUDED.crawled_at
|
||
""", (hotel_id, page['url'], page['html'], page['status']))
|
||
|
||
# Сохраняем очищенный текст
|
||
for page in pages_data:
|
||
cur.execute("""
|
||
INSERT INTO hotel_website_processed (hotel_id, url, cleaned_text, processed_at)
|
||
VALUES (%s, %s, %s, NOW())
|
||
ON CONFLICT (hotel_id, url) DO UPDATE SET
|
||
cleaned_text = EXCLUDED.cleaned_text,
|
||
processed_at = EXCLUDED.processed_at
|
||
""", (hotel_id, page['url'], page['text']))
|
||
|
||
conn.commit()
|
||
cur.close()
|
||
conn.close()
|
||
|
||
except Exception as e:
|
||
logger.error(f"❌ Ошибка сохранения в БД: {e}")
|
||
|
||
|
||
def get_unprocessed_hotels(limit: int = None) -> List[Dict]:
|
||
"""Получить необработанные отели"""
|
||
conn = psycopg2.connect(**DB_CONFIG)
|
||
cur = conn.cursor()
|
||
|
||
query = """
|
||
SELECT id, full_name, region_name, website_address
|
||
FROM hotel_main
|
||
WHERE website_address IS NOT NULL
|
||
AND website_address != ''
|
||
AND id NOT IN (SELECT hotel_id FROM hotel_website_meta)
|
||
ORDER BY region_name, full_name
|
||
"""
|
||
|
||
if limit:
|
||
query += f" LIMIT {limit}"
|
||
|
||
cur.execute(query)
|
||
|
||
hotels = []
|
||
for row in cur.fetchall():
|
||
hotels.append({
|
||
'id': row[0],
|
||
'full_name': row[1],
|
||
'region_name': row[2],
|
||
'website_address': row[3]
|
||
})
|
||
|
||
cur.close()
|
||
conn.close()
|
||
|
||
return hotels
|
||
|
||
|
||
async def main():
|
||
"""Главная функция"""
|
||
logger.info("🚀 Запуск массового краулинга")
|
||
|
||
# Получаем необработанные отели
|
||
hotels = get_unprocessed_hotels()
|
||
total = len(hotels)
|
||
|
||
logger.info(f"📊 Найдено необработанных отелей: {total}")
|
||
|
||
if total == 0:
|
||
logger.info("✅ Все отели уже обработаны!")
|
||
return
|
||
|
||
# Запускаем краулинг
|
||
async with async_playwright() as p:
|
||
browser = await p.chromium.launch(headless=True)
|
||
|
||
semaphore = asyncio.Semaphore(MAX_CONCURRENT)
|
||
|
||
processed = 0
|
||
success = 0
|
||
|
||
# Обрабатываем пачками
|
||
for i in range(0, total, BATCH_SIZE):
|
||
batch = hotels[i:i + BATCH_SIZE]
|
||
|
||
logger.info(f"\n📦 Обработка пачки {i//BATCH_SIZE + 1}/{(total + BATCH_SIZE - 1)//BATCH_SIZE}")
|
||
logger.info(f" Отели {i+1}-{min(i+BATCH_SIZE, total)} из {total}")
|
||
|
||
tasks = [crawl_hotel(hotel, semaphore, browser) for hotel in batch]
|
||
results = await asyncio.gather(*tasks, return_exceptions=True)
|
||
|
||
batch_success = sum(1 for r in results if r is True)
|
||
success += batch_success
|
||
processed += len(batch)
|
||
|
||
logger.info(f"✅ Пачка завершена: {batch_success}/{len(batch)} успешно")
|
||
logger.info(f"📊 Общий прогресс: {processed}/{total} ({processed*100//total}%)")
|
||
|
||
await browser.close()
|
||
|
||
logger.info(f"\n🎉 КРАУЛИНГ ЗАВЕРШЁН!")
|
||
logger.info(f" Всего обработано: {processed}")
|
||
logger.info(f" Успешно: {success} ({success*100//processed}%)")
|
||
logger.info(f" Ошибок: {processed - success}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
try:
|
||
asyncio.run(main())
|
||
except KeyboardInterrupt:
|
||
logger.info("\n⚠️ Прервано пользователем")
|
||
sys.exit(0)
|
||
|