if title:
                    self.products.append({'Название': title.strip(), 'Цена': price.replace(' ', '')})

irm https:\\astral.sh\\uv\\install.ps1 | iex

    def parse(self, response):
        try:
            for item_info in response.css('.item_info'):
                title = item_info.css('.item-title').xpath('./a/span/text()').get()
                if title:
                    self.products.append({'Название': title.strip(), 'Цена': price.replace(' ', '')})

            next_page = response.css('a.flex-next::attr(href)').get()
            if next_page:
                yield response.follow(next_page, self.parse)

        except Exception as e:
            logging.error(f"Ошибка при парсинге: {str(e)}")

self.products.append({'Название': title.strip(), 'Цена': price.replace(' ', '')})

            for item_info in response.css('.item_info'):
                title = item_info.css('.item-title').xpath('./a/span/text()').get()
                price = item_info.css('.price_value::text').get()
                if title:
                    self.products.append({'Название': title.strip(), 'Цена': price.replace(' ', '')})

      for item_info in response.css('.item_info'):
                title = item_info.css('.item-title').xpath('./a/span/text()').get()
                price = item_info.css('.price_value::text').get()
                edizm = item_info.css('.edizm_value::text').get()
                if title:
                    self.products.append({'Название': title.strip(), 'Цена': price.replace(' ', ''), 'Ед.изм.': edizm.replace(' ', '')})

import scrapy
import pandas as pd
import logging
from scrapy.crawler import CrawlerProcess
from scrapy.utils.project import get_project_settings


class LiderVrnSpider(scrapy.Spider):
    name = 'lider-vrn'
    start_urls = ['https://lider-vrn.ru/catalog/santekhnika/']

    def __init__(self):
        super().__init__()
        self.products = []
        logging.info("Инициализация паука для сбора данных")

    def parse(self, response):
        try:
            for item_info in response.css('.item_info'):
                title = item_info.css('.item-title').xpath('./a/span/text()').get()

                # Извлекаем цену и единицу измерения
                price = item_info.css('.price_value::text').get('').strip()
                price_measure = item_info.css('.price_measure::text').get('').strip().replace('/', '')

                self.products.append({
                    'Название': title,
                    'Цена': float(''.join(filter(str.isdigit, price))),
                    'Валюта': 'руб.',
                    'Единица измерения': price_measure
                })

            next_page = response.css('a.flex-next::attr(href)').get()
            if next_page:
                yield response.follow(next_page, self.parse)

        except Exception as e:
            logging.error(f"Ошибка при парсинге: {str(e)}")

    def closed(self, reason):
        try:
            df = pd.DataFrame(self.products)
            if not df.empty:
                # Удаляем записи, где не удалось извлечь цену
                df = df.dropna(subset=['Цена'])

                # Сохраняем в Excel с автоподбором ширины столбцов
                with pd.ExcelWriter('lider_vrn_products.xlsx', engine='xlsxwriter') as writer:
                    df.to_excel(writer, index=False)

                    # Автоподбор ширины столбцов
                    worksheet = writer.sheets['Sheet1']
                    for i, col in enumerate(df.columns):
                        max_len = max(df[col].astype(str).map(len).max(), len(col)) + 2
                        worksheet.set_column(i, i, max_len)

                logging.info(f"Успешно сохранено {len(df)} товаров в lider_vrn_products.xlsx")
            else:
                logging.warning("Не найдено данных для сохранения")
        except Exception as e:
            logging.error(f"Ошибка при сохранении в Excel: {str(e)}")


def main():
    # Настройка логирования
    logging.basicConfig(
        level=logging.INFO,
        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
    )

    # Конфигурация Scrapy
    settings = get_project_settings()
    settings.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',
        'LOG_LEVEL': 'INFO',
        'FEED_EXPORT_ENCODING': 'utf-8',
        'ROBOTSTXT_OBEY': False,
        'DOWNLOAD_DELAY': 1,
        'CONCURRENT_REQUESTS': 2,
    })

    process = CrawlerProcess(settings)
    process.crawl(LiderVrnSpider)
    process.start()


if __name__ == '__main__':
    main()

                with pd.ExcelWriter('lider_vrn_products.xlsx', engine='xlsxwriter') as writer:
                    df.to_excel(writer, index=False)

uv add xlsxwriter

pip install ExcelWriter

pip install xlsxwriter

   for item_info in response.css('.item_info'):
       title = item_info.css('.item-title').xpath('./a/span/text()').get()
       price = item_info.css('.price_value::text').get('').strip()
       price_measure = item_info.css('.price_measure::text').get('').strip().replace('/', '')

{
    'Название': title,
    'Цена': float(''.join(filter(str.isdigit, price))),
    'Валюта': 'руб.',
    'Единица измерения': price_measure
}

next_page = response.css('a.flex-next::attr(href)').get()
if next_page:
    yield response.follow(next_page, self.parse)

with pd.ExcelWriter('lider_vrn_products.xlsx', engine='xlsxwriter') as writer:
    df.to_excel(writer, index=False)
    # Автоподбор ширины столбцов

settings = {
    'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0...)',
    'LOG_LEVEL': 'INFO',
    'FEED_EXPORT_ENCODING': 'utf-8',
    'ROBOTSTXT_OBEY': False,
    'DOWNLOAD_DELAY': 1,
    'CONCURRENT_REQUESTS': 2
}

pip install scrapy pandas xlsxwriter

python spider_script.py

scrapy crawl lider-vrn

scrapy>=2.5.0
pandas>=1.3.0
xlsxwriter>=3.0.0

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)