### Clone and Install Spider Creator

Source: https://github.com/carlosplanchon/spidercreator/blob/main/README.md

Clone the repository and install dependencies using uv or pip. Ensure you are in the main project folder.

```bash
git clone https://github.com/carlosplanchon/spidercreator.git
cd spidercreator

# If you are using uv just run:
uv sync

# If you run pyenv:
pip install -r requirements.txt
```

--------------------------------

### Install Playwright Browsers

Source: https://github.com/carlosplanchon/spidercreator/blob/main/README.md

Install the necessary browser binaries for Playwright to function.

```bash
playwright install chromium
```

--------------------------------

### Set OpenAI API Key

Source: https://github.com/carlosplanchon/spidercreator/blob/main/README.md

Export your OpenAI API key as an environment variable. This is required for the spider generation process.

```bash
export OPENAI_API_KEY=...
```

--------------------------------

### Playwright Spider for Tienda Inglesa

Source: https://github.com/carlosplanchon/spidercreator/blob/main/README.md

A Playwright spider implementation to scrape product data from Tienda Inglesa. It includes fetching HTML, parsing product listings, and extracting details from individual product pages.

```python
from playwright.sync_api import sync_playwright
from parsel import Selector

import prettyprinter

prettyprinter.install_extras()


class TiendaInglesaScraper:
    def __init__(self, base_url):
        self.base_url = base_url

    def fetch(self, page, url):
        page.goto(url)
        page.wait_for_load_state('networkidle')
        return page.content()

    def parse_homepage(self, html_content, page):
        selector = Selector(text=html_content)
        product_containers = selector.xpath("//div[contains(@class,'card-product-container')]")

        products = []

        for container in product_containers:
            product = {}

            product['name'] = container.xpath(".//span[contains(@class,'card-product-name')]/text()").get('').strip()
            relative_link = container.xpath(".//a/@href").get()
            product['link'] = self.base_url.rstrip('/') + relative_link if relative_link else None
            product['discount'] = container.xpath(".//ul[contains(@class,'card-product-promo')]//li[contains(@class,'card-product-badge')]/text()").get('').strip()
            product['price_before'] = container.xpath(".//span[contains(@class,'wTxtProductPriceBefore')]/text()").get('').strip()
            product['price_after'] = container.xpath(".//span[contains(@class,'ProductPrice')]/text()").get('').strip()

            if product['link']:
                detailed_html = self.fetch(page, product['link'])
                detailed_attrs = self.parse_product_page(detailed_html)
                product.update(detailed_attrs)

            print("--- PRODUCT ---")
            prettyprinter.cpprint(product)

            products.append(product)

        return products

    def parse_product_page(self, html_content):
        selector = Selector(text=html_content)

        detailed_attributes = {}

        detailed_attributes['description'] = selector.xpath("//span[contains(@class, 'ProductDescription')]/text()").get('').strip()

        return detailed_attributes


if __name__ == "__main__":

    base_url = 'https://www.tiendainglesa.com.uy/'

    scraper = TiendaInglesaScraper(base_url)

    with sync_playwright() as p:
        browser = p.chromium.launch(headless=False)
        page = browser.new_page()

        homepage_html = scraper.fetch(page, base_url)
        products_data = scraper.parse_homepage(homepage_html, page)

        browser.close()

    for idx, product in enumerate(products_data, 1):
        print(f"\nProduct {idx}:")
        for key, value in product.items():
            print(f"{key.title().replace('_', ' ')}: {value}")
```

--------------------------------

### Generate Playwright Spider with Spider Creator

Source: https://github.com/carlosplanchon/spidercreator/blob/main/README.md

Use the `create_spider` function to generate a Playwright spider. Define the task prompt, including the target URL and extraction details. The spider code will be saved to results/<task_id>/spider_code.py.

```python
from spidercreator import create_spider

# Define the task prompt
PRODUCT_LISTING_TASK_PROMPT = """
Navigate to {url} homepage.
Extract all products on the homepage with its visible attributes.

Select a small sample of products (e.g., 3–5) on the homepage.
For each selected product:
Extract all visible attributes (price, description, brand, stock status, images, etc.).
If a dedicated product page is available (e.g., "View details" link), click through and capture any additional attributes.
Stop after you've collected enough products to demonstrate the data extraction (3 to 5 products).
"""

# Uruguayan supermarket with product listings:
url = "https://tiendainglesa.com.uy/"

browser_use_task = PRODUCT_LISTING_TASK_PROMPT.format(url=url)

# This function generates a spider
# and saves it to results/<task_id>/spider_code.py
task_id: str = create_spider(browser_use_task=browser_use_task)
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.