from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class CatalogCrawlSpider(CrawlSpider):
    name = "catalog_crawl"
    allowed_domains = ["app.internal.example"]
    start_urls = ["https://app.internal.example/products/"]

    rules = (
        Rule(
            LinkExtractor(
                allow=(r"/products/page/\d+/$",),
                restrict_css=("main.catalog",),
            ),
            follow=True,
        ),
        Rule(
            LinkExtractor(
                allow=(r"/products/[^/]+/$",),
                restrict_css=("main.catalog",),
            ),
            callback="parse_item",
        ),
    )

    def parse_item(self, response):
        yield {
            "name": response.css("h1::text").get(),
            "price": response.css("p.price::text").get(),
            "url": response.url,
        }