import scrapy
from itemloaders.processors import MapCompose, TakeFirst
from scrapy.loader import ItemLoader


def normalize_label(value: str) -> str:
    return value.removeprefix("Name:").strip()


class ImageLinkItem(scrapy.Item):
    label = scrapy.Field()
    href = scrapy.Field()


class ImageLinkLoader(ItemLoader):
    default_input_processor = MapCompose(str.strip)
    default_output_processor = TakeFirst()
    label_in = MapCompose(str.strip, normalize_label)


class LoaderSpider(scrapy.Spider):
    name = "loader"
    custom_settings = {
        "ROBOTSTXT_OBEY": False,
    }
    start_urls = [
        (
            "https://docs.scrapy.org/en/latest/_static/"
            "selectors-sample1.html"
        ),
    ]

    def parse(self, response):
        for link in response.css("#images a"):
            loader = ImageLinkLoader(
                item=ImageLinkItem(),
                selector=link,
            )
            loader.add_css("label", "::text")
            loader.add_css(
                "href",
                "::attr(href)",
                MapCompose(response.urljoin),
            )
            yield loader.load_item()