python - scrapy extract only one element

Question

I have the following data extract problem: The spider extracts only first item from every page. There are over a dozen downloadable properties on each site.

When I delete item_loader.default_output_processor = TakeFirst () the spider extracts all the correct data but it puts all the data together…

Can anyone help how to solve it?

Here is the code: spider.py

[...]

class RealEstateSpider(scrapy.Spider):
    name = 'realestates'
    start_urls = [
        'www.webtoscrape.com'
    ]

    def parse(self, response):
        item_loader = ItemLoader(item=REItem(), response=response)
        item_loader.default_input_processor = MapCompose(remove_tags)
        item_loader.default_output_processor = TakeFirst()

        item_loader.add_css("price", ".offer-item-price")
        item_loader.add_css("size", ".offer-item-area")
        item_loader.add_css("rooms", ".offer-item-rooms")
            
        yield item_loader.load_item()


        next_page = response.css('.pager-next a::attr(href)').get()

        if next_page is not None:
            yield response.follow(next_page, callback=self.parse)

items.py

[...]

class REItem(scrapy.Item):
    price = scrapy.Field(
        input_processor=MapCompose(remove_tags, lambda value: float(value.replace("
", "").replace(" ", "").replace(",", ".")))
    )
    size = scrapy.Field(
        input_processor=MapCompose(remove_tags, lambda value: float(value.replace("
", "").replace(" ", "").replace(",", ".")))
    )
    rooms = scrapy.Field(
        input_processor=MapCompose(remove_tags, lambda value: int(value.replace(">", "").replace("
", "").replace(" ", "")))
    )

Answer 1

等待大神答复