diff --git a/docs/topics/exporters.rst b/docs/topics/exporters.rst index 74256eef4..c4cd05683 100644 --- a/docs/topics/exporters.rst +++ b/docs/topics/exporters.rst @@ -93,24 +93,25 @@ described next. 1. Declaring a serializer in the field -------------------------------------- -If you use :class:`~scrapy.Item` you can declare a serializer in the -:ref:`field metadata `. The serializer must be -a callable which receives a value and returns its serialized form. +Every :ref:`item type ` except :class:`dict` lets you declare a +serializer in the :ref:`field metadata `. The serializer +must be a callable which receives a value and returns its serialized form. Example: .. code-block:: python - import scrapy + from dataclasses import dataclass, field def serialize_price(value): return f"$ {str(value)}" - class Product(scrapy.Item): - name = scrapy.Field() - price = scrapy.Field(serializer=serialize_price) + @dataclass + class Product: + name: str + price: float = field(metadata={"serializer": serialize_price}) 2. Overriding the serialize_field() method diff --git a/docs/topics/loaders.rst b/docs/topics/loaders.rst index 5ad005893..3ccc90bf9 100644 --- a/docs/topics/loaders.rst +++ b/docs/topics/loaders.rst @@ -102,14 +102,13 @@ One approach to overcome this is to define items using the .. code-block:: python from dataclasses import dataclass, field - from typing import Optional @dataclass class InventoryItem: - name: Optional[str] = field(default=None) - price: Optional[float] = field(default=None) - stock: Optional[int] = field(default=None) + name: str | None = field(default=None) + price: float | None = field(default=None) + stock: int | None = field(default=None) .. _topics-loaders-processors: @@ -228,7 +227,8 @@ metadata. Here is an example: .. code-block:: python - import scrapy + from dataclasses import dataclass, field + from itemloaders.processors import Join, MapCompose, TakeFirst from w3lib.html import remove_tags @@ -238,14 +238,21 @@ metadata. Here is an example: return value - class Product(scrapy.Item): - name = scrapy.Field( - input_processor=MapCompose(remove_tags), - output_processor=Join(), + @dataclass + class Product: + name: str | None = field( + default=None, + metadata={ + "input_processor": MapCompose(remove_tags), + "output_processor": Join(), + }, ) - price = scrapy.Field( - input_processor=MapCompose(remove_tags, filter_price), - output_processor=TakeFirst(), + price: str | None = field( + default=None, + metadata={ + "input_processor": MapCompose(remove_tags, filter_price), + "output_processor": TakeFirst(), + }, ) diff --git a/docs/topics/media-pipeline.rst b/docs/topics/media-pipeline.rst index 8c04c578d..037fe87fa 100644 --- a/docs/topics/media-pipeline.rst +++ b/docs/topics/media-pipeline.rst @@ -337,17 +337,18 @@ respectively), the pipeline will put the results under the respective field When using :ref:`item types ` for which fields are defined beforehand, you must define both the URLs field and the results field. For example, when using the images pipeline, items must define both the ``image_urls`` and the -``images`` field. For instance, using the :class:`~scrapy.Item` class: +``images`` field. For instance, using a dataclass: .. code-block:: python - import scrapy + from dataclasses import dataclass, field - class MyItem(scrapy.Item): + @dataclass + class MyItem: # ... other item fields ... - image_urls = scrapy.Field() - images = scrapy.Field() + image_urls: list[str] = field(default_factory=list) + images: list[dict] = field(default_factory=list) If you want to use another field name for the URLs key or for the results key, it is also possible to override it. diff --git a/docs/topics/spiders.rst b/docs/topics/spiders.rst index 806af509f..bcef9d5f6 100644 --- a/docs/topics/spiders.rst +++ b/docs/topics/spiders.rst @@ -457,13 +457,14 @@ with a ``TestItem`` declared in a ``myproject.items`` module: .. code-block:: python - import scrapy + from dataclasses import dataclass - class TestItem(scrapy.Item): - id = scrapy.Field() - name = scrapy.Field() - description = scrapy.Field() + @dataclass + class TestItem: + id: str | None = None + name: str | None = None + description: str | None = None .. currentmodule:: scrapy.spiders @@ -556,7 +557,6 @@ Let's now take a look at an example CrawlSpider with rules: .. code-block:: python - import scrapy from scrapy.spiders import CrawlSpider, Rule from scrapy.linkextractors import LinkExtractor @@ -576,7 +576,7 @@ Let's now take a look at an example CrawlSpider with rules: def parse_item(self, response): self.logger.info("Hi, this is an item page! %s", response.url) - item = scrapy.Item() + item = {} item["id"] = response.xpath('//td[@id="item_id"]/text()').re(r"ID: (\d+)") item["name"] = response.xpath('//td[@id="item_name"]/text()').get() item["description"] = response.xpath( @@ -714,9 +714,9 @@ These spiders are pretty easy to use, let's have a look at one example: ) item = TestItem() - item["id"] = node.xpath("@id").get() - item["name"] = node.xpath("name").get() - item["description"] = node.xpath("description").get() + item.id = node.xpath("@id").get() + item.name = node.xpath("name").get() + item.description = node.xpath("description").get() return item Basically what we did up there was to create a spider that downloads a feed from @@ -778,9 +778,9 @@ Let's see an example similar to the previous one, but using a self.logger.info("Hi, this is a row!: %r", row) item = TestItem() - item["id"] = row["id"] - item["name"] = row["name"] - item["description"] = row["description"] + item.id = row["id"] + item.name = row["name"] + item.description = row["description"] return item diff --git a/scrapy/templates/project/module/items.py.tmpl b/scrapy/templates/project/module/items.py.tmpl index 88a18331c..e7d525f36 100644 --- a/scrapy/templates/project/module/items.py.tmpl +++ b/scrapy/templates/project/module/items.py.tmpl @@ -3,10 +3,11 @@ # See documentation in: # https://docs.scrapy.org/en/latest/topics/items.html -import scrapy +from dataclasses import dataclass -class ${ProjectName}Item(scrapy.Item): +@dataclass +class ${ProjectName}Item: # define the fields for your item here like: - # name = scrapy.Field() + # name: str | None = None pass