Source code for scrapy.item

"""
Scrapy Item

See documentation in docs/topics/item.rst
"""

from abc import ABCMeta
from collections.abc import MutableMapping
from copy import deepcopy
from pprint import pformat
from typing import Dict

from scrapy.utils.trackref import object_ref


class Field(dict):
    """Container of field metadata"""


[docs]class ItemMeta(ABCMeta): """Metaclass_ of :class:`Item` that handles field definitions. .. _metaclass: https://realpython.com/python-metaclasses """ def __new__(mcs, class_name, bases, attrs): classcell = attrs.pop("__classcell__", None) new_bases = tuple(base._class for base in bases if hasattr(base, "_class")) _class = super().__new__(mcs, "x_" + class_name, new_bases, attrs) fields = getattr(_class, "fields", {}) new_attrs = {} for n in dir(_class): v = getattr(_class, n) if isinstance(v, Field): fields[n] = v elif n in attrs: new_attrs[n] = attrs[n] new_attrs["fields"] = fields new_attrs["_class"] = _class if classcell is not None: new_attrs["__classcell__"] = classcell return super().__new__(mcs, class_name, bases, new_attrs)
class Item(MutableMapping, object_ref, metaclass=ItemMeta): """ Base class for scraped items. In Scrapy, an object is considered an ``item`` if it is an instance of either :class:`Item` or :class:`dict`, or any subclass. For example, when the output of a spider callback is evaluated, only instances of :class:`Item` or :class:`dict` are passed to :ref:`item pipelines <topics-item-pipeline>`. If you need instances of a custom class to be considered items by Scrapy, you must inherit from either :class:`Item` or :class:`dict`. Items must declare :class:`Field` attributes, which are processed and stored in the ``fields`` attribute. This restricts the set of allowed field names and prevents typos, raising ``KeyError`` when referring to undefined fields. Additionally, fields can be used to define metadata and control the way data is processed internally. Please refer to the :ref:`documentation about fields <topics-items-fields>` for additional information. Unlike instances of :class:`dict`, instances of :class:`Item` may be :ref:`tracked <topics-leaks-trackrefs>` to debug memory leaks. """ fields: Dict[str, Field] def __init__(self, *args, **kwargs): self._values = {} if args or kwargs: # avoid creating dict for most common case for k, v in dict(*args, **kwargs).items(): self[k] = v def __getitem__(self, key): return self._values[key] def __setitem__(self, key, value): if key in self.fields: self._values[key] = value else: raise KeyError(f"{self.__class__.__name__} does not support field: {key}") def __delitem__(self, key): del self._values[key] def __getattr__(self, name): if name in self.fields: raise AttributeError(f"Use item[{name!r}] to get field value") raise AttributeError(name) def __setattr__(self, name, value): if not name.startswith("_"): raise AttributeError(f"Use item[{name!r}] = {value!r} to set field value") super().__setattr__(name, value) def __len__(self): return len(self._values) def __iter__(self): return iter(self._values) __hash__ = object_ref.__hash__ def keys(self): return self._values.keys() def __repr__(self): return pformat(dict(self)) def copy(self): return self.__class__(self) def deepcopy(self): """Return a :func:`~copy.deepcopy` of this item.""" return deepcopy(self)