, , , - , .
, db.
spiders.py, u " p, px c1, c2 response.body", "" , .
u , :
class ItemPersistencePipeline(object):
def process_item(self, item, spider):
try:
item_model = item_to_model(item)
except TypeError:
return item
model, created = get_or_create(item_model)
try:
update_model(model, item_model)
except Exception,e:
return e
return item
, :
def item_to_model(item):
model_class = getattr(item, 'django_model')
if not model_class:
raise TypeError("Item is not a `DjangoItem` or is misconfigured")
return item.instance
def get_or_create(model):
model_class = type(model)
created = False
try:
obj = model_class.objects.get(primary=model.primary)
except model_class.DoesNotExist:
created = True
obj = model
return (obj, created)
from django.forms.models import model_to_dict
def update_model(destination, source, commit=True):
pk = destination.pk
source_dict = model_to_dict(source)
for (key, value) in source_dict.items():
setattr(destination, key, value)
setattr(destination, 'pk', pk)
if commit:
destination.save()
return destination
from: DjangoItem Scrapy
"primary" django , scraped
models.py
class Parent(models.Model):
field1 = CharField()
primary = models.CharField(max_length=80)
class ParentX(models.Model):
field2 = CharField()
parent = models.OneToOneField(Parent, related_name = 'extra_properties')
primary = models.CharField(max_length=80)
class Child(models.Model):
field3 = CharField()
parent = models.ForeignKey(Parent, related_name='childs')
primary = models.CharField(max_length=80)