저는 Scrapy 프로젝트를 가지고 있고 Django 모델 정의 (DjangoItem을 사용하지 않고 있습니다)에서 출력 항목을 오브젝트로 저장하려고합니다.Scrapy 프로젝트에서 Django 모델을 저장합니다.
here으로 장고 설정을 가져오고 있습니다.
이from my_django_project.apps.my_books.models import Book, Category, Image
class DjangoPipeline(object):
def process_item(self, item, spider):
category = Category.objects.get(name='Horror')
book = Book(name='something', category=category)
book.save()
image = Image(name='something', book=book)
image.save()
return item
하지만, 뭔가 이상한 일이 내가 얻을 첫 번째 항목에 대한 내 Scrapy 프로젝트에서
def setup_django_env(path):
import imp, os
from django.core.management import setup_environ
f, filename, desc = imp.find_module('settings', [path])
project = imp.load_module('settings', f, filename, desc)
setup_environ(project)
setup_django_env(PATH_TO_DJANGO_PROJECT)
나는 끝에 모든 항목을 처리하고 DB에 저장 파이프 라인 클래스가 오류 (아래 참조). 나머지 항목은 모두 정상입니다. 저장하려는 항목이 7 개라고 가정 해 봅시다. 처음에는 오류가 발생하고 다른 하나는 저장됩니다. 나는 이런 식으로 뭔가를 할 경우
Traceback (most recent call last):
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/scrapy/middleware.py", line 54, in _process_chain
return process_chain(self.methods[methodname], obj, *args)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/scrapy/utils/defer.py", line 65, in process_chain
d.callback(input)
File "/System/Library/Frameworks/Python.framework/Versions/2.6/Extras/lib/python/twisted/internet/defer.py", line 243, in callback
self._startRunCallbacks(result)
File "/System/Library/Frameworks/Python.framework/Versions/2.6/Extras/lib/python/twisted/internet/defer.py", line 312, in _startRunCallbacks
self._runCallbacks()
--- <exception caught here> ---
File "/System/Library/Frameworks/Python.framework/Versions/2.6/Extras/lib/python/twisted/internet/defer.py", line 328, in _runCallbacks
self.result = callback(self.result, *args, **kw)
File "https://stackoverflow.com/users/ale/djcode/books/lib/scraper/scraper/djangopipeline.py", line 34, in process_item
selected_category = Category.objects.get(name='Horror')
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/manager.py", line 132, in get
return self.get_query_set().get(*args, **kwargs)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/query.py", line 333, in get
clone = self.filter(*args, **kwargs)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/query.py", line 550, in filter
return self._filter_or_exclude(False, *args, **kwargs)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/query.py", line 568, in _filter_or_exclude
clone.query.add_q(Q(*args, **kwargs))
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/sql/query.py", line 1131, in add_q
can_reuse=used_aliases)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/sql/query.py", line 1026, in add_filter
negate=negate, process_extras=process_extras)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/sql/query.py", line 1182, in setup_joins
field, model, direct, m2m = opts.get_field_by_name(name)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/options.py", line 291, in get_field_by_name
cache = self.init_name_map()
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/options.py", line 321, in init_name_map
for f, model in self.get_all_related_m2m_objects_with_model():
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/options.py", line 396, in get_all_related_m2m_objects_with_model
cache = self._fill_related_many_to_many_cache()
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/options.py", line 410, in _fill_related_many_to_many_cache
for klass in get_models():
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/loading.py", line 167, in get_models
self._populate()
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/loading.py", line 61, in _populate
self.load_app(app_name, True)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/loading.py", line 76, in load_app
app_module = import_module(app_name)
File "https://stackoverflow.com/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/utils/importlib.py", line 35, in import_module
__import__(name)
exceptions.ImportError: No module named my_books
은 모두 7 개 항목이 저장 얻을 :
from my_django_project.apps.my_app.models import Book, Category, Image
class DjangoPipeline(object):
def process_item(self, item, spider):
try:
category = Category.objects.get(name='something')
except:
category = Category.objects.get(name='something')
book = Book(name='something', category=category)
try:
book.save()
except:
book.save()
image = Image(name='something', book=book)
try:
image.save()
except:
image.save()
return item
나는 내가 뭘 잘못 알고하지 않습니다. 누군가 날 도와 줄 수 있니?
감사합니다.
my_django_project를 참조 할 때 실제로 해당 참조를 참조하거나 mysite.apps import *와 같은 프로젝트 이름으로 바꾸십시오. – emschorsch
나는 그 프로젝트를 내 프로젝트의 이름으로 바꾸고있다 :) – Alex
안녕하세요, 알렉스, 당신이 한 일을하고 문제를 일으키려고합니다. 당신이 내 생각에 당신이 이걸 알아 냈어 그래서 당신이 내 [질문] (http://stackoverflow.com/questions/14686223/scrapy-project-cant-find-django-core-management) 조언을 제공하십시오. 감사! – GChorn