从Scrapy项目保存Django模型
我有一个Scrapy项目,想把输出的内容保存为Django模型定义中的一个对象(我没有使用DjangoItem)。
我按照这里的说明导入了Django的设置:这里。
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)
在我的Scrapy项目中,有一个管道类负责处理所有的项目,并在最后把它们保存到数据库里:
from 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
但是发生了一些奇怪的事情,对于第一个项目我遇到了一个错误(见下文)。而对于后面的项目,一切都正常。假设我有7个项目要保存,那么第一个项目出错了,其他6个项目都能保存。
Traceback (most recent call last):
File "/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 "/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 "/users/ale/djcode/books/lib/scraper/scraper/djangopipeline.py", line 34, in process_item
selected_category = Category.objects.get(name='Horror')
File "/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 "/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/query.py", line 333, in get
clone = self.filter(*args, **kwargs)
File "/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 "/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 "/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 "/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 "/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 "/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 "/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 "/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 "/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 "/users/ale/virtualenvs/books/lib/python2.6/site-packages/django/db/models/loading.py", line 167, in get_models
self._populate()
File "/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 "/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 "/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
如果我这样做,所有7个项目都能保存:
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
我不知道我哪里做错了。有人能帮我吗?
谢谢!
2 个回答
0
我记得如果缺少 __init__.py
文件,会导致一些奇怪的问题。你在所有模块里都有这个文件吗?
4
我也遇到过同样的问题,后来找到了解决办法。至少对我来说是有效的。
在我的情况下,问题出在Django项目的settings.py文件里——我把我应用的名字加到了INSTALLED_APPS
这个列表里,但我加的是它的简短名字,而不是完整的名字。
举个例子,你可能在INSTALLED_APPS
里加了my_books
这个名字,但其实应该加的是my_django_project.apps.my_books
这个完整的名字。