Mur*_*aya 5 python django scrapy scrapy-spider scrapy-pipeline
我只需要了解如何检测scrapy是否已保存以及蜘蛛中的项目？我正在从网站上获取项目,之后我正在获取该项目的评论.所以首先我必须保存项目,之后我会保存评论.但是当我在编写代码之后编写代码时,它会给我这个错误.
save() prohibited to prevent data loss due to unsaved related object ''.
这是我的代码
def parseProductComments(self, response):
name = response.css('h1.product-name::text').extract_first()
price = response.css('span[id=offering-price] > span::text').extract_first()
node = response.xpath("//script[contains(text(),'var utagData = ')]/text()")
data = node.re('= (\{.+\})')[0] #data = xpath.re(" = (\{.+\})")
data = json.loads(data)
barcode = data['product_barcode']
objectImages = []
for imageThumDiv in response.css('div[id=productThumbnailsCarousel]'):
images = imageThumDiv.xpath('img/@data-src').extract()
for image in images:
imageQuality = image.replace('/80/', '/500/')
objectImages.append(imageQuality)
company = Company.objects.get(pk=3)
comments = []
item = ProductItem(name=name, price=price, barcode=barcode, file_urls=objectImages, product_url=response.url,product_company=company, comments = comments)
yield item
print item["pk"]
for commentUl in response.css('ul.chevron-list-container'):
url = commentUl.css('span.link-more-results::attr(href)').extract_first()
if url is not None:
for commentLi in commentUl.css('li.review-item'):
comment = commentLi.css('p::text').extract_first()
commentItem = CommentItem(comment=comment, product=item.instance)
yield commentItem
else:
yield scrapy.Request(response.urljoin(url), callback=self.parseCommentsPages, meta={'item': item.instance})
这是我的管道.
def comment_to_model(item):
model_class = getattr(item, 'Comment')
if not model_class:
raise TypeError("Item is not a `DjangoItem` or is misconfigured")
def get_comment_or_create(model):
model_class = type(model)
created = False
# Normally, we would use `get_or_create`. However, `get_or_create` would
# match all properties of an object (i.e. create a new object
# anytime it changed) rather than update an existing object.
#
# Instead, we do the two steps separately
try:
# We have no unique identifier at the moment; use the name for now.
obj = model_class.objects.get(product=model.product, comment=model.comment)
except model_class.DoesNotExist:
created = True
obj = model # DjangoItem created a model for us.
obj.save()
return (obj, created)
def get_or_create(model):
model_class = type(model)
created = False
# Normally, we would use `get_or_create`. However, `get_or_create` would
# match all properties of an object (i.e. create a new object
# anytime it changed) rather than update an existing object.
#
# Instead, we do the two steps separately
try:
# We have no unique identifier at the moment; use the name for now.
obj = model_class.objects.get(product_company=model.product_company, barcode=model.barcode)
except model_class.DoesNotExist:
created = True
obj = model # DjangoItem created a model for us.
obj.save()
return (obj, created)
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
class ProductItemPipeline(object):
def process_item(self, item, spider):
if isinstance(item, ProductItem):
item['cover_photo'] = item['files'][0]['path']
item_model = item.instance
model, created = get_or_create(item_model)
#update_model(model, item_model)
if created:
for image in item['files']:
imageItem = ProductImageItem(image=image['path'], product=item.instance)
imageItem.save()
# for comment in item['comments']:
# commentItem = CommentItem(comment=comment, product= item.instance)
# commentItem.save()
return item
if isinstance(item, CommentItem):
comment_to_model = item.instance
model, created = get_comment_or_create(comment_to_model)
if created:
print model
else:
print created
return item
您的代码的很大一部分似乎是在处理 get_or_create 的明显弱点
\n\n# Normally, we would use `get_or_create`. However, `get_or_create` would\n# match all properties of an object (i.e. create a new object\n# anytime it changed) rather than update an existing object.\n幸运的是，这个明显的缺点很容易克服。感谢get_or_create的默认参数
\n\n\n\n\n传递给 get_or_create() \xe2\x80\x94 的任何关键字参数（称为 defaults \xe2\x80\x94 的可选参数除外）都将在 get() 调用中使用。如果找到一个对象，get_or_create() 返回该对象的元组和 False。如果找到多个对象，则 get_or_create 引发 MultipleObjectsReturned。如果未找到对象，get_or_create()\n 将实例化并保存一个新对象，返回新对象和 True 的元组。
\n
仍然不相信 get_or_create 是这项工作的合适人选？我也不是。还有更好的东西。更新或创建！
\n\n\n\n\n一种使用给定 kwargs 更新对象的便捷方法，\n 如果需要则创建一个新对象。默认值是用于更新对象的（字段，值）对的字典。
\n
但我不会详细讨论 update_or_create 的用户，因为代码中尝试更新模型的行已被注释掉，并且您没有明确说明要更新的内容。
\n\n使用标准 API 方法，包含管道的模块只需简化为 ProductItemPipeline 类。并且可以修改
\n\nclass ProductItemPipeline(object):\n def process_item(self, item, spider):\n if isinstance(item, ProductItem):\n item[\'cover_photo\'] = item[\'files\'][0][\'path\']\n\n model, created = ProductItem.get_or_create(product_company=item[\'product_company\'], barcode=item[\'bar_code\'], \n defaults={\'Other_field1\': value1, \'Other_field2\': value2})\n\n if created:\n for image in item[\'files\']:\n imageItem = ProductImageItem(image=image[\'path\'], product=item.instance)\n imageItem.save()\n return item\n\n if isinstance(item, CommentItem):\n\n model, created = CommentItem.get_or_create(field1=value1, defaults={ other fields go in here\'})\n\n if created:\n print model\n else:\n print created\n return item\n我确实相信这是错误存在的地方。
\n\n obj = model_class.objects.get(product=model.product, comment=model.comment)\n现在我们不再使用它，因此错误应该消失。如果您仍然遇到问题，请粘贴完整的回溯。
\n