def __init__(self, *args, **kwargs):
super(ItemStep, self).__init__(*args, **kwargs)
if not self.item_class:
raise exceptions.ArgumentError(
u'You must define an item_class attribute')
if not issubclass(self.item_class, scrapy_item.Item):
raise exceptions.ArgumentError(
u'The item_class must be a subclass of scrapy.Item')
def __init__(self, spider, *args, **kwargs):
self.spider = spider
self.parent_step = kwargs.pop('parent_step', None)
for key, value in kwargs.iteritems():
if not hasattr(self, key):
raise exceptions.ArgumentError(
u'Attribute {} not allowed'.format(key))
else:
setattr(self, key, value)
def __init__(self, *args, **kwargs):
if not self.name:
self.name = utils.slugify_name(self.__class__.__name__)
if not issubclass(self.initial_step, steps.InitStep):
raise exceptions.ArgumentError(
(u'The initial_step attribute must'
' be a subclass of scrapy_venom.steps.InitStep'))
super(SpiderFlow, self).__init__(*args, **kwargs)
def __init__(self, *args, **kwargs):
super(SearchStep, self).__init__(*args, **kwargs)
if not self.search_url:
raise exceptions.ArgumentError(
u'You must define an search_url or get_search_url()')
def __init__(self, *args, **kwargs):
super(InitStep, self).__init__(*args, **kwargs)
if not self.initial_url:
raise exceptions.ArgumentError(
u'You must define an initial_url or get_request_url()')
def __init__(self, *args, **kwargs):
super(HttpMixin, self).__init__(*args, **kwargs)
if self.http_method not in self.ALLOWED_METHODS:
raise exceptions.ArgumentError(u'This http_method is not allowed')