本文整理汇总了Python中frontera.settings.Settings.STRATEGY方法的典型用法代码示例。如果您正苦于以下问题:Python Settings.STRATEGY方法的具体用法?Python Settings.STRATEGY怎么用?Python Settings.STRATEGY使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类frontera.settings.Settings
的用法示例。
在下文中一共展示了Settings.STRATEGY方法的4个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_blocking_middleware
# 需要导入模块: from frontera.settings import Settings [as 别名]
# 或者: from frontera.settings.Settings import STRATEGY [as 别名]
def test_blocking_middleware(self):
settings = Settings()
settings.BACKEND = 'tests.mocks.components.FakeBackend'
settings.MIDDLEWARES = ['frontera.contrib.middlewares.domain.DomainMiddleware',
'frontera.contrib.middlewares.fingerprint.UrlFingerprintMiddleware',
'tests.mocks.components.FakeMiddleware',
'tests.mocks.components.FakeMiddlewareModifySeeds',
'tests.mocks.components.FakeMiddlewareBlocking',
'tests.mocks.components.FakeMiddlewareModifyResponse',
'tests.mocks.components.FakeMiddlewareModifyLinks']
settings.CANONICAL_SOLVER = 'tests.mocks.components.FakeCanonicalSolver'
settings.STRATEGY = 'tests.mocks.components.CrawlingStrategy'
fm = LocalFrontierManager.from_settings(settings)
SEEDS_FILE.seek(0)
fm.add_seeds(SEEDS_FILE)
response = Response(r1.url, request=r1)
fm.page_crawled(response)
fm.links_extracted(r1, links=[r2])
fm.request_error(r3, 'error')
#the seeds, responses, links and errors have not reached the backend.
assert [len(list) for list in fm.backend.lists] == [0]*4
#the 3 seeds reach the first three middlewares.
assert [len(fm.middlewares[i].requests) for i in range(2, 5)] == [3]*3
#the error, response and link reached the first three middlewares.
assert [[len(list) for list in fm.middlewares[i].lists[1:]] for i in range(2, 5)] == [[1]*3]*3
#the values do not reach the bottom 2 middlewares and the canonical solver.
assert [[len(list) for list in fm.middlewares[i].lists] for i in range(5, 7)] == [[0]*4]*2
assert [len(list) for list in fm.canonicalsolver.lists] == [0]*4
示例2: sw_setup_add_seeds
# 需要导入模块: from frontera.settings import Settings [as 别名]
# 或者: from frontera.settings.Settings import STRATEGY [as 别名]
def sw_setup_add_seeds(self):
settings = Settings()
settings.BACKEND = 'frontera.contrib.backends.sqlalchemy.Distributed'
settings.MESSAGE_BUS = 'tests.mocks.message_bus.FakeMessageBus'
settings.SPIDER_LOG_CONSUMER_BATCH_SIZE = 100
settings.STRATEGY = 'tests.mocks.components.CrawlingStrategy'
return StrategyWorker(settings, True)
示例3: sw_setup_filtered_links
# 需要导入模块: from frontera.settings import Settings [as 别名]
# 或者: from frontera.settings.Settings import STRATEGY [as 别名]
def sw_setup_filtered_links(self):
settings = Settings()
settings.BACKEND = 'frontera.contrib.backends.sqlalchemy.Distributed'
settings.MESSAGE_BUS = 'tests.mocks.message_bus.FakeMessageBus'
settings.STRATEGY = 'tests.test_worker_strategy.FilteredLinksCrawlingStrategy'
settings.SPIDER_LOG_CONSUMER_BATCH_SIZE = 100
return StrategyWorker(settings, False)
示例4: strategy
# 需要导入模块: from frontera.settings import Settings [as 别名]
# 或者: from frontera.settings.Settings import STRATEGY [as 别名]
def strategy(self):
settings = Settings()
settings.BACKEND = 'frontera.contrib.backends.sqlalchemy.Distributed'
settings.STRATEGY = 'tests.test_strategy.DummyCrawlingStrategy'
manager = WorkerFrontierManager.from_settings(settings, db_worker=False, strategy_worker=True)
stream = MessageBusStream()
states = MemoryStates(10)
states_ctx = StatesContext(states)
return manager.strategy