mirror of
https://github.com/scrapy/scrapy.git
synced 2025-02-24 17:44:33 +00:00
105 lines
3.6 KiB
Python
105 lines
3.6 KiB
Python
import warnings
|
|
import unittest
|
|
|
|
from zope.interface.verify import DoesNotImplement
|
|
|
|
from scrapy.crawler import Crawler, CrawlerRunner
|
|
from scrapy.settings import Settings, default_settings
|
|
from scrapy.spiderloader import SpiderLoader
|
|
from scrapy.utils.spider import DefaultSpider
|
|
from scrapy.utils.misc import load_object
|
|
|
|
|
|
class CrawlerTestCase(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
self.crawler = Crawler(DefaultSpider, Settings())
|
|
|
|
def test_deprecated_attribute_spiders(self):
|
|
with warnings.catch_warnings(record=True) as w:
|
|
spiders = self.crawler.spiders
|
|
self.assertEqual(len(w), 1)
|
|
self.assertIn("Crawler.spiders", str(w[0].message))
|
|
sl_cls = load_object(self.crawler.settings['SPIDER_LOADER_CLASS'])
|
|
self.assertIsInstance(spiders, sl_cls)
|
|
|
|
self.crawler.spiders
|
|
self.assertEqual(len(w), 1, "Warn deprecated access only once")
|
|
|
|
def test_populate_spidercls_settings(self):
|
|
spider_settings = {'TEST1': 'spider', 'TEST2': 'spider'}
|
|
project_settings = {'TEST1': 'project', 'TEST3': 'project'}
|
|
|
|
class CustomSettingsSpider(DefaultSpider):
|
|
custom_settings = spider_settings
|
|
|
|
settings = Settings()
|
|
settings.setdict(project_settings, priority='project')
|
|
crawler = Crawler(CustomSettingsSpider, settings)
|
|
|
|
self.assertEqual(crawler.settings.get('TEST1'), 'spider')
|
|
self.assertEqual(crawler.settings.get('TEST2'), 'spider')
|
|
self.assertEqual(crawler.settings.get('TEST3'), 'project')
|
|
|
|
self.assertFalse(settings.frozen)
|
|
self.assertTrue(crawler.settings.frozen)
|
|
|
|
def test_crawler_accepts_dict(self):
|
|
crawler = Crawler(DefaultSpider, {'foo': 'bar'})
|
|
self.assertEqual(crawler.settings['foo'], 'bar')
|
|
self.assertEqual(
|
|
crawler.settings['RETRY_ENABLED'],
|
|
default_settings.RETRY_ENABLED
|
|
)
|
|
self.assertIsInstance(crawler.settings, Settings)
|
|
|
|
|
|
|
|
class SpiderLoaderWithWrongInterface(object):
|
|
|
|
def unneeded_method(self):
|
|
pass
|
|
|
|
|
|
class CustomSpiderLoader(SpiderLoader):
|
|
pass
|
|
|
|
|
|
class CrawlerRunnerTestCase(unittest.TestCase):
|
|
|
|
def test_spider_manager_verify_interface(self):
|
|
settings = Settings({
|
|
'SPIDER_LOADER_CLASS': 'tests.test_crawler.SpiderLoaderWithWrongInterface'
|
|
})
|
|
with self.assertRaises(DoesNotImplement):
|
|
CrawlerRunner(settings)
|
|
|
|
def test_crawler_runner_accepts_dict(self):
|
|
runner = CrawlerRunner({'foo': 'bar'})
|
|
self.assertEqual(runner.settings['foo'], 'bar')
|
|
self.assertEqual(
|
|
runner.settings['RETRY_ENABLED'],
|
|
default_settings.RETRY_ENABLED
|
|
)
|
|
self.assertIsInstance(runner.settings, Settings)
|
|
|
|
def test_deprecated_attribute_spiders(self):
|
|
with warnings.catch_warnings(record=True) as w:
|
|
runner = CrawlerRunner(Settings())
|
|
spiders = runner.spiders
|
|
self.assertEqual(len(w), 1)
|
|
self.assertIn("CrawlerRunner.spiders", str(w[0].message))
|
|
self.assertIn("CrawlerRunner.spider_loader", str(w[0].message))
|
|
sl_cls = load_object(runner.settings['SPIDER_LOADER_CLASS'])
|
|
self.assertIsInstance(spiders, sl_cls)
|
|
|
|
def test_spidermanager_deprecation(self):
|
|
with warnings.catch_warnings(record=True) as w:
|
|
runner = CrawlerRunner({
|
|
'SPIDER_MANAGER_CLASS': 'tests.test_crawler.CustomSpiderLoader'
|
|
})
|
|
self.assertIsInstance(runner.spider_loader, CustomSpiderLoader)
|
|
self.assertEqual(len(w), 1)
|
|
self.assertIn('Please use SPIDER_LOADER_CLASS', str(w[0].message))
|
|
|