Check that spidercls arguments in scrapy.crawler classes are not spider objects

scrapy/crawler.py

@@ -7,6 +7,7 @@ import sys
 from twisted.internet import reactor, defer
 from zope.interface.verify import verifyClass, DoesNotImplement
 
+from scrapy import Spider
 from scrapy.core.engine import ExecutionEngine
 from scrapy.resolver import CachingThreadedResolver
 from scrapy.interfaces import ISpiderLoader
@@ -27,6 +28,10 @@ logger = logging.getLogger(__name__)
 class Crawler(object):
 
     def __init__(self, spidercls, settings=None):
+        if isinstance(spidercls, Spider):
+            raise ValueError(
+                'The spidercls argument must be a class, not an object')
+
         if isinstance(settings, dict) or settings is None:
             settings = Settings(settings)
 
@@ -168,6 +173,10 @@ class CrawlerRunner(object):
 
         :param dict kwargs: keyword arguments to initialize the spider
         """
+        if isinstance(crawler_or_spidercls, Spider):
+            raise ValueError(
+                'The crawler_or_spidercls argument cannot be a spider object, '
+                'it must be a spider class (or a Crawler object)')
         crawler = self.create_crawler(crawler_or_spidercls)
         return self._crawl(crawler, *args, **kwargs)
 
@@ -195,6 +204,10 @@ class CrawlerRunner(object):
           a spider with this name in a Scrapy project (using spider loader),
           then creates a Crawler instance for it.
         """
+        if isinstance(crawler_or_spidercls, Spider):
+            raise ValueError(
+                'The crawler_or_spidercls argument cannot be a spider object, '
+                'it must be a spider class (or a Crawler object)')
         if isinstance(crawler_or_spidercls, Crawler):
             return crawler_or_spidercls
         return self._create_crawler(crawler_or_spidercls)

tests/test_crawler.py

@@ -4,6 +4,7 @@ import warnings
 
 from twisted.internet import defer
 from twisted.trial import unittest
+from pytest import raises
 
 import scrapy
 from scrapy.crawler import Crawler, CrawlerRunner, CrawlerProcess
@@ -66,6 +67,10 @@ class CrawlerTestCase(BaseCrawlerTest):
         crawler = Crawler(DefaultSpider)
         self.assertOptionIsDefault(crawler.settings, 'RETRY_ENABLED')
 
+    def test_crawler_rejects_spider_objects(self):
+        with raises(ValueError):
+            Crawler(DefaultSpider())
+
 
 class SpiderSettingsTestCase(unittest.TestCase):
     def test_spider_custom_settings(self):
@@ -177,6 +182,14 @@ class CrawlerRunnerTestCase(BaseCrawlerTest):
             self.assertEqual(len(w), 1)
             self.assertIn('Please use SPIDER_LOADER_CLASS', str(w[0].message))
 
+    def test_crawl_rejects_spider_objects(self):
+        with raises(ValueError):
+            CrawlerRunner().crawl(DefaultSpider())
+
+    def test_create_crawler_rejects_spider_objects(self):
+        with raises(ValueError):
+            CrawlerRunner().create_crawler(DefaultSpider())
+
 
 class CrawlerProcessTest(BaseCrawlerTest):
     def test_crawler_process_accepts_dict(self):

tests/test_downloadermiddleware_httpproxy.py

@@ -25,7 +25,7 @@ class TestHttpProxyMiddleware(TestCase):
 
     def test_not_enabled(self):
         settings = Settings({'HTTPPROXY_ENABLED': False})
-        crawler = Crawler(spider, settings)
+        crawler = Crawler(Spider, settings)
         self.assertRaises(NotConfigured, partial(HttpProxyMiddleware.from_crawler, crawler))
 
     def test_no_environment_proxies(self):