Test by module/file. More organization.

fmartingr · Mar 15, 2013 · 388909c · 388909c
1 parent 3fbed9f
commit 388909c
Show file tree

Hide file tree

Showing 4 changed files with 94 additions and 61 deletions.
diff --git a/test/requirements.py b/test/requirements.py
@@ -0,0 +1,22 @@
+from datCrawl.crawlers import Crawler
+
+
+class AwesomeGoogleCrawler(Crawler):
+    urls = [
+        ('es', 'http\:\/\/(www\.)?google\.es', ),
+        ('de', 'http\:\/\/(www\.)?google\.de', )
+    ]
+
+
+class AwesomeEmptyCrawler(Crawler):
+    pass
+
+
+class AwesomeWikipediaTitleCrawler(Crawler):
+    urls = [
+        ('title', 'http\:\/\/en.wikipedia.org\/wiki\/(.*)', )
+    ]
+
+    def action_title(self, url):
+        # LOOK, IM CRAWLING THE INTERNETS!
+        return {'title': 'Python'}
diff --git a/test/test_base.py b/test/test_base.py
@@ -1,29 +1,9 @@
 import unittest
 from datCrawl import *
+from requirements import *
 
 
-class AwesomeGoogleCrawler(Crawler):
-    urls = [
-        ('es', 'http\:\/\/(www\.)?google\.es', ),
-        ('de', 'http\:\/\/(www\.)?google\.de', )
-    ]
-
-
-class AwesomeEmptyCrawler(Crawler):
-    pass
-
-
-class AwesomeWikipediaTitleCrawler(Crawler):
-    urls = [
-        ('title', 'http\:\/\/en.wikipedia.org\/wiki\/(.*)', )
-    ]
-
-    def action_title(self, url):
-        # LOOK, IM CRAWLING THE INTERNETS!
-        return {'title': 'Python'}
-
-
-class datCrawlTests(unittest.TestCase):
+class datCrawlBaseTests(unittest.TestCase):
 
     def test_instance_check(self):
         core = datCrawl()
@@ -35,45 +15,6 @@ def test_register_urls(self):
         core.register_url(data[0], data[1], data[2])
         self.assertEquals(core.urls[0], data)
 
-    def test_cant_register_crawler_twice(self):
-        core = datCrawl()
-        core.register_crawler(AwesomeGoogleCrawler)
-        self.assertRaises(CrawlerAlreadyRegistered, lambda: core.register_crawler(AwesomeGoogleCrawler))
-
-    def test_register_crawler_with_urls(self):
-        core = datCrawl()
-        core.register_crawler(AwesomeGoogleCrawler)
-        self.assertEqual(core.crawlers['AwesomeGoogleCrawler'], AwesomeGoogleCrawler)
-        # Some other checks if the tuple are well parsed, in order: action, url, crawler name
-        self.assertEqual(core.urls[0][0], AwesomeGoogleCrawler().urls[0][1])
-        self.assertEqual(core.urls[0][1], AwesomeGoogleCrawler().urls[0][0])
-        self.assertEqual(core.urls[0][2], AwesomeGoogleCrawler().__class__.__name__)
-        self.assertEqual(core.urls[1][0], AwesomeGoogleCrawler().urls[1][1])
-        self.assertEqual(core.urls[1][1], AwesomeGoogleCrawler().urls[1][0])
-        self.assertEqual(core.urls[1][2], AwesomeGoogleCrawler().__class__.__name__)
-
-    def test_no_crawler_registered_for_url(self):
-        core = datCrawl()
-        core.register_crawler(AwesomeGoogleCrawler)
-        self.assertEqual(core.crawlers['AwesomeGoogleCrawler'], AwesomeGoogleCrawler)
-        self.assertRaises(CrawlerForThisURLNotFound, lambda: core.run('http://www.github.com'))
-
-    def test_register_crawler_without_urls(self):
-        core = datCrawl()
-        self.assertRaises(CrawlerDontHaveUrlsToWatch, lambda: core.register_crawler(AwesomeEmptyCrawler))
-
-    def test_register_incorrect_crawler(self):
-        core = datCrawl()
-        self.assertRaises(CrawlerIsNotInstanceOfBase, lambda: core.register_crawler(object))
-
-    def test_running_without_registered_crawlers(self):
-        core = datCrawl()
-        self.assertRaises(NoCrawlerRegistered, lambda: core.run('www.google.es'))
-
-    def test_running_without_url_parameters(self):
-        core = datCrawl()
-        self.assertRaises(TypeError, lambda: core.run())
-
     def test_running_full_crawler(self):
         core = datCrawl()
         core.register_crawler(AwesomeWikipediaTitleCrawler)

diff --git a/test/test_crawlers.py b/test/test_crawlers.py
@@ -0,0 +1,47 @@
+import unittest
+from datCrawl import *
+from requirements import *
+
+
+class datCrawlCrawlerTests(unittest.TestCase):
+    def test_register_crawler_with_urls(self):
+        core = datCrawl()
+        core.register_crawler(AwesomeGoogleCrawler)
+        self.assertEqual(core.crawlers['AwesomeGoogleCrawler'], AwesomeGoogleCrawler)
+        # Some other checks if the tuple are well parsed, in order: action, url, crawler name
+        self.assertEqual(core.urls[0][0], AwesomeGoogleCrawler().urls[0][1])
+        self.assertEqual(core.urls[0][1], AwesomeGoogleCrawler().urls[0][0])
+        self.assertEqual(core.urls[0][2], AwesomeGoogleCrawler().__class__.__name__)
+        self.assertEqual(core.urls[1][0], AwesomeGoogleCrawler().urls[1][1])
+        self.assertEqual(core.urls[1][1], AwesomeGoogleCrawler().urls[1][0])
+        self.assertEqual(core.urls[1][2], AwesomeGoogleCrawler().__class__.__name__)
+
+    def test_register_incorrect_crawler(self):
+        core = datCrawl()
+        self.assertRaises(CrawlerIsNotInstanceOfBase, lambda: core.register_crawler(object))
+
+    def test_cant_register_crawler_twice(self):
+        core = datCrawl()
+        core.register_crawler(AwesomeGoogleCrawler)
+        self.assertRaises(CrawlerAlreadyRegistered, lambda: core.register_crawler(AwesomeGoogleCrawler))
+
+    def test_no_crawler_registered_for_url(self):
+        core = datCrawl()
+        core.register_crawler(AwesomeGoogleCrawler)
+        self.assertEqual(core.crawlers['AwesomeGoogleCrawler'], AwesomeGoogleCrawler)
+        self.assertRaises(CrawlerForThisURLNotFound, lambda: core.run('http://www.github.com'))
+
+    def test_register_crawler_without_urls(self):
+        core = datCrawl()
+        self.assertRaises(CrawlerDontHaveUrlsToWatch, lambda: core.register_crawler(AwesomeEmptyCrawler))
+
+    def test_running_without_registered_crawlers(self):
+        core = datCrawl()
+        self.assertRaises(NoCrawlerRegistered, lambda: core.run('www.google.es'))
+
+    def test_running_without_url_parameters(self):
+        core = datCrawl()
+        self.assertRaises(TypeError, lambda: core.run())
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/test/test_downloaders.py b/test/test_downloaders.py
@@ -0,0 +1,23 @@
+import unittest
+from datCrawl import datCrawl, downloaders
+from datCrawl.exceptions import *
+from requirements import *
+
+
+class datCrawlDownloaderTests(unittest.TestCase):
+    def test_register_downloader(self):
+        core = datCrawl()
+        core.register_downloader(downloaders.DefaultDownloader)
+        self.assertEqual(core.downloaders['DefaultDownloader'], downloaders.DefaultDownloader)
+
+    def test_register_incorrect_downloader(self):
+        core = datCrawl()
+        self.assertRaises(DownloaderIsNotInstanceOfBase, lambda: core.register_downloader(object))
+
+    def test_cant_register_downloader_twice(self):
+        core = datCrawl()
+        core.register_downloader(downloaders.DefaultDownloader)
+        self.assertRaises(DownloaderAlreadyRegistered, lambda: core.register_downloader(downloaders.DefaultDownloader))
+
+if __name__ == '__main__':
+    unittest.main()