From 320edd22c468ce36f093cbb86cb8fcffdf2d54e0 Mon Sep 17 00:00:00 2001
From: starek21 <starek21@vt.edu>
Date: Wed, 1 May 2024 15:18:56 -0400
Subject: [PATCH] added scraper unit test
---
test-scraper.py | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
create mode 100644 test-scraper.py
diff --git a/test-scraper.py b/test-scraper.py
new file mode 100644
index 0000000..2686ef0
--- /dev/null
+++ b/test-scraper.py
@@ -0,0 +1,27 @@
+import unittest
+from scraper import scrape_webpage
+
+class TestWebScraping(unittest.TestCase):
+
+ def test_scrape_valid_page(self):
+ """
+ Test scraping a valid webpage to ensure it retrieves text.
+ """
+ # This link should be replaced with a known, stable webpage for testing
+ test_link = "http://example.com"
+ result = scrape_webpage(test_link)
+ self.assertIn("link", result)
+ self.assertIn("text", result)
+ self.assertNotEqual(result["text"], "", "The scraped text should not be empty.")
+
+ def test_scrape_invalid_page(self):
+ """
+ Test scraping an invalid webpage to check error handling.
+ """
+ # This should be a link that will likely return a 404 or other client/server error
+ test_link = "http://example.com/nonexistentpage"
+ result = scrape_webpage(test_link)
+ self.assertTrue("Error identified" in result)
+
+if __name__ == '__main__':
+ unittest.main()
\ No newline at end of file
--
GitLab