💾 Archived View for gmn.clttr.info › sources › geminispace.git › tree › tests › gus › test_crawl.py.… captured on 2022-06-11 at 23:42:31.
⬅️ Previous capture (2021-12-03)
-=-=-=-=-=-=-
import pytest from gus.crawl import should_skip from gus.lib.gemini import GeminiResource class TestUrlExclusion: @pytest.mark.parametrize("test_url,expected_result", [ ("gemini://gemini.circumlunar.space/favicon.ico", True), ("gemini://gemini.circumlunar.space/rss.txt", True), ]) def test_excluded_url_paths(self, test_url, expected_result): resource = GeminiResource(test_url) assert should_skip(resource) == expected_result @pytest.mark.parametrize("test_url,expected_result", [ ("gemini://hannuhartikainen.fi/twinwiki/_revert/1594367314474", True), ("gemini://hannuhartikainen.fi/twinwiki/1594367314474", False), ("gemini://hannuhartikainen.fi/twinwiki/Sandbox/_history/1594037613712", True), ("gemini://hannuhartikainen.fi/twinwiki", False), ("gemini://123456.ch", True), ("gemini://123456.ch/fnord", True), ("gemini://almp1234.app", True), ("gemini://almp1234.app/fnord", True), ]) def test_excluded_url_pattern(self, test_url, expected_result): resource = GeminiResource(test_url) assert should_skip(resource) == expected_result @pytest.mark.parametrize("test_url,expected_result", [ ("gemini://localhost", True), ("gemini://example.org", True), ("gus.guru", False), ("gus.guru/search?turkey", True), ]) def test_excluded_url_prefixes(self, test_url, expected_result): resource = GeminiResource(test_url) assert should_skip(resource) == expected_result