cleanup

adbar · Aug 3, 2023 · 7077420 · 7077420
1 parent d02f9c8
commit 7077420
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 5 deletions.
diff --git a/setup.py b/setup.py
@@ -109,7 +109,7 @@ def get_long_description():
         "certifi",
         "charset_normalizer >= 3.0.1; python_version < '3.7'",
         "charset_normalizer >= 3.1.0; python_version >= '3.7'",
-        "courlan @ git+https://github.com/adbar/courlan@compatibility",
+        "courlan @ git+https://github.com/adbar/courlan",
         "htmldate >= 1.4.3",
         "justext >= 3.0.0",
         "lxml >= 4.9.3 ; platform_system != 'Darwin'",

diff --git a/tests/feeds_tests.py b/tests/feeds_tests.py
@@ -65,7 +65,7 @@ def test_atom_extraction():
         'example.org',
         'http://example.org/',
         'http://example.org',
-    ) == ['http://example.org/article1']
+    ) == ['http://example.org/article1/']  # TODO: remove slash?
 
 
 def test_rss_extraction():
@@ -87,7 +87,7 @@ def test_rss_extraction():
         'example.org',
         'http://example.org/',
         '',
-    ) == ['http://example.org/article1']
+    ) == ['http://example.org/article1/']  # TODO: remove slash?
     # spaces
     assert len(feeds.extract_links(XMLDECL + '<link>\r\n    https://www.ak-kurier.de/akkurier/www/artikel/108815-sinfonisches-blasorchester-spielt-1500-euro-fuer-kinder-in-drk-krankenhaus-kirchen-ein    </link>', 'ak-kurier.de', 'https://www.ak-kurier.de/', '')) == 1
     assert (

diff --git a/tests/sitemaps_tests.py b/tests/sitemaps_tests.py
@@ -164,7 +164,6 @@ def test_robotstxt():
 def test_whole():
     "Test whole process."
     results = sitemaps.sitemap_search("https://www.sitemaps.org", target_lang="de")
-    print(results)
     assert len(results) == 8
 
 

diff --git a/tests/spider_tests.py b/tests/spider_tests.py
@@ -87,7 +87,7 @@ def test_process_links():
     spider.process_links(htmlstring, base_url, language='en')
     todo = spider.URL_STORE.find_unvisited_urls(base_url)
     known_links = spider.URL_STORE.find_known_urls(base_url)
-    assert 'https://example.org/en/page1' in todo and len(known_links) == 4
+    assert 'https://example.org/en/page1/' in todo and len(known_links) == 4  # TODO: remove slash?
     # wrong language
     htmlstring = '<html><body><a href="https://example.org/en/page2"/></body></html>'
     spider.process_links(htmlstring, base_url, language='de')