deprecate base_url parameter in extract_links()

adbar · Oct 21, 2024 · 80022ed · 80022ed
1 parent ea02ae9
commit 80022ed
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 7 deletions.
diff --git a/courlan/core.py b/courlan/core.py
@@ -5,7 +5,6 @@
 # import locale
 import logging
 import re
-import warnings
 
 from typing import List, Optional, Set, Tuple
 from urllib.robotparser import RobotFileParser
@@ -136,7 +135,6 @@ def check_url(
 def extract_links(
     pagecontent: str,
     url: Optional[str] = None,
-    base_url: Optional[str] = None,
     external_bool: bool = False,
     no_filter: bool = False,
     language: Optional[str] = None,
@@ -145,6 +143,7 @@ def extract_links(
     with_nav: bool = False,
     redirects: bool = False,
     reference: Optional[str] = None,
+    base_url: Optional[str] = None,
 ) -> Set[str]:
     """Filter links in a HTML document using a series of heuristics
     Args:
@@ -167,9 +166,7 @@ def extract_links(
         Nothing.
     """
     if base_url:
-        warnings.warn(
-            "'base_url' will soon be deprecated, use 'url'.", PendingDeprecationWarning
-        )
+        raise ValueError("'base_url' is deprecated, use 'url' instead.")
 
     base_url = base_url or get_base_url(url)
     url = url or base_url

diff --git a/tests/unit_tests.py b/tests/unit_tests.py
@@ -862,7 +862,9 @@ def test_external():
 
 def test_extraction():
     """test link comparison in HTML"""
-    assert len(extract_links(None, "https://test.com/", False)) == 0
+    with pytest.raises(ValueError):
+        extract_links(None, base_url="https://test.com/", external_bool=False)
+    assert len(extract_links(None, url="https://test.com/", external_bool=False)) == 0
     assert len(extract_links("", "https://test.com/", False)) == 0
     # link known under another form
     pagecontent = '<html><a href="https://test.org/example"/><a href="https://test.org/example/&"/></html>'
@@ -933,7 +935,7 @@ def test_extraction():
         "https://httpbin.org/links/2/1",
     ]
     links = extract_links(
-        pagecontent, base_url="https://httpbin.org", external_bool=False, with_nav=True
+        pagecontent, url="https://httpbin.org", external_bool=False, with_nav=True
     )
     assert sorted(links) == [
         "https://httpbin.org/links/2/0",