Merge branch 'dev' into test/normalize-credentials-coverage

2026-03-15 16:24:59 +02:00
parent 54fcb7c364 c7f0db912c
commit 656dbc7d12
64 changed files with 5330 additions and 362 deletions
@@ -7,7 +7,6 @@ from scrapling.engines.toolbelt.navigation import (
    create_async_intercept_handler,
 )
 from scrapling.engines.toolbelt.fingerprints import (
-    generate_convincing_referer,
    get_os_name,
    generate_headers
 )
@@ -204,22 +203,6 @@ class TestConstructProxyDict:
 class TestFingerprintFunctions:
    """Test fingerprint generation functions"""

-    def test_generate_convincing_referer(self):
-        """Test referer generation"""
-        url = "https://sub.example.com/page.html"
-        result = generate_convincing_referer(url)
-
-        assert result.startswith("https://www.google.com/search?q=")
-        assert "example" in result
-
-    def test_generate_convincing_referer_caching(self):
-        """Test referer generation caching"""
-        url = "https://example.com"
-        result1 = generate_convincing_referer(url)
-        result2 = generate_convincing_referer(url)
-
-        assert result1 == result2
-
    def test_get_os_name(self):
        """Test OS name detection"""
        result = get_os_name()
@@ -183,6 +183,33 @@ class TestAdvancedSelectors:
        text = page.get_all_text(valid_values=False)
        assert text != ""

+    def test_get_all_text_preserves_interleaved_text_nodes(self):
+        """Test get_all_text preserves interleaved text nodes"""
+        html = """
+        <html>
+        <body>
+            <main>
+                string1
+                <b>string2</b>
+                string3
+                <div>
+                    <span>string4</span>
+                </div>
+                string5
+                <script>ignored</script>
+                string6
+                <style>ignored</style>
+                string7
+            </main>
+        </body>
+        </html>
+        """
+
+        page = Selector(html, adaptive=False)
+        node = page.css("main")[0]
+
+        assert node.get_all_text("\n", strip=True) == "string1\nstring2\nstring3\nstring4\nstring5\nstring6\nstring7"
+

 class TestTextHandlerAdvanced:
    """Test advanced TextHandler functionality"""
@@ -1,6 +1,6 @@
 pytest>=2.8.0,<9
 pytest-cov
-playwright==1.56.0
+playwright==1.58.0
 werkzeug<3.0.0
 pytest-httpbin==2.1.0
 pytest-asyncio