simple test case

tests/test_html.py

@@ -0,0 +1,51 @@
+from typing import Optional
+
+from pydantic import BaseModel
+from bs4 import Tag
+
+from omniread.html.parser import HTMLParser
+from omniread.core.content import Content
+
+
+class ParsedHTML(BaseModel):
+    title: Optional[str]
+    description: Optional[str]
+    content: Optional[str]
+    link: Optional[str]
+
+
+class TestHTMLParser(HTMLParser[ParsedHTML]):
+    """
+    Concrete HTML parser with explicit Pydantic return type.
+    """
+
+    def parse(self) -> ParsedHTML:
+        soup = self._soup
+        meta = self.parse_meta()
+
+        content_div = soup.find("div", id="content")
+        link_tag: Tag | None = soup.find("a")
+
+        return ParsedHTML(
+            title=meta["title"],
+            description=meta["meta"].get("description"),
+            content=self.parse_div(content_div) if content_div else None,
+            link=self.parse_link(link_tag) if link_tag else None,
+        )
+
+
+def test_end_to_end_html_scrape_and_parse(http_scraper):
+    # --- Scrape (real scraper, mocked transport)
+    content: Content = http_scraper.fetch("https://test.local")
+
+    # --- Parse
+    parser = TestHTMLParser(content)
+    result = parser.parse()
+
+    # --- Assertions
+    assert isinstance(result, ParsedHTML)
+
+    assert result.title == "Test Page"
+    assert result.description == "Simple test page"
+    assert result.content == "Hello World"
+    assert result.link == "https://example.com"