"""Pure-parse tests for HtmlPageSource. No network."""
from __future__ import annotations
import pytest
# Skip if optional extras are not installed.
selectolax = pytest.importorskip("selectolax")
from arborist.sources.html_page import parse_html
SAMPLE_HTML = """
Eight Forms of Capital
js linkmail link
"""
def test_parse_extracts_title_and_body():
doc = parse_html("https://example.com/page", SAMPLE_HTML)
assert doc is not None
assert doc.title == "Eight Forms of Capital"
assert "Living" in doc.content
assert "Spiritual" in doc.content
def test_parse_strips_noise():
doc = parse_html("https://example.com/page", SAMPLE_HTML)
assert doc is not None
assert "console.log" not in doc.content
assert "color: red" not in doc.content
assert "Site nav we want stripped" not in doc.content
assert "strip me too" not in doc.content
assert "nav links also stripped" not in doc.content
def test_parse_extracts_edges_and_resolves_relative():
doc = parse_html("https://example.com/page", SAMPLE_HTML)
assert doc is not None
uris = {e.dst_uri for e in doc.edges}
# Relative href resolved against the page URL.
assert "https://example.com/eight-forms-of-capital/" in uris
# External link kept; fragment moved to anchor.
assert "https://example.org/external" in uris
# javascript: / mailto: / tel: / hash-only anchors must be skipped.
assert all("javascript" not in u for u in uris)
assert all("mailto" not in u for u in uris)
def test_parse_anchor_split():
doc = parse_html("https://example.com/page", SAMPLE_HTML)
assert doc is not None
external = next(e for e in doc.edges if e.dst_uri == "https://example.org/external")
assert external.anchor == "section"
def test_parse_empty_body_returns_none():
doc = parse_html("https://example.com/empty", "")
assert doc is None
def test_parse_no_html_returns_none_or_empty():
# Selectolax tolerates non-HTML; we want no Document for empty content.
doc = parse_html("https://example.com/x", "")
assert doc is None