"""测试 Trafilatura HTML Reader 的解析功能。""" import pytest from scripts.readers.html import trafilatura class TestTrafilaturaHtmlReaderParse: """测试 Trafilatura HTML Reader 的 parse 方法。""" def test_normal_file(self, temp_html): """测试正常 HTML 文件解析。""" file_path = temp_html(content="

标题

段落内容

") content, error = trafilatura.parse(file_path) if content is not None: assert "标题" in content or "段落" in content def test_file_not_exists(self, tmp_path): """测试文件不存在的情况。""" non_existent_path = str(tmp_path / "non_existent.html") content, error = trafilatura.parse(non_existent_path) assert content is None # 如果库未安装，也会返回 None，但错误信息不同 assert error is not None def test_empty_file(self, temp_html): """测试空 HTML 文件。""" file_path = temp_html(content="") content, error = trafilatura.parse(file_path) assert content is None or content.strip() == "" def test_special_chars(self, temp_html): """测试特殊字符处理。""" file_path = temp_html(content="

中文测试 😀 ©®

") content, error = trafilatura.parse(file_path) if content is not None: assert "中文" in content or "测试" in content