"""测试所有 HTML Readers 的一致性。""" import pytest from scripts.readers.html import ( html2text, markitdown, trafilatura, domscribe, ) class TestHtmlReadersConsistency: """验证所有 HTML Readers 解析同一文件时核心文字内容一致。""" def test_all_readers_parse_same_content(self, temp_html): """测试所有 Readers 解析同一文件时核心内容一致。""" file_path = temp_html(content=""" 测试页面

测试标题

这是测试段落内容。

第二段内容。

""") # 读取 HTML 内容 with open(file_path, 'r', encoding='utf-8') as f: html_content = f.read() parsers = [ ("html2text", lambda c: html2text.parse(c)), ("markitdown", lambda c: markitdown.parse(c, file_path)), ("trafilatura", lambda c: trafilatura.parse(c)), ("domscribe", lambda c: domscribe.parse(c)), ] successful_results = [] for name, parser in parsers: content, error = parser(html_content) if content is not None and content.strip(): successful_results.append((name, content)) assert len(successful_results) > 0, "没有任何 reader 成功解析文件" core_texts = ["测试标题", "测试段落", "内容", "第二段"] for name, content in successful_results: assert any(text in content for text in core_texts), \ f"{name} 解析结果不包含核心内容"