feat: extractor no content_list

examples/basic_usage.py

@@ -290,7 +290,7 @@ def quicksort(arr):
     return dataset
 
 
-def demo_basic_evaluation():
+def demo_basic_mock_evaluation():
     """演示基本评测流程"""
 
     print("=== WebMainBench 基本使用示例 ===\n")
@@ -382,12 +382,12 @@ def _extract_content(self, html, url=None):
     results_dir = Path("results")
     results_dir.mkdir(exist_ok=True)
 
-    results_path = results_dir / "evaluation_results.json"
+    results_path = results_dir / "mock_evaluation_results.json"
     DataSaver.save_evaluation_results(result, results_path)
     print(f"\n结果已保存到: {results_path}")
 
     # 10. 生成报告
-    report_path = results_dir / "evaluation_report.csv"
+    report_path = results_dir / "mock_evaluation_report.csv"
     DataSaver.save_summary_report(result, report_path)
     print(f"报告已保存到: {report_path}")
 
@@ -701,8 +701,8 @@ def hello_world():
 
 if __name__ == "__main__":
     try:
-        demo_basic_evaluation()
-        # demo_llm_webkit_evaluation()  # 使用新的LLM-WebKit评测示例
+        demo_basic_mock_evaluation()
+        demo_llm_webkit_evaluation()  # 使用LLM-WebKit评测示例
         print("\n✅ 示例运行完成！")
 
     except Exception as e:

results/llm_webkit_evaluation_results.json

@@ -2,7 +2,7 @@
   "metadata": {
     "dataset_name": "llm_webkit_test",
     "extractor_name": "llm-webkit",
-    "timestamp": "2025-07-31T13:52:12.948959",
+    "timestamp": "2025-07-31T14:59:59.169188",
     "total_samples": 3
   },
   "overall_metrics": {
@@ -17,7 +17,7 @@
     {
       "sample_id": "text_code_sample",
       "extraction_success": true,
-      "extraction_time": 3.6406631469726562,
+      "extraction_time": 3.614135980606079,
       "metrics": {
         "code_edit": {
           "score": 0.488,
@@ -113,7 +113,7 @@
     {
       "sample_id": "table_sample",
       "extraction_success": true,
-      "extraction_time": 1.6590700149536133,
+      "extraction_time": 1.6187489032745361,
       "metrics": {
         "code_edit": {
           "score": 1.0,
@@ -209,7 +209,7 @@
     {
       "sample_id": "formula_sample",
       "extraction_success": true,
-      "extraction_time": 1.5354089736938477,
+      "extraction_time": 1.5252501964569092,
       "metrics": {
         "code_edit": {
           "score": 1.0,

results/evaluation_results.json → results/mock_evaluation_results.json

@@ -2,7 +2,7 @@
   "metadata": {
     "dataset_name": "sample_dataset",
     "extractor_name": "mock",
-    "timestamp": "2025-07-31T14:29:43.477342",
+    "timestamp": "2025-07-31T14:59:49.917729",
     "total_samples": 2
   },
   "overall_metrics": {
@@ -17,7 +17,7 @@
     {
       "sample_id": "sample-001-programming-tutorial",
       "extraction_success": true,
-      "extraction_time": 4.0531158447265625e-06,
+      "extraction_time": 7.3909759521484375e-06,
       "metrics": {
         "code_edit": {
           "score": 1.0,

webmainbench/extractors/jina_extractor.py

@@ -79,7 +79,7 @@ def _extract_content(self, html: str, url: str = None) -> ExtractionResult:
 
             return ExtractionResult(
                 content=content,
-                content_list=content_list,
+                # content_list=content_list,
                 title=title,
                 # confidence_score=self._calculate_confidence(content, content_list),
                 success=True

webmainbench/extractors/llm_webkit_extractor.py

@@ -661,7 +661,7 @@ def _extract_content(self, html: str, url: str = None) -> ExtractionResult:
             # 创建结果对象
             result = ExtractionResult(
                 content=main_content,
-                content_list=content_list,
+                # content_list=content_list,
                 title=self._extract_title(html),
                 language=self._detect_language(main_content),
                 confidence_score=confidence,