update requirements

pekopoke · pekopoke · commit 931e6dd28406 · 2025-08-06T10:52:58.000+08:00
diff --git a/examples/basic_usage.py b/examples/basic_usage.py
@@ -801,8 +801,8 @@ def demo_multi_extraction():
 
     # 配置文件路径
     data_dir = Path("../data")
-    # dataset_path = data_dir / "sample_dataset.jsonl"
-    dataset_path = "/home/lulindong/Pycharm_projects/cc/test.jsonl"
+    dataset_path = data_dir / "sample_dataset.jsonl"
+    # dataset_path = "/home/lulindong/Pycharm_projects/cc/test.jsonl"
 
     print(f"📂 数据集文件: {dataset_path}")
 
@@ -816,8 +816,8 @@ def demo_multi_extraction():
             "preserve_formatting": True
         }},
 
-        # {"name": "trafilatura", "config": {}},
-        # {"name": "magic-html", "config": {}},
+        {"name": "trafilatura", "config": {}},
+        {"name": "magic-html", "config": {}},
     ]
 
     # 🔧 选择评测模式：内存模式 vs 批处理模式
diff --git a/tests/test_extractors.py b/tests/test_extractors.py
@@ -32,32 +32,32 @@ def test_trafilatura_extractor(self):
         self.assertEqual(isinstance(result, ExtractionResult), True)
         self.assertEqual(result.success in [True, False], True)
 
-#     def test_magic_html_extractor(self):
-#         # 测试 Magic HTML 抽取器
-#         try:
-#             extractor = ExtractorFactory.create("magic-html")
-#             html_content = """
-#             <html>
-#                 <body>
-#                     <h1 cc-select="true">Python编程教程</h1>
-#                     <p cc-select="true">这是一个Python基础教程，展示如何定义函数。</p>
-#                     <pre cc-select="true"><code>def greet(name):
-#     ""问候函数""
-#     return f"Hello, {name}!"
-#
-# # 使用示例
-# result = greet("World")
-# print(result)</code></pre>
-#                     <p cc-select="true">这个函数可以用来问候任何人。</p>
-#                 </body>
-#             </html>
-#             """
-#             result = extractor.extract(html_content)
-#             self.assertEqual(isinstance(result, ExtractionResult), True)
-#             self.assertEqual(result.success in [True, False], True)
-#         except ValueError as e:
-#             # 如果抽取器未注册，跳过测试
-#             self.skipTest(f"Magic HTML 抽取器未注册: {e}")
+    def test_magic_html_extractor(self):
+        # 测试 Magic HTML 抽取器
+        try:
+            extractor = ExtractorFactory.create("magic-html")
+            html_content = """
+            <html>
+                <body>
+                    <h1 cc-select="true">Python编程教程</h1>
+                    <p cc-select="true">这是一个Python基础教程，展示如何定义函数。</p>
+                    <pre cc-select="true"><code>def greet(name):
+    ""问候函数""
+    return f"Hello, {name}!"
+
+# 使用示例
+result = greet("World")
+print(result)</code></pre>
+                    <p cc-select="true">这个函数可以用来问候任何人。</p>
+                </body>
+            </html>
+            """
+            result = extractor.extract(html_content)
+            self.assertEqual(isinstance(result, ExtractionResult), True)
+            self.assertEqual(result.success in [True, False], True)
+        except ValueError as e:
+            # 如果抽取器未注册，跳过测试
+            self.skipTest(f"Magic HTML 抽取器未注册: {e}")
 
     def test_resiliparse_extractor(self):
         # 测试 Resiliparse 抽取器
