Add link_reader tool

Author: wangjiaju

veadk/tools/builtin_tools/link_reader.py

@@ -0,0 +1,74 @@
+# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from volcenginesdkarkruntime._models import BaseModel
+from volcenginesdkarkruntime import AsyncArk
+from veadk.utils.logger import get_logger
+import asyncio
+from httpx import Timeout
+from veadk.config import getenv
+
+logger = get_logger(__name__)
+
+
+async def link_reader(url_list: list[str]) -> dict:
+    """
+    当你需要获取网页、pdf、抖音视频内容时，使用此工具。可以获取url链接下的标题和内容。
+
+
+    examples: {"url_list":["abc.com", "xyz.com"]}
+    Args:
+        url_list (list[str]): 需要解析网页链接,最多3个
+    Returns:
+        list[dict]: 每个url链接下的标题和内容
+    """
+    logger.debug(f"link_reader url_list: {url_list}")
+    try:
+        client = AsyncArk(
+            api_key=getenv("ARK_API_KEY"), timeout=Timeout(connect=1.0, timeout=60.0)
+        )
+    except Exception as e:
+        logger.error(f"link_reader client init failed:{e}")
+        return []
+
+    body = {
+        "action_name": "LinkReader",
+        "tool_name": "LinkReader",
+        "parameters": {"url_list": url_list},
+    }
+
+    try:
+        response = await client.post(
+            path="/tools/execute", body=body, cast_to=BaseModel
+        )
+        response = response.model_dump()
+        logger.debug(f"link_reader response: {response}")
+
+        if response["status_code"] != 200:
+            logger.error(f"link_reader failed: {response}")
+            return []
+        else:
+            return response["data"]["ark_web_data_list"]
+    except Exception as e:
+        logger.error(f"link_reader failed: {e}")
+        return []
+
+
+if __name__ == "__main__":
+    result = asyncio.run(
+        link_reader(
+            ["https://www.baidu.com", "https://www.baidu.com", "https://www.baidu.com"]
+        )
+    )
+    print(len(result), result)