deepdata: core product code (backend, frontend, runtime, deepflow module)

deepflow/src/crawler/jina_client.py

@@ -0,0 +1,33 @@
+# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
+# SPDX-License-Identifier: MIT
+
+import logging
+import os
+
+import requests
+
+logger = logging.getLogger(__name__)
+
+
+class JinaClient:
+    def crawl(self, url: str, return_format: str = "html") -> str:
+        headers = {
+            "Content-Type": "application/json",
+            "X-Return-Format": return_format,
+        }
+        if os.getenv("JINA_API_KEY"):
+            headers["Authorization"] = f"Bearer {os.getenv('JINA_API_KEY')}"
+        else:
+            logger.warning(
+                "Jina API key is not set. Provide your own key to access a higher rate limit. See https://jina.ai/reader for more information."
+            )
+        data = {"url": url}
+        response = requests.post("https://r.jina.ai/", headers=headers, json=data)
+        
+        if response.status_code != 200:
+            raise ValueError(f"Jina API returned status {response.status_code}: {response.text}")
+        
+        if not response.text or not response.text.strip():
+            raise ValueError("Jina API returned empty response")
+        
+        return response.text