Files
deer-flow/backend/packages/harness/deerflow/community/jina_ai/jina_client.py

39 lines
1.4 KiB
Python
Raw Normal View History

import logging
import os
import requests
logger = logging.getLogger(__name__)
class JinaClient:
def crawl(self, url: str, return_format: str = "html", timeout: int = 10) -> str:
headers = {
"Content-Type": "application/json",
"X-Return-Format": return_format,
"X-Timeout": str(timeout),
}
if os.getenv("JINA_API_KEY"):
headers["Authorization"] = f"Bearer {os.getenv('JINA_API_KEY')}"
else:
2026-01-14 09:21:19 +08:00
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}
try:
response = requests.post("https://r.jina.ai/", headers=headers, json=data)
if response.status_code != 200:
2026-01-14 09:21:19 +08:00
error_message = f"Jina API returned status {response.status_code}: {response.text}"
logger.error(error_message)
return f"Error: {error_message}"
if not response.text or not response.text.strip():
error_message = "Jina API returned empty response"
logger.error(error_message)
return f"Error: {error_message}"
return response.text
except Exception as e:
error_message = f"Request to Jina API failed: {str(e)}"
logger.error(error_message)
return f"Error: {error_message}"