\r \r

Naver News Search\r

\r Search Korean news articles using the Naver Search API.\r \r

Quick Start\r

\r Use the provided script to search news:\r \r

python scripts/search_news.py "검색어" --display 10 --sort date\r
```\r
\r
Options:\r
- `--display N`: Number of results per page (1-100, default: 10)\r
- `--start N`: Start position for pagination (1-1000, default: 1)\r
- `--sort sim|date`: Sort by relevance (sim) or date (date, default: date)\r
- `--after DATETIME`: Only show news published after this time (ISO 8601 format, e.g., `2026-01-29T09:00:00+09:00`)\r
- `--min-results N`: Minimum number of results to fetch (enables auto-pagination)\r
- `--max-pages N`: Maximum number of pages to try when auto-paginating (default: 5)\r
- `--json`: Output raw JSON instead of formatted text\r
\r
## Setup\r
\r
### Environment Variables\r
\r
Required credentials from https://developers.naver.com/:\r
\r
```bash\r
NAVER_CLIENT_ID=your_client_id\r
NAVER_CLIENT_SECRET=your_client_secret\r
```\r
\r
**Configuration locations:**\r
- **Sandbox (default):** Add to `agents.defaults.sandbox.docker.env` in OpenClaw config\r
- **Host:** Add to `env.vars` in OpenClaw config\r
\r
### Getting API Credentials\r
\r
1. Visit https://developers.naver.com/\r
2. Register an application\r
3. Enable "검색" (Search) API\r
4. Copy Client ID and Client Secret\r
5. Add credentials to appropriate config section (see above)\r
\r
## Common Use Cases\r
\r
### Latest news on a topic\r
\r
```bash\r
python scripts/search_news.py "AI 인공지능" --display 20 --sort date\r
```\r
\r
### Search with relevance ranking\r
\r
```bash\r
python scripts/search_news.py "삼성전자" --sort sim\r
```\r
\r
### Filter by time (only recent news)\r
\r
```bash\r
# News published after 9 AM today\r
python scripts/search_news.py "경제" --display 50 --sort sim --after "2026-01-29T09:00:00+09:00"\r
\r
# News from the last hour (programmatic use)\r
python scripts/search_news.py "속보" --after "$(date -u -d '1 hour ago' '+%Y-%m-%dT%H:%M:%S%z')"\r
```\r
\r
### Auto-pagination for guaranteed minimum results\r
\r
```bash\r
# Fetch at least 30 results (automatically requests multiple pages if needed)\r
python scripts/search_news.py "AI" --sort sim --after "2026-01-29T09:00:00+09:00" --min-results 30 --display 50\r
\r
# Limit to 3 pages maximum\r
python scripts/search_news.py "게임" --min-results 50 --max-pages 3\r
```\r
\r
**How auto-pagination works:**\r
1. Fetches first page (e.g., 50 results)\r
2. Applies date filter (e.g., 10 results remain)\r
3. If below `--min-results`, automatically fetches next page\r
4. Stops when minimum is reached or `--max-pages` limit hit\r
\r
### Pagination for more results\r
\r
```bash\r
# First 10 results\r
python scripts/search_news.py "경제" --display 10 --start 1\r
\r
# Next 10 results\r
python scripts/search_news.py "경제" --display 10 --start 11\r
```\r
\r
## Using in Python Code\r
\r
Import and use the search function directly:\r
\r
```python\r
from scripts.search_news import search_news\r
\r
result = search_news(\r
    query="경제 뉴스",\r
    display=10,\r
    sort="date"\r
)\r
\r
for item in result["items"]:\r
    print(item["title"])\r
    print(item["description"])\r
    print(item["link"])\r
```\r
\r
## API Details\r
\r
For complete API reference including response structure, error codes, and rate limits, see:\r
\r
**[references/api.md](references/api.md)**\r
\r
## Notes\r
\r
- Search queries must be UTF-8 encoded\r
- Results include `\x3Cb>` tags around search term matches (strip them for clean text)\r
- Daily limit: 25,000 API calls per application\r
- `link` field may point to Naver News or original source depending on availability\r