From daymade-financial
Fetches A-share stock market news, policy announcements, and forum sentiment from Chinese public sources. Outputs structured JSON or Markdown for analysis or LLM ingestion.
How this skill is triggered — by the user, by Claude, or both
Slash command
/daymade-financial:ashare-news-fetcher [--sources <groups>] [--symbols <codes>] [--limit <n>][--sources <groups>] [--symbols <codes>] [--limit <n>]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
从多个公开中文财经/政策/社交来源抓取 A 股相关情报,输出结构化条目。
从多个公开中文财经/政策/社交来源抓取 A 股相关情报,输出结构化条目。
能做的:
000001,600519)抓取该股股吧情绪不能做的:
requests(必须)beautifulsoup4(可选,只有抓取政策来源时才需要)akshare(可选,用于名称→代码匹配;没有时只用正则提取代码)jieba(可选,安装后名称匹配使用分词,降低误匹配)JIN10_APP_ID(金十数据接口需要;未设置时会跳过该来源,不影响其他 cn 来源)最简安装:
pip install requests
# 如需政策来源:
pip install beautifulsoup4
# 如需名称匹配:
pip install akshare
# 如需更精确的名称匹配:
pip install jieba
/ashare-news-fetcher 000001,600519 cn,guba
参数说明(都是可选的):
000001,600519cn(中文快讯)、policy(政策)、guba(股吧)--sources cn --limit 30python scripts/fetch_intel.py --sources cn,policy --limit 20
python scripts/fetch_intel.py --symbols 000001,600519 --sources guba
python scripts/fetch_intel.py --sources cn --keywords 降准,降息 --format markdown
常用选项:
--sources:来源组,默认 cn--symbols:股票代码,用于 guba--keywords:关键词过滤,逗号分隔--limit:每组最多返回条数,默认 30--format:json 或 markdown,默认 json--output:输出到文件;省略则打印到 stdout--verbose:打印调试日志| 来源组 | 来源 | 内容类型 | 是否需要 bs4 |
|---|---|---|---|
cn | 财联社、华尔街见闻、金十、新浪 7x24、东财快讯 | 市场快讯 | 否 |
policy | 证监会、央行、上交所、财政部 | 政策/监管公告 | 是(证监会除外) |
guba | 东方财富股吧 | 个股散户情绪 | 否 |
详细 API 端点和解析方式见 references/source_apis.md。
测试说明与运行方式见 references/testing.md。
每个 item 的结构见 references/output_schema.md。示例:
{
"item_id": "4ffde7bc7b18b55e",
"source_id": "cn_sina",
"source_name": "sina",
"title": "...",
"summary": "...",
"url": "...",
"category": "market",
"priority": "normal",
"tags": ["公司", "市场"],
"related_symbols": ["000001"],
"published_at": "2026-06-25 17:50:41",
"fetched_at": "2026-06-25 09:50:52",
"extra": {}
}
按时间倒序排列,每条展示来源、时间、分类、相关代码、标签、链接和摘要。
guba 来源对反爬较敏感,建议单次不要请求过多股票,代码之间已有 0.5s 请求间隔。jin10)前,建议在环境变量中配置 JIN10_APP_ID;未配置时该来源会自动跳过,不影响财联社、华尔街见闻、新浪、东财等其他 cn 来源。
export JIN10_APP_ID="your-app-id"
拿到结构化情报后,常见的下一步是交给分析 skill 做总结或生成日报:
要不要把这些消息总结一下,生成一份 A 股消息日报?
npx claudepluginhub p/daymade-daymade-financial-daymade-financialLoads A-share stock analysis with multi-source news aggregation, market sentiment reading, stock scoring (v2.0 symmetric -80 to +100), and raw news browsing. Activated by keywords like '分析A股' or '今日主线'.
Queries Chinese A-share data via local akshare Python library: real-time quotes, historical K-lines (daily/weekly/monthly/minute), adjusted prices, shareholder counts, announcements. Uses EM/Sina APIs, outputs CSV/JSON.
Analyzes A-stock (Chinese stocks) with real-time quotes, technical analysis, fundamentals, sector analysis, derivatives, and cross-market data. Uses akshare and natural language routing.