@nickchenzz/xueqiu-spyder
B爬取雪球(Xueqiu)个股热门讨论,通过评论数筛选大V,汇总其对该股票的观点并生成报告。也可爬取指定大V用户的全部帖子。当用户需要查看某只股票的大V观点、市场情绪分析、或某位大V的发帖记录时使用。
Install
agr install @nickchenzz/xueqiu-spyder --target claudeWrites 11 files into .claude/skills/, pinned to git-9678efa2.
- .claude/skills/xueqiu-spyder/.gitignore
- .claude/skills/xueqiu-spyder/README.md
- .claude/skills/xueqiu-spyder/SKILL.md
- .claude/skills/xueqiu-spyder/analyzer.py
- .claude/skills/xueqiu-spyder/config.py
- .claude/skills/xueqiu-spyder/crawler.py
- .claude/skills/xueqiu-spyder/main.py
- .claude/skills/xueqiu-spyder/report.py
- .claude/skills/xueqiu-spyder/requirements.txt
- .claude/skills/xueqiu-spyder/search_user.py
- .claude/skills/xueqiu-spyder/setup_cookie.py
Document
name: xueqiu-spyder description: 爬取雪球(Xueqiu)个股热门讨论,通过评论数筛选大V,汇总其对该股票的观点并生成报告。也可爬取指定大V用户的全部帖子。当用户需要查看某只股票的大V观点、市场情绪分析、或某位大V的发帖记录时使用。
雪球爬虫工具
使用场景
- 用户想了解某只股票在雪球上的大V观点
- 用户提供股票代码(如 SH600519、SZ002738)
- 用户想做个股舆情/情绪分析
- 用户想爬取某位特定大V的帖子记录
使用方式
1. 股票大V观点
python main.py stock <股票代码> [--min-reply 20] [--max-pages 20] [--output ./output]
2. 用户帖子爬取
python main.py user <用户ID或用户名> [--max-pages 10] [--days 30] [--column] [--output ./output]
支持直接传用户名(如 治雨),会自动搜索并解析为数字ID。也可传数字ID。
3. 搜索用户
python main.py search <关键词>
示例
python main.py stock SZ002738 --min-reply 20 --max-pages 10
python main.py user 治雨 --column --max-pages 20
python main.py user 9548638136 --days 30
python main.py search 治雨
输出
在 ./output/ 目录下生成 Markdown 报告。
Trustgrade B
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- warnLicenseno SPDX license detected
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-9678efa25b9b2026-07-31