xueqiu
Skill0 starsChanged 9 months agoMITView on GitHub
Xueqiu Scraper - Scrape all posts and articles from any Xueqiu user profile
- Installs packages
In this repository33 other files it gives its agents.
- 13fSkill
- info-lake-healthSkill
- calendarSkill
- chatgpt-organizerSkill
- chatgptSkill
- exploreSkill
- flashbackSkill
- GANSkill
- kbSkill
- learnSkill
- linkSkill
- meeting-backtestSkill
- meeting-transcriptSkill
- mocSkill
- notebooklmSkill
- organizer-transcriptSkill
- planSkill
- podcastSkill
- podwise-downloaderSkill
- portfolioSkill
- prompt-optimizerSkill
- researchSkill
- reviewSkill
- socratic-writerSkill
- substackSkill
- supply-chainSkill
- telegramSkill
- thesisSkill
- tradeSkill
- vault-healthSkill
- wechat-haoSkill
- x-bookmarksSkill
- youtube-downloaderSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 56
After scraping, optionally export key posts to Obsidian with standardized frontmatter:
- Distinctive: line 71
Ticker detection: Use shared/ticker_detector for entity-aware tagging (supports Chinese company names like 贵州茅台 → 600519, 比亚迪 → BYDDF):
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Xueqiu Profile Scraper
Scrapes all posts and articles from any Xueqiu user profile. Outputs split text files for NotebookLM.
Project Location
~/xueqiu
When to Use This Skill
- User wants to scrape Xueqiu profiles
- User mentions Xueqiu URL or user ID
- User wants to export Chinese investment posts
- User mentions preparing content for NotebookLM
Key Files
scrape_xueqiu.py- Main scrapersetup_cookies.py- Save login cookiesxueqiu_cookies.json- Saved cookies
Commands
Scrape User Profile
cd "~/xueqiu" && python scrape_xueqiu.py [URL_OR_UID]Example:
cd "~/xueqiu" && python scrape_xueqiu.py https://xueqiu.com/1965894836
cd "~/xueqiu" && python scrape_xueqiu.py 1965894836Setup Cookies (One-Time)
cd "~/xueqiu" && python setup_cookies.pyInstall Dependencies
cd "~/xueqiu" && pip install -r requirements.txt && playwright install chromiumOutput
~/xueqiu\output\{username}\ with JSON and split TXT files.
Obsidian Integration
After scraping, optionally export key posts to Obsidian with standardized frontmatter:
Output path: ~/Documents/Obsidian Vault/Xueqiu/{username}/
Frontmatter template:
---
date: YYYY-MM-DD
source: xueqiu
author: "{username}"
tickers: [TICKER1, TICKER2]
tags: [xueqiu, 投资]
---Ticker detection: Use shared/ticker_detector for entity-aware tagging (supports Chinese company names like 贵州茅台 → 600519, 比亚迪 → BYDDF):
import sys; sys.path.insert(0, str(Path.home() / ".claude" / "skills"))
from shared.ticker_detector import detect_tickers
results = detect_tickers(post_text)Post-Scraping
自动执行: 完成所有处理后,立即对输出文件夹执行 link 扫描(等同于 /link 信息源/雪球/),为新增笔记添加 [[wikilinks]]。
用户说"跳过 link"时跳过此步。
Framework Tagging (after ticker detection)
在 ticker 检测之后,自动标注内容属于分析框架的哪些维度:
from shared.framework_tagger import tag_content
sections = tag_content(text, mode="hybrid") # e.g. ["S1", "S4.2"]将结果添加到 frontmatter extra dict:
framework_sections: [S1, S4.2, S7]如果 framework_tagger 不可用或返回空列表,跳过(不报错)。
与其他 Skills 的关系
| Skill | 关系 |
/notebooklm | Split TXT files can be uploaded as NLM sources |
/moc | Xueqiu posts appear in ticker MOC if tagged |
/research | Chinese investor perspectives supplement research |
/link | Auto-link Xueqiu posts to other vault content |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

