MediaCrawler
Crawls posts and their comments from Chinese social platforms (Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Baidu Tieba, Zhihu) into structured JSON files.
- •You need to analyze user sentiment on a competitor’s post across multiple Chinese platforms.
- •You want to build a dataset of Q&A comments from Zhihu for training a language model.
- •You are monitoring brand mentions in real‑time by pulling new comments from TikTok‑style videos.
python run.py --platform douyin --type video --url https://www.douyin.com/video/7145678901234567890 --output ./douyin_comments.json
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/mediacrawler && curl -fsSL https://workflowstacks.com/api/skills/mediacrawler/claude-skill -o ~/.claude/skills/mediacrawler/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
MediaCrawler is a large Python project (~33k lines across 200 code files, plus 24 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.
- 1README.mdStart here — what it does and how to install it
- 2main.pyWhere the program starts running
- 3package.jsonDependencies and the commands it exposes
- 4.env.exampleThe API keys and settings you must provide
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/mediacrawler && curl -fsSL https://workflowstacks.com/api/skills/mediacrawler/claude-skill -o ~/.claude/skills/mediacrawler/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? Claim your listing → and earn 85% of every sale.
Related skills
More ai-agent tools founders pair with this one.