douban-k-search

Name: douban-k-search
Availability: InStock
Author: KunCheng-He

Retrieve structured Douban data for books, movies, and music via HTTP and Playwright.

8|3|Updated Apr 18, 2026

Search Tags:#automation #data extraction #research #search #media #douban

Ready to run

npx skills add https://github.com/KunCheng-He/kk-ai --skill douban-k-search

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: douban-k-search
Source: https://github.com/KunCheng-He/kk-ai/tree/main/skills/shared/douban-k-search
Command: npx skills add https://github.com/KunCheng-He/kk-ai --skill douban-k-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, beautifulsoup4, pydantic, playwright, playwright-stealth, typer, rich, and includes scripts (resource) components.

What problem does it solve?

This skill solves the friction of manually searching and navigating the Douban platform to retrieve reliable cultural product information, ratings, and community feedback.

Core Features & Use Cases

Multi-Category Search: Quickly find books, movies, or music albums using keywords.
Detailed Insights: Retrieve comprehensive metadata including ratings, cast/author info, and summaries.
Community Sentiment: Access user-generated short reviews to gauge public reception.
Use Case: When researching a new book or film, use this skill to instantly pull its rating distribution and top user reviews to inform your decision-making process.

Quick Start

Use the douban-k-search skill to search for the movie Inception and retrieve its detailed information and user reviews.

Frequently Asked Questions about douban-k-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract structured data from Douban for books, movies, and music?▼

You can extract structured Douban data using automated search and detail extraction. The skill retrieves ratings, cast/author info, and user reviews via HTTP requests and Playwright-based browser automation for complex pages.

Can I use Playwright to scrape Douban movie ratings and user reviews?▼

Yes, you can use Playwright to scrape Douban movie ratings and user reviews. The skill employs Playwright-stealth for browser automation on complex pages, ensuring reliable extraction of community sentiment and rating distributions.

What is the best way to automate Douban search for cultural product research?▼

Automating Douban search is best handled through this skill's multi-category search capability. It quickly finds books, movies, or music albums using keywords and formats the parsed data into clean, actionable insights for cultural product research.

Does Douban data extraction with httpx and beautifulsoup4 require a browser?▼

Douban data extraction with httpx and beautifulsoup4 does not always require a browser. The skill uses HTTP requests for standard pages but switches to Playwright-based browser automation specifically for complex pages.

Why does automated Douban scraping fail on some complex pages?▼

Automated Douban scraping fails on some complex pages due to dynamic content loading or anti-bot measures. The skill addresses this by implementing Playwright-stealth browser automation to robustly parse and extract data from these complex pages.

What Python dependencies do I need for retrieving Douban metadata and ratings?▼

To retrieve Douban metadata and ratings, you need the Python dependencies httpx, beautifulsoup4, pydantic, playwright, and playwright-stealth. These handle HTTP requests, HTML parsing, data validation, and browser automation.