dsh-mediacrawler
Run the following command in DeepSeek Harness:
dsh plugin install xwh-01/dsh-mediacrawler
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install the plugin with the command dsh plugin install xwh-01/dsh-mediacrawler, using the full source address https://github.com/xwh-01/dsh-mediacrawler.
About this plugin
Social media data collection often faces challenges like platform login verification, rate limits, and anti-automation measures. DeepSeek Harness users need a reliable way to fetch data from multiple platforms, but directly integrating MediaCrawler can be complex and lack supervision. dsh-mediacrawler acts as an MCP adapter, seamlessly connecting DeepSeek Harness with MediaCrawler, offering 12 tools that cover the entire workflow from environment checks and starting collections to monitoring status and exporting results. It supports search, post/video details, creator feeds, and explicitly enabled comments on platforms like Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu, with browser isolation and credential redaction ensuring security. This plugin is ideal for developers, data analysts, and researchers who need to collect data from social media platforms for content analysis, market research, or monitoring, but desire a controlled, repeatable, and secure tool that enhances efficiency without manually managing MediaCrawler.
Use Cases
- Batch collect posts and comments from platforms like Xiaohongshu and Douyin for content analysis.
- Monitor creator activities and trending topics to gain real-time market insights.
- Export structured data for research or reporting, ensuring reproducibility and security.
Best For
- Developers: Need to integrate data collection into DeepSeek Harness workflows.
- Data Analysts: Involved in social media content analysis and market research.
- Researchers: Conducting academic studies or social trend monitoring.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.