mediacrawler-social-crawl

Crawl social media content by keywords using MediaCrawler and platform APIs.

Updated May 8, 2026

Search Tags:#data extraction #social media #AI #media analysis #content crawl

Ready to run

npx skills add https://github.com/superfhp/lumi-agent --skill mediacrawler-social-crawl

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mediacrawler-social-crawl
Source: https://github.com/superfhp/lumi-agent/tree/main/skills/mediacrawler-social-crawl
Command: npx skills add https://github.com/superfhp/lumi-agent --skill mediacrawler-social-crawl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mediacrawler, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of crawling and extracting social media content based on specified keywords, saving users the time and effort of manual searches.

Core Features & Use Cases

Keyword-based Crawl: Allows users to search for content across multiple social media platforms using specific keywords.
Data Extraction: Extracts and returns data from platforms such as xhs, wb, bili, dy, ks, tieba, zhihu.
Data File Generation: Generates data files for each keyword and platform combination, enabling easy analysis and reporting.

Quick Start

Use the mediacrawler-social-crawl skill with the keywords "AI" and "deep learning" and request data from "xhs" and "wb".

Frequently Asked Questions about mediacrawler-social-crawl

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

FAQPage Schema

How do I extract social media content using specific keywords?▼

You can extract social media content by defining specific keywords to automatically crawl platforms like xhs, wb, bili, and zhihu. The process retrieves and parses posts matching your search terms, generating structured data files for each keyword and platform combination.

Does social media crawling work with multiple platforms at once?▼

Yes, social media crawling supports multiple platforms simultaneously. You can request data from xhs, wb, bili, dy, ks, tieba, and zhihu in a single operation. It generates separate data files for each platform and keyword combination used.

Do I need MediaCrawler to perform keyword-based data extraction?▼

Yes, you need MediaCrawler to perform keyword-based data extraction. This skill requires the MediaCrawler dependency to execute the crawl and process the retrieved data, utilizing platform-specific APIs and Python libraries for parsing.

How does keyword-based crawling handle large volumes of social media data?▼

Keyword-based crawling handles large volumes of social media data by automating the retrieval and parsing process. It utilizes platform-specific APIs and Python libraries to efficiently extract content, organizing the results into distinct data files for easy analysis.

What is the best way to automate content crawl tasks for media analysis?▼

The best way to automate content crawl tasks for media analysis is using keyword-based extraction. By specifying search terms and target platforms, the system automatically retrieves relevant posts and generates structured data files for reporting.