Web Scraper

sandbase/web-scraper

Scrape web pages as clean Markdown or HTML, crawl entire sites, extract structured product data with custom schemas, and capture screenshots. Covers single-page extraction, multi-page crawling, visual monitoring, product data mining, and site structure discovery.

Endpoints: 7
Clients: 3
Agents: 1

Install Skill

NPX

$ npx -y skills add https://github.com/sandbaseai/sandbase-skills/tree/main/research/web-scraper

SandBase AgentAGENT · SUPPORTED
CodexCLIENT · SUPPORTED
ClaudeCLIENT · SUPPORTED
CursorCLIENT · SUPPORTED

Tools & Endpoints

7 endpoints

Endpoints

01
context_dev_scrape_markdown
02
context_dev_capture_screenshot
03
context_dev_extract_structured_data
04
context_dev_extract_product
05
firecrawl_scrape
06
firecrawl_crawl
07
firecrawl_map

More Skills

All Skills

Social Intelligence
Zhihu Research
Search questions, answers, articles, and topics on Zhihu — China's premier Q&A and knowledge-sharing platform. Covers answer research, hot list tracking, topic discovery, column analysis, user experti...
8 endpoints
Tools & Utilities
YouTube Transcript
Extract full transcripts and captions from YouTube videos for content analysis, summarization, note-taking, and repurposing. Supports multiple languages and auto-generated captions. Ideal for research...
3 endpoints
Social Intelligence
YouTube Research
Search videos and channels, analyze content performance, extract transcripts, read comments for sentiment, and discover trending Shorts on YouTube. Covers video search, channel strategy analysis, comm...
8 endpoints

Web Scraper

Endpoints

Zhihu Research

YouTube Transcript

YouTube Research