Fetch web pages and convert HTML into clean LLM-ready markdown with anti-bot bypass.
npx skills add https://github.com/leba01/stealthfetch --skill fetching-web-content
Please help me install this Agent Skill. Skill: fetching-web-content Source: https://github.com/leba01/stealthfetch/tree/main/skill Command: npx skills add https://github.com/leba01/stealthfetch --skill fetching-web-content
Fetching web pages for reading or scraping often returns messy HTML packed with navigation, ads, boilerplate, and sometimes blocked-by-bot responses instead of usable content.
FetchResult with markdown plus page fields like title, author, date, description, canonical URL, hostname, and sitename.Use the fetching-web-content skill to fetch https://en.wikipedia.org/wiki/Web_scraping and return the page as cleaned markdown.
High-intent search queries and answers about installing and using this skill.
To extract web page content and get clean markdown, you fetch the URL and the tool strips navigation, ads, and boilerplate, returning LLM-ready markdown text suitable for summarization or knowledge ingestion.
For pages blocked by Cloudflare, DataDome, PerimeterX, or Akamai, the fetcher detects the block and automatically escalates from standard HTTP fetching to a stealth browser to bypass the anti-bot protection and retrieve content.
No, SSRF protection is built-in. The fetcher validates URLs to reject private and loopback destinations, preventing server-side request forgery vulnerabilities when ingesting user-provided web links for scraping.
Yes, optional metadata extraction produces a FetchResult containing the markdown text alongside page fields like title, author, date, description, canonical URL, hostname, and sitename for comprehensive content ingestion.
Standard web scraping returns messy HTML because pages contain navigation, ads, and boilerplate. Using a fetcher that converts pages to clean markdown strips these elements, yielding readable text for immediate use.
Stealth browser escalation is an optional fallback for anti-bot bypass. While it handles blocks from systems like Cloudflare, it is slower than standard HTTP fetching and is only triggered when initial fetch attempts detect a block.
AJBcodingValidate and filter URLs to protect web requests from SSRF.
u9401066Extract text, figures, and citations from PDFs into Markdown.
icyzhScrape static and JavaScript-rendered web pages using stealth browser automation.
richardnguyen0715Scrape static and JavaScript-rendered web content with stealth and Cloudflare bypass.