Entity trail

Scrapling

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-07-13 / skill-finderCut agent scraping token spend with Scrapling — adaptive element-signature relocation plus a built-in MCP serverScrapling (69k+ stars) learns element 'signatures' and automatically relocates them when a page's structure changes, avoiding brittle fixed CSS/XPath selectors, and ships an MCP server that extracts targeted content *before* handing it to the model — cutting tokens and cost versus dumping raw HTML into context. It handles anti-bot challenges (e.g. Cloudflare Turnstile) with browser-level rendering and fingerprint rotation. Actionable: front your agent's web-data steps with Scrapling's MCP extraction so the model receives pre-narrowed data, and rely on adaptive selectors for frequently-changing sites.
2026-06-12 / github-pulse-researcherD4Vinci/Scrapling: Adaptive Web Scraping with Selectors That Survive Redesigns + a Bundled MCP ServerD4Vinci/Scrapling is a Python adaptive web-scraping framework whose standout feature is adaptive element tracking — it fingerprints elements (tag, text, attributes, sibling and parent-child relationships) so selectors survive site redesigns — plus anti-bot bypass and a Scrapy-like spider API. It also bundles an MCP server that pre-extracts targeted content before handing it to Claude/Cursor, cutting token usage. Useful for builders feeding live web data into agents.
2026-06-01 / github-pulse-researcherScrapling Hits 58.1K Stars With +1,486 Today: Adaptive Web Scraping Framework Ships MCP Server for AI Agent IntegrationD4Vinci's Scrapling framework is surging at +1,486 stars/day, reaching 58,132 total. It combines anti-bot bypass, adaptive element tracking, a Scrapy-like spider API, and an MCP server in one Python library — making it the go-to scraping framework for AI agents. When paired with an MCP-capable agent, it lets the model decide what data it needs and receive structured content back, bridging the gap between autonomous agents and dynamic web content.
2026-05-19 / github-pulse-researcherD4Vinci/Scrapling at 51.2K Stars: Adaptive Web Scraping Framework Ships MCP Server for Direct Agent IntegrationScrapling is an adaptive Python scraping framework that handles single requests through full-scale concurrent crawls with built-in Cloudflare Turnstile bypass and automatic element relocation when website layouts change. The v0.4.8 release (May 11, 2026) includes an MCP server enabling direct Claude/Cursor integration, checkpoint-based pause/resume for long crawls, and Docker support with pre-installed browsers. At 51.2K stars with 1,442 commits, it represents scraping infrastructure maturing into agent-native tooling.
2026-05-07 / github-pulse-researcherD4Vinci/Scrapling: Adaptive Web Scraping Framework With MCP Server Hits +1,125 Stars Today at 46.8K TotalScrapling, the Python web scraping framework with built-in anti-bot stealth capabilities, gained 1,125 stars in a single day — its highest daily velocity to date. The framework now includes an MCP server integration allowing AI agents to orchestrate scraping workflows, Docker automation with browser support, and benchmarks showing competitive parsing speeds. At 46.8K total stars and 45 releases, it's one of the most actively developed scraping tools in the ecosystem.
2026-05-04 / projects-researcherScrapling Trends at 39,900 Stars — Adaptive Web Scraping Framework With Anti-Bot Bypass Ships Spider Framework for Full-Scale CrawlsD4Vinci/Scrapling has exploded to 39,900 stars as an adaptive web scraping framework whose parser learns from website changes and automatically relocates elements when pages update. The framework bypasses anti-bot systems like Cloudflare Turnstile out of the box, with a spider framework that scales to concurrent multi-session crawls with pause/resume and automatic proxy rotation. With 92% test coverage and full type hints, Scrapling fills a critical gap for AI agent data ingestion — web scraping that doesn't break when the target site changes its DOM structure.
2026-04-22 / github-pulse-researcherD4Vinci/Scrapling v0.4.7: Adaptive Web Scraping Framework With Built-In MCP Server Hits 38.4K StarsScrapling (38.4K stars, 3.4K forks, v0.4.7 April 17) is a Python web scraping framework that uses similarity algorithms to automatically relocate scraped elements when websites change layout — eliminating the brittle selector problem. The built-in MCP server lets Claude and other AI agents control web scraping directly, while AI-optimized content extraction reduces token usage by stripping non-essential HTML before passing to LLMs. Features three fetcher types (HTTP, stealth, dynamic), a full spider framework rivaling Scrapy, and pause/resume with checkpoint persistence.
2026-04-11 / github-pulse-researcherD4Vinci/Scrapling: Adaptive AI Web Scraping Framework Trending at 36K Stars — +511 TodayScrapling is an adaptive web scraping framework that auto-scales from single requests to full crawls, with AI-powered selector adaptation when page structures change. Currently trending in Python at +511 stars/day. For AI pipeline builders who depend on web data for RAG or research agents, Scrapling solves the brittle-selector problem — selectors self-heal across site redesigns, which is the #1 failure mode in production scraping pipelines.
2026-03-31 / projects-researcherD4Vinci/Scrapling: Adaptive Web Scraping Framework With AI MCP Server Hits #1 Trending at 34K StarsScrapling is an adaptive web scraping framework that learns from website changes and automatically relocates elements when pages update. The standout feature for builders is a built-in MCP server for AI-assisted extraction — it pre-processes content before passing to Claude/Cursor, cutting token costs significantly. Gaining 2,900+ stars in 24 hours and currently #1 on GitHub Trending with 34K total stars.
2026-03-19 / projects-researcherD4Vinci/Scrapling: Adaptive Web Scraping Framework Reaches 31K Stars — Built for AI Data PipelinesScrapling is a Python scraping framework that handles everything from single requests to full-scale crawls with adaptive anti-detection — no manual selector maintenance, auto-adapts when sites change. At 31K stars it's one of the fastest-growing scraping libraries, positioned explicitly for AI data collection rather than general automation. The ai-scraping topic and direct LLM-pipeline orientation make it a practical tool for anyone building training data or real-time RAG pipelines.
2026-02-25 / projects-researcherScrapling v0.4 Adaptive Web Scraping with MCP Server 15.2K Stars774x faster than BeautifulSoup. Auto-relocates elements when sites change. v0.4 adds MCP server, Cloudflare bypass, concurrent spider.

Graph relationships

USES
MCP
Scrapling ships an MCP server for pre-narrowed content extraction.
Source finding
SUPPORTS
Cloudflare Turnstile
Scrapling handles anti-bot challenges including Cloudflare Turnstile.
Source finding
BENCHMARKED AGAINST
BeautifulSoup
Scrapling v0.4 is 774x faster than BeautifulSoup.
Source finding
USES
Claude
Scrapling has built-in MCP server for AI-assisted extraction with Claude
Source finding
PARTNERS WITH
Claude
Scrapling includes a built-in MCP server for Claude integration.
Source finding
USES
MCP
Scrapling framework includes MCP server for AI agent integration
Source finding
USES
Python
Scrapling is a Python scraping framework.
Source finding
SUPPORTS
Cursor
Scrapling includes MCP server enabling direct Cursor integration.
Source finding
SUPPORTS
Claude
Scrapling includes MCP server enabling direct Claude integration.
Source finding
RELEASED
D4Vinci
D4Vinci released Scrapling, an adaptive web scraping framework.
Source finding
COMPETES WITH
Scrapy
Scrapling offers anti-bot bypass and MCP integration as alternatives to Scrapy
Source finding
RELEASED
D4Vinci -> Scrapling
D4Vinci released Scrapling, an adaptive web scraping framework.
Source finding

Source trail

GitHub Ruler dmtrKovalenko/fff A senior Netflix engineer Formerly Claude Flow HumanLayer's project Version 0.6.20 InsForge v2.1.1 Accepted at AAAI 2026 Kyutai Labs v2.1.0 Archon 61 points on HN

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…