←
Unclecode (Hossein)2,793 posts
Unclecode (Hossein) avatar

Unclecode (Hossein)

@unclecode

Author of Crawl4AI. AI & software builder, systems thinker, founder of Kidocode. I build, analyze, and advise on hard technical problems.

◷ Joined September 2009▧ 283 Photos and videos
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Nov 10

Every scraper builder has this graveyard. Mine is big.

I have a graveyard of dead scrapers. Every one died the same way: the site moved a div, my CSS selector went blind, and the pipeline handed me an empty CSV at 3am. Scrapling is the first framework I've seen that treats that as the actual problem, not a user error. It's a Python scraping library — fetchers, stealth browsers, spiders, the whole pipeline. Its standout is adaptive element tracking: instead of pinning ".price", it tracks the element itself. Site redesigns? It follows along. It also matches similar elements across a page, which is how most of my scrapers actually die — the tenth product card renders slightly different from the first nine. Three things I verified tonight: 1. The whole pipeline in one library — fast HTTP fetch, a stealth browser that handles Cloudflare Turnstile, parsing, concurrent spiders, JSON/CSV export. 2. It ships an MCP server and an agent skill. Your coding agent can browse and extract by itself. That's where this is all going. 3. Install is `pip install "scrapling[fetchers]"` — and yes, you need the [fetchers] extra. Plain `pip install scrapling` gives you a Fetcher that imports nothing. Learned that one the fun way. Five lines later I had 10 quotes off a live page in 1.6 seconds. That's the whole pitch: less time writing selectors, more time using data. Cold water: anti-bot bypass is an arms race, not a finished product — treat the Turnstile claims as "works today". And adaptive tracking is smart, not magic. If the entire page got rewritten in React, you'll still be debugging. But 96K stars and 1.6K new ones a day don't lie about how real this pain is. Repo's in the first comment. BSD-3 license, so your company lawyer won't flinch. If you scrape the web for a living, follow along — I dig up stuff like this every day. When was the last time your scraper survived a site redesign without a 3am fix? Be honest. 🔵 Fellow Premium members, let's connect! I post about AI & tech — follow for more 👥

Post attachment
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Nov 10

Nice to see Crawl4AI on this list. Never gets old.

9 GITHUB REPOS THAT LET YOU SCRAPE ANY WEBSITE WITHOUT GETTING BLOCKED. Most scrapers get banned in the first 100 requests. These ones do not. Crawl4AI — AI-powered crawler built for LLM pipelines. Extracts clean structured data automatically. github.com/unclecode/crawl4a… Firecrawl — Turns any website into clean markdown for AI consumption. Built for RAG pipelines. github.com/firecrawl/firecra… Scrapy — The battle-tested Python scraping framework. 50,000+ stars. Still the most reliable at scale. github.com/scrapy/scrapy Crawlee — Playwright and Puppeteer wrapped in a scraping framework with built-in anti-detection. github.com/apify/crawlee Playwright — Microsoft's browser automation library. Handles JavaScript-heavy sites that break every other scraper. github.com/microsoft/playwri… ScrapeGraph AI — Uses LLMs to navigate and extract data using natural language instructions. github.com/ScrapeGraphAI/Scr… Browser Use — Gives AI agents full browser control. Your Claude agent can now browse and scrape anything. github.com/browser-use/brows… Katana — Fast reconnaissance crawler built for security researchers. Handles complex site architectures. github.com/projectdiscovery/… Maxun — No-code web scraping platform. Build scrapers without writing a single line of code. github.com/getmaxun/maxun Bookmark this before your next data project. Follow @cyrilXBT for every open source build worth your weekend the moment it surfaces.

Post attachmentPost attachmentPost attachment
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 22

Another good use I found for @typesafeai’s Jev: automatically switching Claude Code models based on what I’m working on. I built JevShift for this. It looks at the task and recent context, then picks a model. Here’s a quick demo 👇

1:45
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 18

This is how I matched: modelprint fingerprints 23 known models every day, so when a mystery signature shows up i just compare. modelprint.ai/history btw i also measured the models the viral post says are inside pareto. none of them match what it served me. rumors need measurement too :)

Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 18

i fingerprinted this "union alpha" which turned out it is (unbiased/pareto) for 15 times in 100 minutes: 02:05-02:34 UTC: a fingerprint matching hermes-4-405b in my library, 4 of 4 probes. 02:37: every probe value changes at once. new model. 02:40-03:46: a signature matching nothing i have measured. unknown model. and in 10 of the 15 runs, the same text sent twice, seconds apart, was billed with two different token counts. people spent the stealth week arguing whether it was openai, llama, qwen or glm. everyone was right. they were fingerprinting different models behind one name. Not only for mystery models. Your daily OpenAI or Gemini API deserves the same check. modelprint.ai

Union Alpha is revealed on OpenRouter as @TheUnbiasedCo Pareto! Impressive detective work and demand from the community cut this stealth period short, but you can continue using it now: openrouter.ai/unbiased/paret…

ClaudeDevs avatar
⟳ Unclecode (Hossein) retweeted
ClaudeDevs@ClaudeDevs·Sep 11

New in Claude Code: claude plugin eval See what value your plugin is adding, or if it needs more work. You can create test cases, run your plugin or skill against those test cases, score those runs, then run each case again without the plugin to see the differences.

Post attachment
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 3

I really wonder how will be the saas model? Here @treg_ai let us access to 2800+ saas and pay as u go!

Treg@treg_aiSep 3

Grok bot just killed 2800+ SaaS... Instead of paying $600 subscriptions, build a loop with Treg Try it at treg.to/grokbot Cost cents per call, and tailored to just your needs No subscription, 0% markup Fully open sourced, git repo below 👇

1:00
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 3

Fabel 5.1 is where finally I feel claude code talk concise and relevant! It gets the point much faster, do not generate long essay result for a simple question and so far so good!

Fable 5.1 makes Claude Tag even more useful. Here it builds a last-minute leadership deck from a metrics spreadsheet and other data across Slack, spots a vendor report that disagrees with the numbers, and flags it before moving on. Claude Tag is available in Slack on Team and Enterprise plans.

1:26
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 2

I think paying for all LLM should become pay as you go! Pay only when u use and not monthly subscription! Unless u r a heavy users. Is that something u look? Check this treg oss library and hosted version

Fable 5.1 + Treg = Run GTM fully in a terminal No more $200 subscriptions, just $0.0004/call Fable 5.1 excels at complex, long-running tasks + @treg_ai connects it to 2800+ data & tools: Leads enrich, SEO, social, ads Fully open sourced No subscription, 0% markup Try it at treg.to/fable Git Repo below 👇

0:58
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Sep 1

An AI agent to make sense, needs many tools, or better to make many api calls, and imagine if you want to subscribe to each of em and never never to their cap! How come you make that agent into a profitable business? The solution is a proxy that lets you pay just for the API calls you make! Here @treg_ai is doing that and more: tool routing, team account, remvoe the need to share api keys between team members and many more.

Introducing Claude for people-search No more $600 subscriptions, juts $0.0089/lead Claude is now the best people finder in the world #1 on People Search Bench Fully open source, 0% markup Try it at treg.to/people-search Git Repo below 👇

0:49
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Aug 27

Ok the mystery the ox-alpha is GLM-5.3-Flash, And modelprint.ai was right! ox alpha was the first real test I did. day one, the fingerprint said glm family, 4 of 4 tokenizer probes. day five, z.ai confirmed it. today i reran it on the official glm-5.3-flash endpoint: same values, 47, 56, 60, 90. the label changed, the model did not. anyway the guessing game was fun, but it was not the point for me. but the real question: can you fingerprint a model from its behavior alone, without access to weights? even for open models, reading the weights is slow. behavior is fast. if that works, you get something bigger: a version control system for models that does not depend on the lab, the provider, or anyone's word. the API itself is the source of truth. so now it is a tool, and it is open. join, contribute, add probes. and when the next mystery model appears, we run it again. modelprint.ai

Z.ai@Zai_orgAug 26

Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously previewed as Ox Alpha, running entirely on Chinese AI chips Blog: z.ai/blog/glm-5.3-flash Available now across all official platforms: Weights: huggingface.co/zai-org/GLM-5… API: docs.z.ai/guides/llm/glm-5.3… Coding Plan: z.ai/subscribe ZCode: zcode.z.ai/en Chat: chat.z.ai AutoClaw: autoclaw.z.ai

Post attachment
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Aug 27

update: the official name is out, glm-5.3-flash. i reran the fingerprint on the new endpoint and compared with day one of the stealth run: tokenizer probes 47, 56, 60, 90 then. 47, 56, 60, 90 now. same template delta. the label changed, the model did not. modelprint.ai/history

Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Aug 26

Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai

42T tokens of Ox Alpha in 6 days Most used model after DeepSeek Flash's 56 day run Reveal in a few hours

Post attachment
Unclecode (Hossein) avatar
Unclecode (Hossein)@unclecode·Aug 25

Back to OxAlpha fingerpting, the modelprint has a home now: modelprint.ai And a memory. Every day it fingerprints 21 models, each locked to one provider, and records what it finds. A new entry is written only when a value actually changes. modelprint.ai/history So when someone says a model "feels different today", there is now a place to check instead of guess.

Post attachment

Everyone guessed who made Ox Alpha today. I fingerprinted it instead. One page, 9 infrastructure probes: tokenizers, error codes, hidden templates. I ran • the mystery model against 12 suspects. One family matches every tokenizer test: GLM. Plumbing does not lie. Tool in reply, bring your own keys. Link in reply