I will build ai agents web scraping bots and data extraction pipelines in python

H
hamzakhantanoli
H
hamzakhantanoli
Hamza Khan

About this gig

 Who this is for

 - Founders and ops leads who need recurring data (price monitoring, lead enrichment, market research)

 - Researchers and analysts pulling structured data from public websites or PDFs

 - ML and AI teams gathering training data

 - Agencies whose clients ask for "scrape this for us" and need a reliable subcontractor

 

 What I build

 - Web scrapers in Python (Scrapy, BeautifulSoup, Playwright) or Node (Playwright, Puppeteer)

 - AI-powered parsing with OpenAI or Claude so unstructured pages become typed JSON, not regex spaghetti

 - Recurring data pipelines with scheduling, deduplication, change detection, and alerting

 - PDF, document, and OCR extraction when the data isn't on webpage


Stack

 Python, JavaScript, TypeScript, Scrapy, BeautifulSoup, Playwright, Puppeteer, Selenium, requests, httpx, Pandas, OpenAI

 API, Anthropic Claude API, function calling and structured outputs, PostgreSQL, MongoDB, Supabase, Airtable, Google

 Sheets

Get to know Hamza Khan

Hamza Khan

Experienced Full Stack AI Developer

5.0(10)
  • FromPakistan
  • Member sinceFeb 2020
  • Avg. response time6 hours
  • Last delivery1 year
  • Languages

    English, Hindi, Italian, French
I'm a full-stack developer with 6+ years shipping React, Next.js, and Node.js apps. Most of my work now is AI-first: AI SaaS MVPs, custom chatbots with RAG over your data, and OpenAI / Claude integrations. Stack: JavaScript, TypeScript, React, Next.js, Node.js, Vercel AI SDK, OpenAI API, Claude API, Stripe, Supabase, Firebase. Clean, typed, SEO-friendly code — and you own everything I deliver.

My Portfolio