<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Web-Scraping on Hitesh Pattanayak</title><link>/tags/web-scraping/</link><description>Recent content in Web-Scraping on Hitesh Pattanayak</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 27 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="/tags/web-scraping/index.xml" rel="self" type="application/rss+xml"/><item><title>Building MCP Tool Servers for a Dividend Review Agent (divvy-forge Part 2)</title><link>/posts/divvy-forge-mcp-servers-demo/</link><pubDate>Thu, 27 Aug 2026 00:00:00 +0000</pubDate><guid>/posts/divvy-forge-mcp-servers-demo/</guid><description>How I built two MCP tool servers — divvy-reader and market-data-fetcher — that give a TrueForge agent live access to a GitHub portfolio and real stock fundamentals. Includes a walkthrough of the raw MCP protocol, BeautifulSoup scraping, and the yfinance fallback.</description></item><item><title>Building a Self-Healing Web Scraper with Bright Data Scraper Studio</title><link>/posts/building-a-self-healing-web-scraper-with-bright-data/</link><pubDate>Thu, 20 Aug 2026 00:00:00 +0000</pubDate><guid>/posts/building-a-self-healing-web-scraper-with-bright-data/</guid><description>Web scrapers break silently when a site changes its DOM. Here&amp;rsquo;s how I built a pipeline that detects a broken scrape, analyses the live page, and rewrites its own parser automatically — using Bright Data Scraper Studio&amp;rsquo;s API.</description></item></channel></rss>