Codex hit HTTP 403, then injected JS via Chrome DevTools to scrape the whole site
burkov · x · 2026-10-11
burkov asked Codex to convert an online HTML book to Markdown, but the server blocked scripted downloads with HTTP 403. After he said "use my session in Chrome," Codex opened the site in Chrome, launched DevTools, injected JavaScript, and auto-downloaded all assets with a progress indicator — outputting a single JSON file with the HTML content. "Honestly a bit scary," he notes, highlighting agents' ability to piggyback on local user sessions to bypass access limits.
More from coding & agent
- Python vs Go vs Rust for production agentic systems: a six-dimension practical evaluation — mostly_deterministic · 2026-10-11
- Agent Use Cases: a free site scanning the web daily for 1,000+ real AI agent use cases — Roger_M_Taylor · 2026-10-11
- Theo: Modern models handle mid-task steering well enough to skip message queueing — pvncher · 2026-10-11
- 1,680 A/B trials show 50-year-old Unix formalisms crush English prompt rules, 98.3% vs 0.8% — RandalSchwartz · 2026-10-11
- Creator tests viral open-source REA to reverse engineer CapCut's hidden tricks — vista8 · 2026-10-11
- Running 426GB MXFP4 DeepSeek on 192GB VRAM to power a 4-sub-agent code review — HankYeomans · 2026-10-11