anti-crawl-a.json

{
    "name": "anti-crawl-a",
    "pair": "anti-crawl",
    "phase": "A",
    "description": "Agent needs to scrape a technical forum (e.g., WeChat article, Feishu doc) for debugging information. The forum blocks direct HTTP requests.",
    "setup": {
        "repo_state": "Agent needs to fetch content from a protected web page",
        "ci_state": "N/A",
        "error_message": "Failed to fetch web page: TLS SNI blocked, connection refused, or 403 forbidden. Tried curl, requests, Playwright — all failed."
    },
    "expected_outcome": {
        "fix_commands": [
            "Check if the site is behind GFW or Cloudflare",
            "Use proxy or alternative scraping method",
            "Consider using open-source mirror or API instead"
        ],
        "lesson_generated": true,
        "lesson_fields": ["title", "domain", "problem", "root_cause", "solution", "verification"]
    },
    "validation": {
        "lesson_has_anti_crawl_info": true,
        "lesson_has_workaround": true
    }
}