feat: local content-mining platform for YouTube creator scraping

Scraper de canales de YouTube hacia notas Markdown para base de conocimiento (Obsidian-ready), con plataforma web local. Engine + CLI (Workstream A): - Modular pipeline: discover/extract/parse/chapters/render/store + ratelimit - SQLite store con migración idempotente: FTS5 (transcript search), columnas de metadata enriquecida, tablas cookies_meta y scrape_jobs - Módulos: segments, cookies (Netscape vault), export (json/csv/srt/html), analysis (word freq/timeline/wordcloud), monitor (watch loop), pipeline - CLI Click group: search, export, audio, channels, watch, analyze, re-render - Fix del bug de scoping de cookies en cli.py Webapp local (Workstream B): - FastAPI backend: dashboard, channels, videos facetado, transcript, search FTS, analysis, scrape jobs con SSE, cookies drag-and-drop, exports, folders (abrir en OS), tools (re-render, formato) - SPA no-build (Alpine.js + Tailwind + Chart.js por CDN): 9 vistas, tema dark command-center con acento rojo→rosa, cookie vault drag-drop, consola de scrapeo con progreso live vía SSE Launcher + subagentes (Workstream C): - start-server.bat / stop-server.bat con auto port-scan + browser open - .opencode/agent/webapp-builder.md + .opencode/goals/webapp-build.md Tests: 38 pytest verdes. Sin funcionalidad de IA (enfoque data-mining).
2026-07-26 23:19:34 -06:00
commit 621bbc5f5c
45 changed files with 6541 additions and 0 deletions
@@ -0,0 +1,84 @@
+$ErrorActionPreference = 'Stop'
+$root = Split-Path -Parent $PSScriptRoot
+Set-Location -LiteralPath $root
+
+Write-Host ""
+Write-Host "  [yt-scraper] iniciando servidor local..." -ForegroundColor Cyan
+
+if (-not (Test-Path '.run')) { New-Item -ItemType Directory -Path '.run' | Out-Null }
+
+# Already running?
+if (Test-Path '.run\server.info') {
+    $firstLine = (Get-Content '.run\server.info' -TotalCount 1)
+    $existingPort = ($firstLine -split '\s+')[0]
+    try {
+        $r = Invoke-WebRequest -Uri "http://localhost:$existingPort/healthz" -UseBasicParsing -TimeoutSec 2
+        if ($r.Content -match 'ok') {
+            Write-Host "  [ok] servidor ya activo en el puerto $existingPort" -ForegroundColor Green
+            Start-Process "http://localhost:$existingPort"
+            exit 0
+        }
+    } catch {}
+}
+
+# Collect candidate free ports scanning from 8000.
+$candidates = @()
+foreach ($p in 8000..8100) {
+    try {
+        $listener = [System.Net.Sockets.TcpListener]::new([System.Net.IPAddress]::Loopback, $p)
+        $listener.Start(); $listener.Stop()
+        $candidates += $p
+        if ($candidates.Count -ge 8) { break }
+    } catch {}
+}
+if ($candidates.Count -eq 0) {
+    Write-Host "  [error] no se encontro ningun puerto libre (8000-8100)" -ForegroundColor Red
+    exit 2
+}
+
+# Launch uvicorn DETACHED in its own persistent minimized console window, logging to .run/server.log.
+# The `cmd /c` window is an independent console: it survives this launcher exiting.
+$launched = $false
+$proc = $null
+$port = 0
+foreach ($candidate in $candidates) {
+    # clear previous log
+    Remove-Item '.run\server.log' -Force -ErrorAction SilentlyContinue
+    $cmdLine = '/c python -m uvicorn yt_scraper.webapp.app:app --host 127.0.0.1 --port ' + $candidate + ' --log-level info > .run\server.log 2>&1'
+    $proc = Start-Process -FilePath 'cmd.exe' -ArgumentList $cmdLine -WorkingDirectory $root -WindowStyle Minimized -PassThru
+    Set-Content -Path '.run\server.info' -Value "$candidate $($proc.Id) $(Get-Date -Format o)" -Encoding ASCII
+
+    $ok = $false
+    for ($i = 0; $i -lt 40; $i++) {
+        Start-Sleep -Milliseconds 500
+        try {
+            $r = Invoke-WebRequest -Uri "http://localhost:$candidate/healthz" -UseBasicParsing -TimeoutSec 2
+            if ($r.Content -match 'ok') { $ok = $true; break }
+        } catch {}
+    }
+    if ($ok) { $port = $candidate; $launched = $true; break }
+
+    # failed on this port — show why from the log, then try the next candidate
+    Stop-Process -Id $proc.Id -Force -ErrorAction SilentlyContinue
+    Remove-Item '.run\server.info' -Force -ErrorAction SilentlyContinue
+}
+
+if (-not $launched) {
+    Write-Host "  [error] no se pudo iniciar el servidor." -ForegroundColor Red
+    if (Test-Path '.run\server.log') {
+        Write-Host "  --- ultimo log del servidor ---" -ForegroundColor Yellow
+        Get-Content '.run\server.log' -Tail 25 | ForEach-Object { Write-Host "    $_" }
+    } else {
+        Write-Host "  instala dependencias:  pip install -e `".[web]`"" -ForegroundColor Yellow
+    }
+    exit 3
+}
+
+Start-Process "http://localhost:$port"
+Write-Host ""
+Write-Host "  [ok] servidor activo" -ForegroundColor Green
+Write-Host "    URL:   http://localhost:$port"
+Write-Host "    PID:   $($proc.Id)  (ventana minimizada 'cmd' independiente)"
+Write-Host "    log:   .run\server.log"
+Write-Host "    stop:  stop-server.bat"
+Write-Host ""