feat: initial commit

2026-04-18 08:59:04 +02:00
commit 862c0d1703
32 changed files with 8492 additions and 0 deletions
--- a/Taskfile.yml
+++ b/Taskfile.yml
@@ -0,0 +1,138 @@
+version: '3'
+
+dotenv: ['.env.test']
+
+vars:
+  URL: 'https://example.com'
+  FETCHER: 'http'
+  FORMAT: 'pretty'
+  SERVICE_URL: 'http://localhost:8765'
+
+tasks:
+
+  # ── Build ──────────────────────────────────────────────────────────────────
+
+  build:
+    desc: Compile TypeScript to dist/
+    cmds:
+      - npm run build
+
+  dev:
+    desc: Watch mode — recompile on change
+    cmds:
+      - npm run dev
+
+  # ── Code quality ───────────────────────────────────────────────────────────
+
+  lint:
+    desc: Run ESLint
+    cmds:
+      - npm run lint
+
+  format:
+    desc: Format source with Prettier
+    cmds:
+      - npm run format
+
+  # ── Tests ──────────────────────────────────────────────────────────────────
+
+  test:
+    desc: Run all unit tests
+    cmds:
+      - npm test
+
+  test:watch:
+    desc: Run tests in watch mode
+    cmds:
+      - npm run test:watch
+
+  test:coverage:
+    desc: Run tests with coverage report
+    cmds:
+      - npm run test:coverage
+
+  # ── Python service ─────────────────────────────────────────────────────────
+
+  service:install:
+    desc: Install Python service dependencies (creates .venv in service/)
+    dir: service
+    cmds:
+      - python3 -m venv .venv
+      - .venv/bin/pip install -e ".[dev]"
+      - .venv/bin/scrapling install
+
+  service:start:
+    desc: Start Scrapling microservice on port 8765
+    dir: service
+    cmds:
+      - .venv/bin/uvicorn main:app --host 0.0.0.0 --port 8765 --reload
+
+  service:health:
+    desc: Check Scrapling service health
+    cmds:
+      - curl -s {{.SERVICE_URL}}/health | python3 -m json.tool
+
+  # ── Scrapling CLI runner ────────────────────────────────────────────────────
+
+  scrape:
+    desc: "Scrape a URL  [URL=https://example.com] [FETCHER=http|stealth|dynamic] [FORMAT=pretty|json]"
+    cmds:
+      - >
+        npx ts-node scripts/scrapling-run.ts {{.URL}}
+        --fetcher {{.FETCHER}}
+        --format {{.FORMAT}}
+
+  scrape:html:
+    desc: "Scrape and return raw HTML  [URL=https://example.com]"
+    cmds:
+      - npx ts-node scripts/scrapling-run.ts {{.URL}} --html --format json
+
+  scrape:stealth:
+    desc: "Scrape with stealth fetcher  [URL=https://example.com]"
+    cmds:
+      - npx ts-node scripts/scrapling-run.ts {{.URL}} --fetcher stealth --format {{.FORMAT}}
+
+  scrape:dynamic:
+    desc: "Scrape with Playwright browser  [URL=https://example.com]"
+    cmds:
+      - npx ts-node scripts/scrapling-run.ts {{.URL}} --fetcher dynamic --format {{.FORMAT}}
+
+  # ── Docker ─────────────────────────────────────────────────────────────────
+
+  docker:build:
+    desc: Build Docker image for Scrapling service
+    cmds:
+      - docker build -t scrapling-service ./service
+
+  docker:up:
+    desc: Start full stack (n8n + scrapling-service) via Docker Compose
+    cmds:
+      - docker compose up -d
+
+  docker:down:
+    desc: Stop Docker Compose stack
+    cmds:
+      - docker compose down
+
+  docker:logs:
+    desc: Tail Docker Compose logs
+    cmds:
+      - docker compose logs -f
+
+  # ── Composite ─────────────────────────────────────────────────────────────
+
+  check:
+    desc: Lint + test (pre-push safety check)
+    cmds:
+      - task: lint
+      - task: test
+
+  setup:
+    desc: Install all dependencies and copy .env.test.example if missing
+    cmds:
+      - npm install
+      - |
+        if [ ! -f .env.test ]; then
+          cp .env.test.example .env.test
+          echo ".env.test created — fill in your credentials"
+        fi