Add github build action.

.github/workflows/build.yml

@@ -0,0 +1,46 @@
+name: Docker
+on:
+  push:
+    tags:
+      - 'v*'
+env:
+  IMAGE_NAME: ${{ github.repository }}
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Run pnpm
+      run: npm install -g pnpm && pnpm install && pnpm run build
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
+
+    - name: Log in to yiwen-ai registry
+      uses: docker/login-action@v2
+      with:
+        registry: ${{ secrets.CR_REGISTRY }}
+        username: ${{ secrets.CR_USERNAME }}
+        password: ${{ secrets.CR_PASSWORD }}
+
+    - name: Extract metadata (tags, labels) for Docker
+      id: meta
+      uses: docker/metadata-action@v4
+      with:
+        images: |
+          ${{ secrets.CR_REGISTRY }}/ywweb/webscraper
+        tags: |
+          type=semver,pattern={{raw}}
+
+    - name: Build and push Docker image
+      uses: docker/build-push-action@v4
+      with:
+        context: .
+        push: true
+        platforms: linux/amd64
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}

Dockerfile

@@ -1,6 +1,6 @@
 # the available images at https://crawlee.dev/docs/guides/docker-images
 # https://hub.docker.com/r/apify/actor-node-playwright-chrome/tags
-FROM apify/actor-node-playwright-chrome:18-1.34.3-next
+FROM apify/actor-node-playwright-chrome:20-1.35.1-beta
 
 # Copy just package.json and package-lock.json
 # to speed up the build using Docker layer cache.

README.md

@@ -1 +1,3 @@
-# webscraper
+# webscraper
+
+GET http://127.0.0.1:8080/scraping?url=https%3A%2F%2Fmp.weixin.qq.com%2Fs%2Felu0e-EdVkbdp3W68R7zLQ

package.json

@@ -1,6 +1,6 @@
 {
   "name": "webscraper",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "",
   "private": true,
   "main": "dist/main.js",
@@ -77,7 +77,8 @@
     "koa": "^2.14.2",
     "long": "^5.2.3",
     "nanoid": "^4.0.2",
-    "playwright": "^1.35.1"
+    "playwright": "^1.35.1",
+    "zeed-dom": "0.10.5"
   },
   "devDependencies": {
     "@types/config": "^3.3.0",

src/tiptap.ts

@@ -177,7 +177,8 @@ export function parseHTMLDocument (html: string): {
   html: string
 } {
   // writeFileSync('./debug/test-s.html', html, 'utf8')
-
+  // some error: "_a.startsWith is not a function"
+  // https://discuss.prosemirror.net/t/is-there-a-way-to-run-prosemirror-on-nodejs/2517/8
   const jsonDoc = generateJSON(html, tiptapExtensions)
   const amender = new JSONDocumentAmender()
   const htmlDoc = generateHTML(amender.amendNode(jsonDoc as Node), tiptapExtensions)