Add auto-scrape workflow

.github/workflows/auto-update.yml

@@ -0,0 +1,128 @@
+name: Regular Auto Update
+
+env:
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
+on:
+  schedule:
+    # 每两周的周一凌晨2点运行
+    - cron: '0 2 * * 1/2'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+concurrency:
+  group: auto-scrape
+  cancel-in-progress: false
+
+jobs:
+  scrape-commit:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+        with:
+          submodules: recursive
+
+      - name: Setup Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.11'
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Detect scraper directory
+        run: |
+          if [ -x "./sp" ]; then
+            echo "SCRAPER_DIR=." >> "$GITHUB_ENV"
+          elif [ -x "./dblp-publications-scraper/sp" ]; then
+            echo "SCRAPER_DIR=./dblp-publications-scraper" >> "$GITHUB_ENV"
+          else
+            echo "Cannot find sp launcher. Checked ./sp and ./dblp-publications-scraper/sp"
+            ls -la
+            exit 1
+          fi
+
+      - name: Install scraper dependencies
+        working-directory: ${{ env.SCRAPER_DIR }}
+        run: |
+          chmod +x ./sp
+          ./sp i
+
+      - name: Run scraper
+        working-directory: ${{ env.SCRAPER_DIR }}
+        env:
+          VENUE_SHORT_LLM_API_KEY: ${{ secrets.VENUE_SHORT_LLM_API_KEY }}
+        run: |
+          CONFIG_FILE="config.github.json"
+          if [ ! -f "$CONFIG_FILE" ]; then
+            CONFIG_FILE="config.json"
+          fi
+
+          if [ ! -f "$CONFIG_FILE" ]; then
+            echo "No config file found in $PWD"
+            ls -la
+            exit 1
+          fi
+
+          CI_CONFIG_FILE="config.ci.json"
+          python - <<'PY'
+          import json
+
+          source_file = "config.github.json"
+          try:
+              with open(source_file, "r", encoding="utf-8") as f:
+                  cfg = json.load(f)
+          except FileNotFoundError:
+              source_file = "config.json"
+              with open(source_file, "r", encoding="utf-8") as f:
+                  cfg = json.load(f)
+
+          cfg["existing_js_path"] = "../collection/auto-collected/auto_collected.js"
+
+          with open("config.ci.json", "w", encoding="utf-8") as f:
+              json.dump(cfg, f, ensure_ascii=False, indent=2)
+
+          print(f"Prepared CI config from: {source_file}")
+          PY
+
+          echo "Using config: $CI_CONFIG_FILE"
+          ./sp --config "$CI_CONFIG_FILE"
+
+
+
+      - name: Check for changes to commit
+        id: check_changes
+        run: |
+          git add -A
+          if git diff --cached --quiet; then
+            echo "changes_detected=false" >> $GITHUB_OUTPUT
+            echo "No changes to commit, skipping PR."
+            exit 0
+          else
+            echo "changes_detected=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Create pull request for updates
+        if: steps.check_changes.outputs.changes_detected == 'true'
+        uses: peter-evans/create-pull-request@v7
+        with:
+          commit-message: "chore: auto update publications"
+          branch: "chore/auto-scrape-updates"
+          delete-branch: true
+          title: "chore: auto update publications"
+          body: |
+            This PR is automatically generated by the Auto Scrape workflow.
+
+            Changes include:
+            - refreshed auto-collected publications
+            - updated bundled JSON assets
+          labels: |
+            automation
+            publications

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "dblp-publications-scraper"]
+	path = dblp-publications-scraper
+	url = https://github.com/imethanguo/dblp-publications-scraper.git

src/bundle.ts

@@ -19,8 +19,8 @@ async function main() {
             return value;
         }), 'validate date string'),
         authors: Joi.array().min(1).items(Joi.string()).required(),
-        venue: Joi.string().min(1).required(),
-        venueShort: Joi.string().min(1).required(),
+        venue: Joi.string().allow('').required(),
+        venueShort: Joi.string().allow('').required(),
         tags: Joi.array().items(Joi.string()),
         awards: Joi.array().items(Joi.string()),
         paperUrl: Joi.string().allow(null, ''),