feat(skill/gemini-music-web): 新增音乐生成与下载收集流程

2026-03-04 02:04:48 +08:00
parent 4caa839154
commit aa72b570e1
4 changed files with 794 additions and 0 deletions
@@ -0,0 +1,230 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+usage() {
+  cat <<'EOF'
+Usage:
+  run_music_flow.sh --prompt "<text>" --target /abs/output/dir [--count N] [--session NAME] [--no-headed]
+
+Example:
+  run_music_flow.sh \
+    --prompt "创作一段 90 BPM 的 lo-fi hiphop，温暖、夜晚、钢琴和刷镲，时长 30 秒。" \
+    --target /Users/xd/java/xhs/output/gemini-music \
+    --count 2
+EOF
+}
+
+PROMPT=""
+TARGET=""
+COUNT=1
+SESSION="gmw$(date +%s)"
+HEADED=1
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --prompt)
+      PROMPT="${2:-}"
+      shift 2
+      ;;
+    --target)
+      TARGET="${2:-}"
+      shift 2
+      ;;
+    --count)
+      COUNT="${2:-1}"
+      shift 2
+      ;;
+    --session)
+      SESSION="${2:-$SESSION}"
+      shift 2
+      ;;
+    --no-headed)
+      HEADED=0
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown arg: $1" >&2
+      usage
+      exit 1
+      ;;
+  esac
+done
+
+if [[ -z "$PROMPT" || -z "$TARGET" ]]; then
+  echo "Both --prompt and --target are required." >&2
+  usage
+  exit 1
+fi
+
+if ! [[ "$COUNT" =~ ^[0-9]+$ ]] || [[ "$COUNT" -lt 1 ]]; then
+  echo "--count must be a positive integer." >&2
+  exit 1
+fi
+
+CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
+PWCLI="${PWCLI:-$CODEX_HOME/skills/playwright/scripts/playwright_cli.sh}"
+COLLECT_SCRIPT="$(cd "$(dirname "$0")" && pwd)/collect_downloads.py"
+
+if ! command -v npx >/dev/null 2>&1; then
+  echo "npx is required." >&2
+  exit 1
+fi
+if [[ ! -x "$PWCLI" ]]; then
+  echo "Playwright wrapper not found or not executable: $PWCLI" >&2
+  exit 1
+fi
+if [[ ! -f "$COLLECT_SCRIPT" ]]; then
+  echo "Collector script not found: $COLLECT_SCRIPT" >&2
+  exit 1
+fi
+
+pw() {
+  "$PWCLI" --session "$SESSION" "$@"
+}
+
+json_escape() {
+  python3 - "$1" <<'PY'
+import json
+import sys
+print(json.dumps(sys.argv[1]))
+PY
+}
+
+is_login_required() {
+  local out
+  out="$(
+    pw eval "() => {
+      const hasAccount = !!document.querySelector('button[aria-label*=\\\"Google 账号\\\"], button[aria-label*=\\\"Google Account\\\"]');
+      const hasService = !!document.querySelector('a[href*=\\\"ServiceLogin\\\"]');
+      const hasLoginCtl = Array.from(document.querySelectorAll('a,button')).some(el => /登录|Sign in/i.test((el.textContent || '').trim()));
+      return !hasAccount && (hasService || hasLoginCtl);
+    }"
+  )"
+  echo "$out" | rg -q '^true$'
+}
+
+enter_music_tool() {
+  local js
+  js="$(cat <<'JS'
+const labels = [/创作音乐/, /制作音乐/, /Create music/i, /Music/i];
+
+const tryCardButtons = async () => {
+  for (const re of labels) {
+    const btn = page.getByRole('button', { name: re }).first();
+    if (await btn.count()) {
+      try {
+        await btn.click({ timeout: 2000 });
+        return true;
+      } catch (_) {
+        // Overlay may intercept pointer. Fall through to menu strategy.
+      }
+    }
+  }
+  return false;
+};
+
+const tryToolMenu = async () => {
+  await page.getByRole('button', { name: '工具', exact: true }).click();
+  for (const re of labels) {
+    const itemCheck = page.getByRole('menuitemcheckbox', { name: re }).first();
+    if (await itemCheck.count()) {
+      await itemCheck.click();
+      return true;
+    }
+    const itemPlain = page.getByRole('menuitem', { name: re }).first();
+    if (await itemPlain.count()) {
+      await itemPlain.click();
+      return true;
+    }
+  }
+  return false;
+};
+
+let ok = await tryCardButtons();
+if (!ok) ok = await tryToolMenu();
+if (!ok) {
+  // Re-open the tool menu once and retry as a last attempt.
+  ok = await tryToolMenu();
+}
+if (!ok) {
+  throw new Error('Music tool entry not found');
+}
+JS
+)"
+  pw run-code "$js" >/dev/null
+}
+
+submit_and_download_one() {
+  local track_prompt="$1"
+  local escaped
+  escaped="$(json_escape "$track_prompt")"
+  local js
+  js="$(cat <<JS
+const prompt = $escaped;
+const input = page.getByRole('textbox', { name: /为 Gemini 输入提示|Enter a prompt/i }).first();
+await input.click();
+await input.fill(prompt);
+await input.press('Enter');
+
+const stopBtn = page.getByRole('button', { name: /停止回答|Stop response/i }).first();
+await stopBtn.waitFor({ state: 'visible', timeout: 15000 }).catch(() => {});
+await stopBtn.waitFor({ state: 'hidden', timeout: 240000 });
+
+const downloadBtn = page.getByRole('button', { name: /下载音乐作品|Download music/i }).last();
+await downloadBtn.click();
+
+const mp3Item = page.getByRole('menuitem', { name: /纯音频|MP3/i }).first();
+if (await mp3Item.count()) {
+  await mp3Item.click();
+} else {
+  const anyItem = page.getByRole('menuitem').first();
+  if (await anyItem.count()) await anyItem.click();
+}
+
+await page.waitForTimeout(1200);
+JS
+)"
+  pw run-code "$js" >/dev/null
+}
+
+mkdir -p "$TARGET"
+start_ts="$(python3 - <<'PY'
+import time
+print(time.time())
+PY
+)"
+
+if [[ "$HEADED" -eq 1 ]]; then
+  pw open "https://gemini.google.com/app" --headed >/dev/null
+else
+  pw open "https://gemini.google.com/app" >/dev/null
+fi
+pw snapshot >/dev/null
+
+if is_login_required; then
+  echo "Gemini is not logged in. Please log in at https://gemini.google.com/app and rerun." >&2
+  exit 2
+fi
+
+enter_music_tool
+
+for ((i=1; i<=COUNT; i++)); do
+  current_prompt="$PROMPT"
+  if [[ "$COUNT" -gt 1 ]]; then
+    current_prompt="$PROMPT
+变体要求：这是第 $i / $COUNT 首。保持风格一致，但旋律和节奏细节需要变化。"
+  fi
+  submit_and_download_one "$current_prompt"
+done
+
+python3 "$COLLECT_SCRIPT" \
+  --target "$TARGET" \
+  --since "$start_ts" \
+  --expected-count "$COUNT" \
+  --limit "$COUNT" \
+  --prefix "gemini-music" \
+  --prompt "$PROMPT"