Files
unicut/scripts/e2e_quickvideo_cover.py
T
jinghui dde45fb4e9 feat(quickvideo): AI一键出片自动生成视频封面
- aiQuickVideo.ts 新增 generateQuickVideoCover(): 标题+图片→封面
  (视觉模型看图/纯文本降级/标题模板兜底, 远程图转dataURL防过期)
- QuickVideo.tsx: 第1步封面与文案并行生成, 第4步封面预览行,
  封面插时间轴最前3秒, 未就绪拦截确认, resetAll清理
- 新增 E2E 脚本 scripts/e2e_quickvideo_cover.py (mock网关, 10项断言全过)
- lint: doc.88531.cn 入 allowlist, lan 文档示例豁免 (external_refs=0)
- 文档: CHANGELOG/README/about.md 教程同步
2026-11-17 17:50:51 +08:00

322 lines
14 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""AI 一键出片「自动封面」端到端:mock 掉对话/生图网关(无需真实 Key),
真实跑完向导 4 步,断言:
1. 确认页出现封面预览行且状态为「AI 按标题和图片生成」
2. 生成后时间轴第一个元素是「视频封面」图片、时长 3 秒、在片头
3. 字幕从封面之后才开始(第一条字幕 BeginTime >= 3000ms)
用法:python3 scripts/e2e_quickvideo_cover.py
"""
import sys, time, json, base64
from playwright.sync_api import sync_playwright
BASE = "https://127.0.0.1:3005"
APPID = "qv_cover_%d" % int(time.time())
STAMP = time.strftime("%H:%M:%S")
def log(msg):
print("[%s] %s" % (STAMP, msg), flush=True)
GUARD = """async () => {
try {
const root = await navigator.storage.getDirectory();
const db = await new Promise((res, rej) => {
const rq = indexedDB.open('H5VideoLocalDB');
rq.onupgradeneeded = () => rq.result.createObjectStore('folderHandles');
rq.onsuccess = () => res(rq.result);
rq.onerror = () => rej(rq.error);
});
const done = await new Promise((res, rej) => {
const tx = db.transaction('folderHandles', 'readwrite');
const st = tx.objectStore('folderHandles');
const rec = { id: 'root', handle: root };
if (st.keyPath) st.put(rec); else st.put(rec, 'root');
tx.oncomplete = () => res(true);
tx.onerror = () => rej(tx.error);
});
db.close();
return done;
} catch (e) { return String(e); }
}"""
# 1280x720 纯色 PNG(mock 生图返回 b64_json)
def make_cover_png_b64():
from PIL import Image
import io
im = Image.new("RGB", (1280, 720), (30, 90, 200))
buf = io.BytesIO()
im.save(buf, format="PNG")
return base64.b64encode(buf.getvalue()).decode()
COPY_JSON = json.dumps({
"segments": [
{"text": "第一段测试口播内容,介绍这张封面", "image": 1},
{"text": "第二段测试口播内容继续讲下去", "image": 2},
{"text": "第三段测试口播内容收尾总结一下", "image": 3},
]
}, ensure_ascii=False)
COVER_PROMPT = "A striking tech product cover, blue gradient, cinematic light, no text"
def install_mock(page, cover_b64):
"""对话/生图网关全部本地 mock:按请求内容区分文案请求与封面提示词请求"""
def handler(route):
req = route.request
url = req.url
if req.method == "OPTIONS":
return route.fulfill(status=204, headers={
"access-control-allow-origin": "*",
"access-control-allow-methods": "POST, OPTIONS",
"access-control-allow-headers": "content-type, authorization",
})
body = req.post_data or ""
headers = {"access-control-allow-origin": "*", "content-type": "application/json"}
if "chat/completions" in url:
# 封面提示词请求的 prompt 里有「做一张封面图」,文案请求有「只输出 JSON」
if "做一张封面图" in body:
content = COVER_PROMPT
else:
content = COPY_JSON
payload = json.dumps({"choices": [{"message": {"content": content}}]})
return route.fulfill(status=200, headers=headers, body=payload)
if "images/generations" in url:
payload = json.dumps({"data": [{"b64_json": cover_b64}]})
return route.fulfill(status=200, headers=headers, body=payload)
return route.fulfill(status=404, headers=headers, body="{}")
page.route("**/v1/chat/completions", handler)
page.route("**/v1/images/generations", handler)
def js_click(page, expr, desc):
ok = page.evaluate("() => { const e = %s; if (e) { e.click(); return true; } return false; }" % expr)
log("点 %s: %s" % (desc, ok))
return ok
def wait_text(page, text, seconds=120, label=""):
for _ in range(seconds):
page.wait_for_timeout(1000)
if page.evaluate("() => document.body.innerText.includes(%s)" % json.dumps(text)):
log("到位[%s]: %s" % (label, text))
return True
log("等待超时[%s]: %s" % (label, text))
return False
def make_images():
from PIL import Image, ImageDraw
out = []
for i, color in enumerate([(200, 60, 60), (60, 140, 200), (80, 170, 90)], 1):
p = "/tmp/qvc_img%d.png" % i
im = Image.new("RGB", (960, 720), color)
d = ImageDraw.Draw(im)
d.text((40, 40), "COVER TEST %d" % i, fill=(255, 255, 255))
im.save(p)
out.append(p)
return out
def main():
imgs = make_images()
cover_b64 = make_cover_png_b64()
log("测试图片: %s" % imgs)
with sync_playwright() as p:
browser = p.chromium.launch(
executable_path="/usr/bin/chromium",
headless=True,
args=["--no-sandbox", "--disable-gpu", "--disable-dev-shm-usage", "--mute-audio",
"--autoplay-policy=no-user-gesture-required"],
)
ctx = browser.new_context(ignore_https_errors=True)
page = ctx.new_page()
errors = []
page.on("pageerror", lambda e: errors.append(str(e)))
page.on("console", lambda m: errors.append("console:" + m.text[:200]) if m.type == "error" else None)
page.on("console", lambda m: log("页面日志 %s" % m.text[:220]) if "[qv]" in m.text else None)
# 预置 AI 配置(Key 是假的,所有请求都被 route mock 掉)
page.add_init_script("""
localStorage.setItem('micut.ai.config.v1', JSON.stringify({
baseUrl: 'https://ai.88531.cn/v1',
apiKey: 'e2e-mock-key',
model: 'mock-model',
}));
""")
install_mock(page, cover_b64)
log("打开工程 %s" % APPID)
page.goto("%s/editor/%s" % (BASE, APPID), wait_until="domcontentloaded", timeout=120000)
page.wait_for_timeout(4000)
log("守卫: %s" % page.evaluate(GUARD))
page.reload(wait_until="domcontentloaded")
page.wait_for_selector("#h5dsCanvas", timeout=90000)
try:
page.wait_for_function("() => document.body.innerText.includes('AI创作')", timeout=90000)
log("侧栏已就绪")
except Exception as e:
log("侧栏等待超时: %s" % e)
page.wait_for_timeout(3000)
js_click(page, """(() => {
const w = document.createTreeWalker(document.body, NodeFilter.SHOW_TEXT);
let n;
while (n = w.nextNode()) {
const t = (n.textContent || '').trim();
if (t === 'AI创作' && n.parentElement) return n.parentElement;
}
return null;
})()""", "AI创作")
page.wait_for_timeout(2500)
js_click(page, "[...document.querySelectorAll('button')].find(x => (x.innerText||'').includes('一键出片'))",
"开始一键出片")
page.wait_for_timeout(3000)
# 步骤1:3 张图 + 标题
fi = page.query_selector("div.semi-modal input[type=file]")
if not fi:
fi = page.query_selector("input[type=file][accept='image/*']")
if not fi:
log("ERROR: 找不到向导的图片输入框")
print(json.dumps({"ok": False, "why": "no-file-input"}, ensure_ascii=False))
return 1
fi.set_input_files(imgs)
page.wait_for_timeout(2500)
page.fill("input[placeholder*='三步搞定']", "封面功能端到端验证")
page.wait_for_timeout(500)
js_click(page, "[...document.querySelectorAll('button')].find(x=>(x.innerText||'').includes('① 识别图片'))", "生成文案")
got = wait_text(page, "下一步:配置声音", 180, "第2步")
log("文案生成完成: %s" % got)
if not got:
print(json.dumps({"ok": False, "why": "copy-timeout", "errors": errors[-6:]}, ensure_ascii=False))
return 1
js_click(page, "[...document.querySelectorAll('button')].find(x=>(x.innerText||'').includes('下一步:配置声音'))", "下一步")
page.wait_for_timeout(2000)
# 步骤3:合成全部配音(真实 edge-tts)
js_click(page, "[...document.querySelectorAll('button')].find(x=>(x.innerText||'').includes('合成全部配音'))", "合成全部配音")
done = wait_text(page, "图片转场", 300, "第4步效果面板")
log("配音合成完成: %s" % done)
if not done:
print(json.dumps({"ok": False, "why": "synth-timeout", "errors": errors[-6:]}, ensure_ascii=False))
return 1
page.wait_for_timeout(1500)
# 断言 1:确认页封面预览行
body = page.inner_text(".semi-modal-body")
has_cover_row = ("视频封面" in body) and ("AI 按标题和图片生成" in body)
has_cover_thumb = page.evaluate("""() => {
const img = [...document.querySelectorAll('.semi-modal img')].find(i => (i.alt||'') === '视频封面');
return !!(img && img.src && img.src.startsWith('data:image/png'));
}""")
has_total = "预计成片" in body
log("确认页封面行: %s, 缩略图 dataURL: %s" % (has_cover_row, has_cover_thumb))
page.screenshot(path="/tmp/qvc_step4.png", full_page=False)
# 生成
js_click(page, "[...document.querySelectorAll('button')].find(x=>(x.innerText||'').includes('③ 确认生成视频'))", "确认生成视频")
page.wait_for_timeout(12000)
# 断言 2/3:时间轴数据
res = page.evaluate("""() => {
const ed = window.__editor && window.__editor.movie;
if (!ed) return {err:'no-editor'};
const d = ed.data || {};
const els = (d.elements || []).slice().sort((a,b) => (a.startTime||0) - (b.startTime||0));
const imgs = els.filter(e => e.type === 'image');
const caps = d.captions || [];
const f = els[0] || null;
// 元素本身不存 url,资源经 resourceManage.getResouceById(resourceId) 取
let resUrl = '';
const rid = f && f.resourceId;
if (rid) {
const mgr = window.__editor.movie.resourceManage;
try {
const r = mgr && mgr.getResouceById && mgr.getResouceById(rid);
if (r) resUrl = r.url || (r.urls && r.urls.url) || '';
} catch (e) { resUrl = 'ERR:' + e; }
}
return {
first: f,
coverResourceUrl: resUrl.slice(0, 40),
imgCount: imgs.length,
elements: els.map(e => ({ name: e.name, type: e.type, t: e.startTime, d: e.duration })),
captionCount: caps.length,
caption0: caps[0] ? JSON.parse(JSON.stringify(caps[0])) : null,
canvas: { w: d.width, h: d.height },
};
}""")
log("工程数据: " + json.dumps(res, ensure_ascii=False)[:2000])
f = res.get("first") or {}
cap0 = res.get("caption0") or {}
# 字幕在元素数据里以秒存 startTime(addCaptions 的 BeginTime 输入被 SDK 归一化)
cap_begin = cap0.get("startTime", cap0.get("BeginTime", cap0.get("beginTime")))
url = res.get("coverResourceUrl") or ((f.get("urls") or {}).get("url") or f.get("url") or "")
checks = {
"cover_row_on_step4": has_cover_row,
"cover_thumb_dataurl": has_cover_thumb,
"first_is_cover": f.get("name") == "视频封面" and f.get("type") == "image",
"cover_at_head": (f.get("startTime") is not None) and abs(float(f.get("startTime"))) < 0.01,
"cover_dur_3": abs(float(f.get("duration") or 0) - 3) < 0.01,
"cover_has_url": bool(url),
"cover_url_is_dataurl": str(url).startswith("data:image"),
# 字幕从封面结束(第 3 秒)起接续
"caption_after_cover": (cap_begin or 0) >= 3,
"caption_count_3": res.get("captionCount") == 3,
}
log("原始首元素: " + json.dumps({k: v for k, v in f.items() if k in ('name','type','startTime','duration','urls','url','trackIndex')}, ensure_ascii=False)[:800])
log("原始字幕0: " + json.dumps(cap0, ensure_ascii=False)[:400])
log("断言: " + json.dumps(checks, ensure_ascii=False))
log("JS 错误: %s" % (errors[-5:] if errors else "无"))
# 播一下确认渲染
page.evaluate("""() => {
const m = window.__editor && window.__editor.movie;
if (m && m.pause) m.pause();
const st = window.__editor;
if (st && st.updateMovie) st.updateMovie(1.0);
}""")
page.wait_for_timeout(2500)
page.screenshot(path="/tmp/qvc_playing.png", full_page=False)
log("截图: /tmp/qvc_step4.png /tmp/qvc_playing.png")
# 刷新确认封面持久化
saved = page.evaluate("""() => {
const s = window.__editor;
if (typeof s.saveApp === 'function') { s.saveApp(() => {}); return 'saveApp 已调用'; }
return '没有 saveApp';
}""")
log("手动保存: %s" % saved)
page.wait_for_timeout(8000)
page.reload(wait_until="domcontentloaded")
page.wait_for_selector("#h5dsCanvas", timeout=90000)
page.wait_for_timeout(12000)
after = page.evaluate("""() => {
const d = (window.__editor && window.__editor.movie && window.__editor.movie.data) || {};
const els = (d.elements || []).slice().sort((a,b) => (a.startTime||0) - (b.startTime||0));
const f = els[0] || {};
return { firstName: f.name, firstT: f.startTime, firstD: f.duration,
els: els.length, caps: (d.captions||[]).length };
}""")
log("刷新后: " + json.dumps(after, ensure_ascii=False))
checks["cover_persist_after_reload"] = (
after.get("firstName") == "视频封面"
and after.get("firstT") is not None and abs(float(after.get("firstT"))) < 0.01
)
ok = all(checks.values())
print(json.dumps({"ok": ok, "checks": checks, "errors": errors[-5:]}, ensure_ascii=False))
browser.close()
return 0 if ok else 2
if __name__ == "__main__":
sys.exit(main())