| |
| """End-to-end eval renders: each page as the user sees it with a given build of the extension (or none). |
| |
| usage: ext_render.py --urls URLS.jsonl --out OUT --variant TAG=EXT_DIR [--variant TAG=EXT_DIR ...] [--light] |
| URLS.jsonl lines: {"id", "url"}. Writes OUT/<tag>/<id>.jpg (viewport, after the extension settled) and |
| OUT/<tag>/<id>.json (Nadir status). With --light also OUT/light/<id>.jpg without any extension. |
| Each variant runs in its own persistent profile, so first-visit behaviour (no site cache) is what gets judged. |
| """ |
| import argparse, asyncio, json, os, shutil, time |
| from pathlib import Path |
| from playwright.async_api import async_playwright |
|
|
| STATUS_JS = "async () => { const a = await chrome.storage.session.get(null); return Object.values(a).pop() || null; }" |
|
|
|
|
| async def render_variant(p, tag, ext, urls, out, args): |
| od = out / tag |
| od.mkdir(parents=True, exist_ok=True) |
| prof = out / f"_profile_{tag}" |
| shutil.rmtree(prof, ignore_errors=True) |
| |
| launch_args = ["--hide-scrollbars", "--mute-audio", "--disable-features=DisableLoadExtensionCommandLineSwitch", f"--user-agent={args.ua}"] |
| if ext: |
| launch_args += [f"--disable-extensions-except={ext}", f"--load-extension={ext}"] |
| |
| ctx = await p.chromium.launch_persistent_context(str(prof), executable_path=args.exe or None, channel=None if args.exe else "chromium", headless=True, |
| ignore_default_args=["--disable-extensions"] if ext else [], |
| viewport={"width": 1280, "height": 800}, args=launch_args, user_agent=args.ua) |
| sw = None |
| if ext: |
| sw = ctx.service_workers[0] if ctx.service_workers else await ctx.wait_for_event("serviceworker", timeout=20000) |
| sem = asyncio.Semaphore(args.conc) |
|
|
| async def one(rec): |
| dst = od / f"{rec['id']}.jpg" |
| if dst.exists(): |
| return |
| async with sem: |
| pg = await ctx.new_page() |
| st = {"url": rec["url"], "t": time.time()} |
| try: |
| await pg.goto(rec["url"], wait_until="domcontentloaded", timeout=30000) |
| try: |
| await pg.wait_for_load_state("load", timeout=10000) |
| except Exception: |
| pass |
| await pg.wait_for_timeout(args.wait * 1000) |
| await pg.screenshot(path=str(dst), type="jpeg", quality=82) |
| if sw: |
| try: |
| st["nadir"] = await sw.evaluate(STATUS_JS) |
| except Exception as e: |
| st["nadir_err"] = str(e)[:120] |
| except Exception as e: |
| st["error"] = str(e)[:200] |
| finally: |
| st["ok"] = dst.exists() and "error" not in st |
| (od / f"{rec['id']}.json").write_text(json.dumps(st)) |
| await pg.close() |
| await asyncio.gather(*[one(r) for r in urls]) |
| await ctx.close() |
| shutil.rmtree(prof, ignore_errors=True) |
|
|
|
|
| async def main(): |
| ap = argparse.ArgumentParser() |
| ap.add_argument("--urls", required=True) |
| ap.add_argument("--out", required=True) |
| ap.add_argument("--variant", action="append", default=[], help="TAG=EXT_DIR") |
| ap.add_argument("--light", action="store_true") |
| ap.add_argument("--exe", default="") |
| ap.add_argument("--wait", type=float, default=7.0) |
| ap.add_argument("--conc", type=int, default=4) |
| ap.add_argument("--ua", default="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36") |
| args = ap.parse_args() |
| out = Path(args.out) |
| urls = [json.loads(l) for l in open(args.urls) if l.strip()] |
| async with async_playwright() as p: |
| jobs = [("light", None)] if args.light else [] |
| jobs += [tuple(v.split("=", 1)) for v in args.variant] |
| |
| await asyncio.gather(*[render_variant(p, tag, ext, urls, out, args) for tag, ext in jobs]) |
| print("done", len(urls), [t for t, _ in jobs], flush=True) |
|
|
|
|
| if __name__ == "__main__": |
| asyncio.run(main()) |
|
|
