391 lines
14 KiB
Python
391 lines
14 KiB
Python
"""Playwright 登录检测子进程：由 browser_service 以独立解释器启动，argv[1] 为 JSON 配置路径。
|
||
|
||
注意：不得在模块顶层 import playwright / jiangchang_skill_core —— 若导入失败，进程会在 main() 之前以退出码 1 退出，
|
||
且写不了 result_path，父进程只能得到 subprocess_error。所有重依赖均在 _run_login_child 内延迟加载。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import os
|
||
import sys
|
||
import time
|
||
import traceback
|
||
from urllib.parse import urlparse
|
||
|
||
_scripts_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||
if _scripts_dir not in sys.path:
|
||
sys.path.insert(0, _scripts_dir)
|
||
|
||
from util.playwright_stealth import (
|
||
STEALTH_INIT_SCRIPT,
|
||
persistent_context_launch_parts,
|
||
stealth_enabled,
|
||
)
|
||
|
||
|
||
def _is_context_closed_error(ex: BaseException) -> bool:
|
||
s = str(ex).lower()
|
||
if "target closed" in s or "browser has been closed" in s or "context was destroyed" in s:
|
||
return True
|
||
if "closed" in s or "destroyed" in s:
|
||
return True
|
||
return False
|
||
|
||
|
||
def _write_result_file(
|
||
result_path: str,
|
||
interactive_ok: bool,
|
||
end_reason: str,
|
||
detail: str = "",
|
||
) -> None:
|
||
if not (result_path or "").strip():
|
||
return
|
||
payload: dict = {"interactive_ok": interactive_ok, "end_reason": end_reason}
|
||
d = (detail or "").strip()
|
||
if d:
|
||
payload["detail"] = d[:8000]
|
||
try:
|
||
with open(result_path, "w", encoding="utf-8") as rf:
|
||
json.dump(payload, rf, ensure_ascii=False)
|
||
except Exception as write_ex:
|
||
print(f"login_child: failed to write result file: {write_ex}", file=sys.stderr)
|
||
|
||
|
||
def page_location_href(p):
|
||
try:
|
||
href = p.evaluate("() => location.href")
|
||
if href and str(href).strip():
|
||
return str(href).strip()
|
||
except Exception:
|
||
pass
|
||
try:
|
||
return (p.url or "").strip()
|
||
except Exception:
|
||
return ""
|
||
|
||
|
||
def host_matches_anchor(netloc, anchor):
|
||
h = (netloc or "").lower().strip()
|
||
a = (anchor or "").lower().strip()
|
||
if not a:
|
||
return True
|
||
if not h:
|
||
return False
|
||
return h == a or h.endswith("." + a) or a.endswith("." + h)
|
||
|
||
|
||
def loc_first_visible(pg, selectors):
|
||
for sel in selectors:
|
||
s = str(sel).strip()
|
||
if not s:
|
||
continue
|
||
try:
|
||
loc = pg.locator(s).first
|
||
if loc.is_visible(timeout=500):
|
||
return True, s
|
||
except Exception:
|
||
pass
|
||
return False, None
|
||
|
||
|
||
def list_pages_on_anchor(ctx, main_page, bundle):
|
||
anchor = (bundle.get("anchor_host") or "").strip().lower()
|
||
seen_ids = set()
|
||
pages = []
|
||
for pg in list(ctx.pages or []):
|
||
try:
|
||
i = id(pg)
|
||
if i not in seen_ids:
|
||
seen_ids.add(i)
|
||
pages.append(pg)
|
||
except Exception:
|
||
pages.append(pg)
|
||
if main_page is not None:
|
||
try:
|
||
i = id(main_page)
|
||
if i not in seen_ids:
|
||
seen_ids.add(i)
|
||
pages.append(main_page)
|
||
except Exception:
|
||
pages.append(main_page)
|
||
out = []
|
||
for pg in pages:
|
||
try:
|
||
href = page_location_href(pg)
|
||
except Exception:
|
||
continue
|
||
if not href or str(href).lower().startswith("about:"):
|
||
continue
|
||
try:
|
||
host = urlparse(href).netloc.lower()
|
||
except Exception:
|
||
continue
|
||
if anchor and not host_matches_anchor(host, anchor):
|
||
continue
|
||
out.append(pg)
|
||
return out
|
||
|
||
|
||
def evaluate_logged_out_dom(ctx, main_page, bundle):
|
||
selectors = [
|
||
str(x).strip()
|
||
for x in (bundle.get("logged_out_dom_selectors") or [])
|
||
if x is not None and str(x).strip()
|
||
]
|
||
if not selectors:
|
||
return True, "no_logged_out_dom_selectors_configured"
|
||
for pg in list_pages_on_anchor(ctx, main_page, bundle):
|
||
try:
|
||
href = page_location_href(pg)
|
||
except Exception:
|
||
href = ""
|
||
hit, which = loc_first_visible(pg, selectors)
|
||
if hit:
|
||
return True, "logged_out_dom=%r url=%r" % (which, href)
|
||
return False, ""
|
||
|
||
|
||
def _run_login_child(c: dict) -> None:
|
||
"""单次登录检测；结果一律写入 c['result_path']（由 finally 保证）。"""
|
||
result_path = (c.get("result_path") or "").strip()
|
||
try:
|
||
from playwright.sync_api import sync_playwright
|
||
except ImportError:
|
||
_write_result_file(
|
||
result_path,
|
||
False,
|
||
"playwright_missing",
|
||
traceback.format_exc(),
|
||
)
|
||
return
|
||
|
||
interactive_ok = False
|
||
end_reason = "timeout"
|
||
ctx = None
|
||
lg = None
|
||
last_eval_detail = ""
|
||
detail_msg = ""
|
||
|
||
try:
|
||
try:
|
||
from jiangchang_skill_core.unified_logging import attach_unified_file_handler
|
||
except Exception as e:
|
||
end_reason = "logging_import_failed"
|
||
detail_msg = traceback.format_exc()
|
||
print(detail_msg, file=sys.stderr)
|
||
return
|
||
|
||
try:
|
||
profile_dir = (c.get("profile_dir") or "").strip()
|
||
if not profile_dir:
|
||
end_reason = "profile_missing"
|
||
detail_msg = "profile_dir empty in config"
|
||
return
|
||
|
||
os.makedirs(profile_dir, exist_ok=True)
|
||
try:
|
||
n_entries = len(os.listdir(profile_dir))
|
||
except OSError as e:
|
||
end_reason = "profile_dir_unusable"
|
||
detail_msg = f"{type(e).__name__}: {e}"
|
||
return
|
||
except Exception as e:
|
||
end_reason = "profile_dir_unusable"
|
||
detail_msg = traceback.format_exc()
|
||
print(detail_msg, file=sys.stderr)
|
||
return
|
||
|
||
log_path = (c.get("log_file") or "").strip()
|
||
if log_path:
|
||
try:
|
||
lg = attach_unified_file_handler(
|
||
log_path,
|
||
skill_slug="account-manager",
|
||
logger_name="openclaw.skill.account_manager.login_child",
|
||
)
|
||
except Exception as e:
|
||
lg = None
|
||
print(f"login_child: attach_unified_file_handler failed: {e}", file=sys.stderr)
|
||
|
||
if lg is not None:
|
||
lg.info(
|
||
"login_child_start profile_dir=%r profile_entry_count=%s channel=%r url=%r timeout_sec=%r",
|
||
profile_dir,
|
||
n_entries,
|
||
c.get("channel"),
|
||
c.get("url"),
|
||
c.get("timeout_sec"),
|
||
)
|
||
|
||
bundle = c.get("login_detect_bundle") or {}
|
||
poll = float(c.get("poll_interval", 1.5))
|
||
try:
|
||
dom_grace = float(c.get("dom_grace_sec", 4.0))
|
||
except (TypeError, ValueError):
|
||
dom_grace = 4.0
|
||
if dom_grace < 0:
|
||
dom_grace = 0.0
|
||
t0 = time.time()
|
||
deadline = t0 + float(c["timeout_sec"])
|
||
|
||
with sync_playwright() as p:
|
||
try:
|
||
args, ignore_automation = persistent_context_launch_parts()
|
||
lc_kw = dict(
|
||
user_data_dir=profile_dir,
|
||
headless=False,
|
||
channel=c["channel"],
|
||
no_viewport=True,
|
||
args=args,
|
||
)
|
||
if ignore_automation is not None:
|
||
lc_kw["ignore_default_args"] = ignore_automation
|
||
ctx = p.chromium.launch_persistent_context(**lc_kw)
|
||
if stealth_enabled():
|
||
ctx.add_init_script(STEALTH_INIT_SCRIPT)
|
||
except Exception as e:
|
||
if _is_context_closed_error(e):
|
||
end_reason = "user_closed"
|
||
else:
|
||
end_reason = "launch_failed"
|
||
detail_msg = f"{type(e).__name__}: {e}"
|
||
if lg is not None:
|
||
lg.exception("launch_persistent_context failed: %s", e)
|
||
print(detail_msg, file=sys.stderr)
|
||
return
|
||
|
||
try:
|
||
page = ctx.pages[0] if ctx.pages else ctx.new_page()
|
||
page.goto(c["url"], wait_until="domcontentloaded", timeout=60000)
|
||
if dom_grace > 0:
|
||
time.sleep(dom_grace)
|
||
if lg is not None:
|
||
lg.info(
|
||
"goto_done initial_pages=%s poll_interval_sec=%s dom_grace_sec=%s",
|
||
len(ctx.pages or []),
|
||
poll,
|
||
dom_grace,
|
||
)
|
||
while time.time() < deadline:
|
||
iter_start = time.time()
|
||
try:
|
||
still_logged_out, dom_detail = evaluate_logged_out_dom(ctx, page, bundle)
|
||
ok = not still_logged_out
|
||
last_eval_detail = dom_detail
|
||
if lg is not None:
|
||
parts = []
|
||
for tab in list(ctx.pages or []):
|
||
try:
|
||
href = page_location_href(tab)
|
||
pu = (tab.url or "").strip()
|
||
parts.append("href=%r playwright_url=%r" % (href, pu))
|
||
except Exception:
|
||
parts.append("(tab_read_error)")
|
||
lg.debug(
|
||
"poll elapsed=%.1fs left=%.1fs tabs=%s logged_out=%s ok=%s detail=%s | %s",
|
||
iter_start - t0,
|
||
deadline - iter_start,
|
||
len(ctx.pages or []),
|
||
still_logged_out,
|
||
ok,
|
||
dom_detail,
|
||
" ; ".join(parts) if parts else "no_tabs",
|
||
)
|
||
if ok:
|
||
interactive_ok = True
|
||
end_reason = "login_ok"
|
||
if lg is not None:
|
||
lg.info("login_detected_ok %s", dom_detail)
|
||
break
|
||
except Exception as ex:
|
||
if _is_context_closed_error(ex):
|
||
end_reason = "user_closed"
|
||
if lg is not None:
|
||
lg.warning("login_poll_browser_closed err=%s", ex)
|
||
break
|
||
if lg is not None:
|
||
lg.warning("poll_exception err=%s", ex, exc_info=True)
|
||
spent = time.time() - iter_start
|
||
time.sleep(max(0.0, poll - spent))
|
||
|
||
if not interactive_ok and end_reason != "user_closed":
|
||
if lg is not None:
|
||
lg.warning("login_poll_exhausted detail=%s", last_eval_detail)
|
||
rem = max(0.0, deadline - time.time())
|
||
if rem > 0:
|
||
try:
|
||
ctx.wait_for_event("close", timeout=rem * 1000)
|
||
except Exception:
|
||
pass
|
||
elif interactive_ok:
|
||
if lg is not None:
|
||
lg.info("login_dom_ok_preparing_to_release_profile_dir")
|
||
print(
|
||
"INFO:LOGIN_DOM_OK 页面检测已判定登录成功；约 2 秒后关闭本窗口以释放用户目录，供后续大模型网页会话使用。",
|
||
flush=True,
|
||
)
|
||
time.sleep(2.0)
|
||
except Exception as e:
|
||
interactive_ok = False
|
||
if _is_context_closed_error(e):
|
||
end_reason = "user_closed"
|
||
if lg is not None:
|
||
lg.warning("login_runner_browser_closed err=%s", e)
|
||
else:
|
||
end_reason = "page_error"
|
||
detail_msg = traceback.format_exc()
|
||
if lg is not None:
|
||
lg.exception("login_runner_page_err %s", e)
|
||
print(detail_msg, file=sys.stderr)
|
||
finally:
|
||
try:
|
||
ctx.close()
|
||
except Exception:
|
||
pass
|
||
ctx = None
|
||
|
||
except Exception as e:
|
||
interactive_ok = False
|
||
end_reason = "child_fatal"
|
||
detail_msg = traceback.format_exc()
|
||
if lg is not None:
|
||
lg.exception("login_child_unhandled %s", e)
|
||
print(detail_msg, file=sys.stderr)
|
||
finally:
|
||
if ctx is not None:
|
||
try:
|
||
ctx.close()
|
||
except Exception:
|
||
pass
|
||
_write_result_file(result_path, interactive_ok, end_reason, detail_msg)
|
||
|
||
|
||
def _entrypoint() -> None:
|
||
"""读取配置 → 运行检测；任意异常都写入 result JSON，进程以 0 退出（由父进程读 JSON 判定成败）。"""
|
||
result_path = ""
|
||
if len(sys.argv) < 2:
|
||
print("login_child: missing cfg path argv", file=sys.stderr)
|
||
return
|
||
|
||
cfg_path = sys.argv[1]
|
||
try:
|
||
with open(cfg_path, encoding="utf-8") as f:
|
||
c = json.load(f)
|
||
except Exception:
|
||
tb = traceback.format_exc()
|
||
print(tb, file=sys.stderr)
|
||
return
|
||
|
||
result_path = (c.get("result_path") or "").strip()
|
||
|
||
try:
|
||
_run_login_child(c)
|
||
except Exception:
|
||
tb = traceback.format_exc()
|
||
print(tb, file=sys.stderr)
|
||
_write_result_file(result_path, False, "child_fatal", tb)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
_entrypoint()
|