Files
account-manager/scripts/service/browser_service.py
chendelian c83841cf90
All checks were successful
技能自动化发布 / release (push) Successful in 39s
chore: auto release commit (2026-04-06 16:44:58)
2026-04-06 16:44:59 +08:00

406 lines
14 KiB
Python
Raw Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
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.
"""Chromium/Edge 检测与 Playwright 登录、仅打开浏览器。"""
import json
import os
import subprocess
import sys
import tempfile
import time
from urllib.parse import urlparse
from db.accounts_repo import get_account_by_id, mark_login_status
from util.logging_config import (
get_skill_logger,
get_skill_log_file_path,
subprocess_env_with_trace,
)
from util.platforms import (
PLATFORMS,
PLATFORM_URLS,
_LOGIN_LOGGED_OUT_DOM_GENERIC_SELECTORS,
)
# 子进程入口脚本与本模块同目录(独立解释器执行,非 import
_SERVICE_DIR = os.path.dirname(os.path.abspath(__file__))
def _win_find_exe(candidates):
for p in candidates:
if p and os.path.isfile(p):
return p
return None
def resolve_chromium_channel():
"""
Playwright channel: 'chrome' | 'msedge' | None
Windows 优先 Chrome其次 Edge其它系统默认 chrome由 Playwright 解析 PATH
"""
if sys.platform != "win32":
return "chrome"
pf = os.environ.get("ProgramFiles", r"C:\Program Files")
pfx86 = os.environ.get("ProgramFiles(x86)", r"C:\Program Files (x86)")
local = os.environ.get("LocalAppData", "")
chrome = _win_find_exe(
[
os.path.join(pf, "Google", "Chrome", "Application", "chrome.exe"),
os.path.join(pfx86, "Google", "Chrome", "Application", "chrome.exe"),
os.path.join(local, "Google", "Chrome", "Application", "chrome.exe") if local else "",
]
)
if chrome:
return "chrome"
edge = _win_find_exe(
[
os.path.join(pfx86, "Microsoft", "Edge", "Application", "msedge.exe"),
os.path.join(pf, "Microsoft", "Edge", "Application", "msedge.exe"),
os.path.join(local, "Microsoft", "Edge", "Application", "msedge.exe") if local else "",
]
)
if edge:
return "msedge"
return None
def _print_browser_install_hint():
print("❌ 未检测到 Google Chrome 或 Microsoft Edge请先安装后再登录")
print(" • Chrome: https://www.google.com/chrome/")
print(" • Edge: https://www.microsoft.com/zh-cn/edge")
def _login_timeout_seconds():
try:
return max(60, int((os.getenv("JIANGCHANG_LOGIN_TIMEOUT_SECONDS") or "300").strip()))
except ValueError:
return 300
def _login_poll_interval_seconds():
"""轮询间隔,默认 1.5s。"""
try:
v = float((os.getenv("JIANGCHANG_LOGIN_POLL_INTERVAL_SECONDS") or "1.5").strip())
return max(0.5, min(v, 10.0))
except ValueError:
return 1.5
def _login_dom_grace_seconds() -> float:
"""goto 后等待再开始 DOM 判定,减轻跳转中途误判。默认 4sJIANGCHANG_LOGIN_DOM_GRACE_SECONDS。"""
try:
v = float((os.getenv("JIANGCHANG_LOGIN_DOM_GRACE_SECONDS") or "4").strip())
return max(0.0, min(v, 60.0))
except ValueError:
return 4.0
def _wait_login_timeout_seconds() -> int:
"""供 wait-login / llm 编排:默认 180 秒JIANGCHANG_WAIT_LOGIN_TIMEOUT_SECONDS。"""
try:
return max(30, min(600, int((os.getenv("JIANGCHANG_WAIT_LOGIN_TIMEOUT_SECONDS") or "180").strip())))
except ValueError:
return 180
def _login_out_bundle_for(platform_key: str) -> dict:
"""传给子进程anchor + 未登录可见的选择器列表。"""
spec = PLATFORMS.get(platform_key, {}) if platform_key else {}
anchor = (urlparse(PLATFORM_URLS.get(platform_key, "") or "").netloc or "").lower()
spec_lo_dom = [
str(s).strip()
for s in (spec.get("login_logged_out_selectors") or [])
if s is not None and str(s).strip()
]
if bool(spec.get("login_skip_generic_logged_out_dom")):
logged_out_dom_selectors = list(spec_lo_dom)
else:
logged_out_dom_selectors = list(_LOGIN_LOGGED_OUT_DOM_GENERIC_SELECTORS) + spec_lo_dom
return {
"logged_out_dom_selectors": logged_out_dom_selectors,
"anchor_host": anchor,
}
def _run_login_browser_session(
target: dict,
timeout_sec: int,
*,
verbose_ui: bool = True,
) -> tuple[bool, str]:
"""
启动 Playwright 登录检测子进程;**是否已登录以子进程 DOM 判定为准**。
成功后尽力 `mark_login_status` 供 list/排序展示,**跨技能编排请勿再依赖该字段**(可能与真实 Cookie 会话脱节)。
返回 (是否已登录成功, end_reason)end_reason 为 login_child 写入的 reason失败时可能为
timeout / user_closed / subprocess_error。
"""
log = get_skill_logger()
account_id = target.get("id")
channel = resolve_chromium_channel()
if not channel:
log.warning("login_aborted no_chromium_channel")
if verbose_ui:
_print_browser_install_hint()
return False, "no_channel"
try:
import playwright # noqa: F401
except ImportError:
log.error("login_aborted playwright_missing")
if verbose_ui:
print("ERROR:需要 playwrightpip install playwright && playwright install chromium")
return False, "playwright_missing"
profile_dir = (target.get("profile_dir") or "").strip()
if not profile_dir:
log.warning("login_aborted profile_dir_empty account_id=%s", account_id)
if verbose_ui:
print("ERROR:PROFILE_DIR_MISSING 库中 profile_dir 为空。")
return False, "profile_missing"
os.makedirs(profile_dir, exist_ok=True)
url = (target.get("url") or "").strip() or PLATFORM_URLS.get(
target["platform"], "https://www.google.com"
)
platform = (target.get("platform") or "").strip().lower()
poll_sec = _login_poll_interval_seconds()
dom_grace_sec = _login_dom_grace_seconds()
browser_name = "Google Chrome" if channel == "chrome" else "Microsoft Edge"
if verbose_ui:
print(f"正在为账号 [{target['name']}] 打开 {browser_name}")
print(f"访问地址:{url}")
print(
"请在窗口内完成登录。系统根据页面是否仍出现「登录」等未登录控件判断;"
"成功后自动关闭窗口并写入状态(无需手动关浏览器)。"
)
print(
f"页面加载后先等待约 {dom_grace_sec:g} 秒再开始检测(减轻跳转误判,可用 JIANGCHANG_LOGIN_DOM_GRACE_SECONDS 调整)。"
)
print(f"轮询间隔约 {poll_sec} 秒;全程最长 {timeout_sec} 秒。")
log_file = get_skill_log_file_path()
log.info(
"login_browser_start account_id=%s platform=%s channel=%s timeout_sec=%s poll_sec=%s "
"dom_grace_sec=%s profile_dir=%s start_url=%s log_file=%s",
account_id,
platform,
channel,
timeout_sec,
poll_sec,
dom_grace_sec,
profile_dir,
url,
log_file,
)
login_runner_path = os.path.join(_SERVICE_DIR, "login_child_runner.py")
cfg = {
"channel": channel,
"profile_dir": profile_dir,
"url": url,
"timeout_sec": timeout_sec,
"poll_interval": poll_sec,
"dom_grace_sec": dom_grace_sec,
"login_detect_bundle": _login_out_bundle_for(platform),
"log_file": log_file,
}
with tempfile.NamedTemporaryFile(
mode="w", suffix=".json", delete=False, encoding="utf-8"
) as rf:
result_path = rf.name
cfg["result_path"] = result_path
with tempfile.NamedTemporaryFile(
mode="w", suffix=".json", delete=False, encoding="utf-8"
) as jf:
json.dump(cfg, jf, ensure_ascii=False)
cfg_path = jf.name
proc_rc = None
try:
r = subprocess.run(
[sys.executable, login_runner_path, cfg_path],
timeout=timeout_sec + 180,
env=subprocess_env_with_trace(),
)
proc_rc = r.returncode
if proc_rc != 0:
if verbose_ui:
print("⚠️ 浏览器进程异常退出,将仅根据已写入的检测结果更新状态")
log.warning("login_subprocess_nonzero_return code=%s", proc_rc)
except subprocess.TimeoutExpired as ex:
if verbose_ui:
print("⚠️ 等待浏览器超时,将仅根据已写入的检测结果更新状态")
log.warning("login_subprocess_timeout err=%s", ex)
finally:
try:
os.unlink(cfg_path)
except OSError:
pass
interactive_ok = False
end_reason = "subprocess_error"
try:
with open(result_path, encoding="utf-8") as rf:
data = json.load(rf)
interactive_ok = bool(data.get("interactive_ok"))
end_reason = str(data.get("end_reason") or "").strip() or (
"login_ok" if interactive_ok else "timeout"
)
except Exception:
end_reason = "subprocess_error"
try:
os.unlink(result_path)
except OSError:
pass
time.sleep(0.5)
ok = interactive_ok
log.info(
"login_finished account_id=%s interactive_ok=%s end_reason=%s subprocess_rc=%s marking_db=%s",
account_id,
interactive_ok,
end_reason,
proc_rc,
ok,
)
mark_login_status(account_id, ok)
return ok, end_reason if not ok else "login_ok"
def cmd_login(account_id):
log = get_skill_logger()
log.info("login_command account_id=%r", account_id)
target = get_account_by_id(account_id)
if not target:
log.warning("login_aborted account_not_found account_id=%r", account_id)
print("ERROR:ACCOUNT_NOT_FOUND")
return
timeout_sec = _login_timeout_seconds()
ok, _end_reason = _run_login_browser_session(target, timeout_sec, verbose_ui=True)
log_file = get_skill_log_file_path()
if ok:
print("✅ 已判定登录成功,状态已写入数据库")
else:
log.warning(
"login_not_detected account_id=%s platform=%s see_log=%s",
target.get("id"),
(target.get("platform") or "").strip().lower(),
log_file,
)
print("⚠️ 未检测到有效登录,状态为未登录。请关闭其他占用该用户目录的浏览器后重试,或延长 JIANGCHANG_LOGIN_TIMEOUT_SECONDS 后再登录。")
print(f" 详细轮询日志见:{log_file}(可将 JIANGCHANG_LOG_LEVEL=DEBUG 打开更细粒度)")
def cmd_wait_login(account_id) -> int:
"""
跨技能编排:若未登录则打开浏览器并在限时内等待登录。
返回 0已登录原本已登录或本次登录成功1失败超时 / 用户关浏览器 / 其它)。
stdout 首行OK:WAIT_LOGIN 或 ERROR:WAIT_LOGIN_*。
"""
log = get_skill_logger()
log.info("wait_login_command account_id=%r", account_id)
target = get_account_by_id(account_id)
if not target:
log.warning("wait_login_aborted account_not_found account_id=%r", account_id)
print("ERROR:ACCOUNT_NOT_FOUND")
return 1
# 库内 login_status=1 时跳过开窗(仅性能提示;与真实 Cookie 可能不同步,此时应再执行 wait-login 覆盖)
if int(target.get("login_status") or 0) == 1:
print("OK:WAIT_LOGIN")
return 0
if not resolve_chromium_channel():
_print_browser_install_hint()
return 1
try:
import playwright # noqa: F401
except ImportError:
print("ERROR:需要 playwrightpip install playwright && playwright install chromium")
return 1
if not (target.get("profile_dir") or "").strip():
print("ERROR:PROFILE_DIR_MISSING 库中 profile_dir 为空。")
return 1
sec = _wait_login_timeout_seconds()
print(
f"⏳ 账号「{target.get('name', target['id'])}」尚未登录,将打开浏览器;请在 {sec} 秒内完成登录。"
"关闭浏览器将视为放弃。"
)
ok, end_reason = _run_login_browser_session(target, sec, verbose_ui=False)
if ok:
print("OK:WAIT_LOGIN")
return 0
if end_reason == "user_closed":
print("ERROR:WAIT_LOGIN_ABORTED 已关闭浏览器,未完成登录。")
return 1
if end_reason == "timeout":
print("ERROR:WAIT_LOGIN_TIMEOUT 限时内未完成登录。")
return 1
if end_reason == "playwright_missing":
print("ERROR:需要 playwrightpip install playwright && playwright install chromium")
return 1
if end_reason == "profile_missing":
print("ERROR:PROFILE_DIR_MISSING 库中 profile_dir 为空。")
return 1
if end_reason == "no_channel":
_print_browser_install_hint()
return 1
print(f"ERROR:WAIT_LOGIN_FAILED end_reason={end_reason}")
return 1
def cmd_open(account_id):
"""打开该账号的持久化浏览器,仅用于肉眼确认是否已登录;不写数据库。"""
get_skill_logger().info("open account_id=%r", account_id)
target = get_account_by_id(account_id)
if not target:
get_skill_logger().warning("open_not_found account_id=%r", account_id)
print("ERROR:ACCOUNT_NOT_FOUND")
return
channel = resolve_chromium_channel()
if not channel:
_print_browser_install_hint()
return
try:
import playwright # noqa: F401
except ImportError:
print("ERROR:需要 playwrightpip install playwright && playwright install chromium")
return
profile_dir = (target.get("profile_dir") or "").strip()
if not profile_dir:
print("ERROR:PROFILE_DIR_MISSING 库中 profile_dir 为空。")
return
os.makedirs(profile_dir, exist_ok=True)
url = (target.get("url") or "").strip() or PLATFORM_URLS.get(
target["platform"], "https://www.google.com"
)
browser_name = "Google Chrome" if channel == "chrome" else "Microsoft Edge"
print(f"正在打开 [{target['name']}] 的 {browser_name}(仅查看,不写入数据库)")
print(f"地址:{url}")
print("请在本窗口中自行确认登录态。关闭浏览器后命令结束。")
print("需要自动检测并写入数据库时请执行python main.py login <id>")
open_runner_path = os.path.join(_SERVICE_DIR, "open_child_runner.py")
cfg = {"channel": channel, "profile_dir": profile_dir, "url": url}
with tempfile.NamedTemporaryFile(
mode="w", suffix=".json", delete=False, encoding="utf-8"
) as jf:
json.dump(cfg, jf, ensure_ascii=False)
cfg_path = jf.name
try:
subprocess.run(
[sys.executable, open_runner_path, cfg_path],
env=subprocess_env_with_trace(),
)
finally:
try:
os.unlink(cfg_path)
except OSError:
pass