237899745/zsglpt
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

replace screenshot pipeline and update admin

Browse Source
This commit is contained in:
yuyx
2025-12-31 16:50:35 +08:00
parent 2d98ab66a3
commit 41ead4bead
25 changed files with 443 additions and 2250 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
services/browser_manager.py
View File

@@ -1,112 +0,0 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from __future__ import annotations
import threading
import time
from typing import Optional
from app_logger import get_logger
from browser_installer import check_and_install_browser
from playwright_automation import PlaywrightBrowserManager
logger = get_logger("browser_manager")
_browser_manager: Optional[PlaywrightBrowserManager] = None
_lock = threading.Lock()
_cond = threading.Condition(_lock)
_init_in_progress = False
_init_error: Optional[str] = None
_init_thread: Optional[threading.Thread] = None
def get_browser_manager() -> Optional[PlaywrightBrowserManager]:
return _browser_manager
def is_browser_manager_ready() -> bool:
return _browser_manager is not None
def get_browser_manager_init_error() -> Optional[str]:
return _init_error
def init_browser_manager(*, block: bool = True, timeout: Optional[float] = None) -> bool:
global _browser_manager
global _init_in_progress, _init_error
deadline = time.monotonic() + float(timeout) if timeout is not None else None
with _cond:
if _browser_manager is not None:
return True
if _init_in_progress:
if not block:
return False
while _init_in_progress:
if deadline is None:
_cond.wait(timeout=0.5)
continue
remaining = deadline - time.monotonic()
if remaining <= 0:
break
_cond.wait(timeout=min(0.5, remaining))
return _browser_manager is not None
_init_in_progress = True
_init_error = None
ok = False
error: Optional[str] = None
manager: Optional[PlaywrightBrowserManager] = None
try:
logger.info("正在初始化Playwright浏览器管理器...")
if not check_and_install_browser(log_callback=lambda msg, account_id=None: logger.info(str(msg))):
error = "浏览器环境检查失败"
logger.error("浏览器环境检查失败！")
ok = False
else:
manager = PlaywrightBrowserManager(
headless=True,
log_callback=lambda msg, account_id=None: logger.info(str(msg)),
)
ok = True
logger.info("Playwright浏览器管理器创建成功！")
except Exception as exc:
error = f"{type(exc).__name__}: {exc}"
logger.exception("初始化Playwright浏览器管理器时发生异常")
ok = False
with _cond:
if ok and manager is not None:
_browser_manager = manager
else:
_init_error = error or "初始化失败"
_init_in_progress = False
_cond.notify_all()
return ok
def init_browser_manager_async() -> None:
"""异步初始化浏览器环境，避免阻塞 Web 请求/服务启动。"""
global _init_thread
def _worker():
try:
init_browser_manager(block=True)
except Exception:
logger.exception("异步初始化浏览器管理器失败")
with _cond:
if _browser_manager is not None:
return
if _init_thread and _init_thread.is_alive():
return
if _init_in_progress:
return
_init_thread = threading.Thread(target=_worker, daemon=True, name="browser-manager-init")
_init_thread.start()

218
services/screenshots.py
View File

@@ -3,15 +3,16 @@
from __future__ import annotations
import os
import shutil
import subprocess
import time
import database
import email_service
from api_browser import APIBrowser, get_cookie_jar_path, is_cookie_jar_fresh
from app_config import get_config
from app_logger import get_logger
from browser_pool_worker import get_browser_worker_pool
from playwright_automation import PlaywrightAutomation
from services.browser_manager import get_browser_manager
from services.client_log import log_to_client
from services.runtime import get_socketio
from services.state import safe_get_account, safe_remove_task_status, safe_update_task_status
@@ -24,6 +25,93 @@ config = get_config()
SCREENSHOTS_DIR = config.SCREENSHOTS_DIR
os.makedirs(SCREENSHOTS_DIR, exist_ok=True)
_WKHTMLTOIMAGE_TIMEOUT_SECONDS = int(os.environ.get("WKHTMLTOIMAGE_TIMEOUT_SECONDS", "60"))
_WKHTMLTOIMAGE_JS_DELAY_MS = int(os.environ.get("WKHTMLTOIMAGE_JS_DELAY_MS", "3000"))
_WKHTMLTOIMAGE_WIDTH = int(os.environ.get("WKHTMLTOIMAGE_WIDTH", "1920"))
_WKHTMLTOIMAGE_QUALITY = int(os.environ.get("WKHTMLTOIMAGE_QUALITY", "95"))
_WKHTMLTOIMAGE_UA = os.environ.get(
"WKHTMLTOIMAGE_USER_AGENT",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
)
def _resolve_wkhtmltoimage_path() -> str | None:
return os.environ.get("WKHTMLTOIMAGE_PATH") or shutil.which("wkhtmltoimage")
def _ensure_login_cookies(account, proxy_config, log_callback) -> bool:
"""确保有可用的登录 cookies（通过 API 登录刷新）"""
try:
with APIBrowser(log_callback=log_callback, proxy_config=proxy_config) as api_browser:
if not api_browser.login(account.username, account.password):
return False
return api_browser.save_cookies_for_screenshot(account.username)
except Exception:
return False
def take_screenshot_wkhtmltoimage(
url: str,
output_path: str,
cookies_path: str | None = None,
proxy_server: str | None = None,
log_callback=None,
) -> bool:
wkhtmltoimage_path = _resolve_wkhtmltoimage_path()
if not wkhtmltoimage_path:
if log_callback:
log_callback("wkhtmltoimage 未安装或不在 PATH 中")
return False
ext = os.path.splitext(output_path)[1].lower()
image_format = "jpg" if ext in (".jpg", ".jpeg") else "png"
cmd = [
wkhtmltoimage_path,
"--format",
image_format,
"--width",
str(_WKHTMLTOIMAGE_WIDTH),
"--disable-smart-width",
"--javascript-delay",
str(_WKHTMLTOIMAGE_JS_DELAY_MS),
"--load-error-handling",
"ignore",
"--enable-local-file-access",
"--encoding",
"utf-8",
"--user-agent",
_WKHTMLTOIMAGE_UA,
]
if image_format in ("jpg", "jpeg"):
cmd.extend(["--quality", str(_WKHTMLTOIMAGE_QUALITY)])
if cookies_path:
cmd.extend(["--cookie-jar", cookies_path])
if proxy_server:
cmd.extend(["--proxy", proxy_server])
cmd.extend([url, output_path])
try:
result = subprocess.run(cmd, capture_output=True, text=True, timeout=_WKHTMLTOIMAGE_TIMEOUT_SECONDS)
if result.returncode != 0:
if log_callback:
err_msg = (result.stderr or result.stdout or "").strip()
log_callback(f"wkhtmltoimage 截图失败: {err_msg[:200]}")
return False
return True
except subprocess.TimeoutExpired:
if log_callback:
log_callback("wkhtmltoimage 截图超时")
return False
except Exception as e:
if log_callback:
log_callback(f"wkhtmltoimage 截图异常: {e}")
return False
def _emit(event: str, data: object, *, room: str | None = None) -> None:
try:
@@ -42,7 +130,7 @@ def take_screenshot_for_account(
task_start_time=None,
browse_result=None,
):
"""为账号任务完成后截图（使用工作线程池，真正的浏览器复用）"""
"""为账号任务完成后截图（使用截图线程池并发执行）"""
account = safe_get_account(user_id, account_id)
if not account:
return
@@ -63,9 +151,11 @@ def take_screenshot_for_account(
_emit("account_update", acc.to_dict(), room=f"user_{user_id}")
max_retries = 3
proxy_config = account.proxy_config if hasattr(account, "proxy_config") else None
proxy_server = proxy_config.get("server") if proxy_config else None
cookie_path = get_cookie_jar_path(account.username)
for attempt in range(1, max_retries + 1):
automation = None
try:
safe_update_task_status(
account_id,
@@ -75,100 +165,39 @@ def take_screenshot_for_account(
if attempt > 1:
log_to_client(f"🔄 第 {attempt} 次截图尝试...", user_id, account_id)
worker_id = browser_instance.get("worker_id", "?") if isinstance(browser_instance, dict) else "?"
use_count = browser_instance.get("use_count", 0) if isinstance(browser_instance, dict) else 0
log_to_client(
f"使用Worker-{browser_instance['worker_id']}的浏览器（已使用{browser_instance['use_count']}次）",
f"使用Worker-{worker_id}执行截图（已执行{use_count}次）",
user_id,
account_id,
)
proxy_config = account.proxy_config if hasattr(account, "proxy_config") else None
automation = PlaywrightAutomation(get_browser_manager(), account_id, proxy_config=proxy_config)
automation.playwright = browser_instance["playwright"]
automation.browser = browser_instance["browser"]
def custom_log(message: str):
log_to_client(message, user_id, account_id)
automation.log = custom_log
log_to_client("登录中...", user_id, account_id)
login_result = automation.quick_login(account.username, account.password, account.remember)
if not login_result["success"]:
error_message = login_result.get("message", "截图登录失败")
log_to_client(f"截图登录失败: {error_message}", user_id, account_id)
if attempt < max_retries:
log_to_client("将重试...", user_id, account_id)
time.sleep(2)
continue
log_to_client("❌ 截图失败: 登录失败", user_id, account_id)
return {"success": False, "error": "登录失败"}
if not is_cookie_jar_fresh(cookie_path) or attempt > 1:
log_to_client("正在刷新登录态...", user_id, account_id)
if not _ensure_login_cookies(account, proxy_config, custom_log):
log_to_client("截图登录失败", user_id, account_id)
if attempt < max_retries:
log_to_client("将重试...", user_id, account_id)
time.sleep(2)
continue
log_to_client("❌ 截图失败: 登录失败", user_id, account_id)
return {"success": False, "error": "登录失败"}
log_to_client(f"导航到 '{browse_type}' 页面...", user_id, account_id)
# 截图场景：优先用 bz 参数直达页面（更稳定，避免页面按钮点击失败导致截图跑偏）
navigated = False
try:
from urllib.parse import urlsplit
from urllib.parse import urlsplit
parsed = urlsplit(config.ZSGL_LOGIN_URL)
base = f"{parsed.scheme}://{parsed.netloc}"
if "注册前" in str(browse_type):
bz = 0
else:
bz = 2 # 应读
target_url = f"{base}/admin/center.aspx?bz={bz}"
# 目标：保留外层框架（左侧菜单/顶部栏），仅在 mainframe 内部导航到目标内容页
iframe = None
try:
iframe = automation.get_iframe_safe(retry=True, max_retries=5)
except Exception:
iframe = None
if iframe:
iframe.goto(target_url, timeout=60000)
current_url = getattr(iframe, "url", "") or ""
if "center.aspx" not in current_url:
raise RuntimeError(f"unexpected_iframe_url:{current_url}")
try:
iframe.wait_for_load_state("networkidle", timeout=10000)
except Exception:
pass
try:
iframe.wait_for_selector("table.ltable", timeout=5000)
except Exception:
pass
else:
# 兜底：若获取不到 iframe，则退回到主页面直达
automation.main_page.goto(target_url, timeout=60000)
current_url = getattr(automation.main_page, "url", "") or ""
if "center.aspx" not in current_url:
raise RuntimeError(f"unexpected_url:{current_url}")
try:
automation.main_page.wait_for_load_state("networkidle", timeout=10000)
except Exception:
pass
try:
automation.main_page.wait_for_selector("table.ltable", timeout=5000)
except Exception:
pass
navigated = True
except Exception as nav_error:
log_to_client(f"直达页面失败，将尝试按钮切换: {str(nav_error)[:120]}", user_id, account_id)
# 兼容兜底：若直达失败，则回退到原有按钮切换方式
if not navigated:
result = automation.browse_content(
navigate_only=True,
browse_type=browse_type,
auto_next_page=False,
auto_view_attachments=False,
interval=0,
should_stop_callback=None,
)
if not result.success and result.error_message:
log_to_client(f"导航警告: {result.error_message}", user_id, account_id)
time.sleep(2)
parsed = urlsplit(config.ZSGL_LOGIN_URL)
base = f"{parsed.scheme}://{parsed.netloc}"
if "注册前" in str(browse_type):
bz = 0
else:
bz = 2 # 应读
target_url = f"{base}/admin/center.aspx?bz={bz}"
timestamp = get_beijing_now().strftime("%Y%m%d_%H%M%S")
@@ -178,7 +207,13 @@ def take_screenshot_for_account(
screenshot_filename = f"{username_prefix}_{login_account}_{browse_type}_{timestamp}.jpg"
screenshot_path = os.path.join(SCREENSHOTS_DIR, screenshot_filename)
if automation.take_screenshot(screenshot_path):
if take_screenshot_wkhtmltoimage(
target_url,
screenshot_path,
cookies_path=cookie_path if is_cookie_jar_fresh(cookie_path) else None,
proxy_server=proxy_server,
log_callback=custom_log,
):
if os.path.exists(screenshot_path) and os.path.getsize(screenshot_path) > 1000:
log_to_client(f"✓ 截图成功: {screenshot_filename}", user_id, account_id)
return {"success": True, "filename": screenshot_filename}
@@ -197,15 +232,6 @@ def take_screenshot_for_account(
if attempt < max_retries:
log_to_client("将重试...", user_id, account_id)
time.sleep(2)
finally:
if automation:
try:
if automation.context:
automation.context.close()
automation.context = None
automation.page = None
except Exception as e:
logger.debug(f"关闭context时出错: {e}")
return {"success": False, "error": "截图失败，已重试3次"}

2
services/tasks.py
View File

@@ -574,7 +574,7 @@ def run_task(user_id, account_id, browse_type, enable_screenshot=True, source="m
with APIBrowser(log_callback=custom_log, proxy_config=proxy_config) as api_browser:
if api_browser.login(account.username, account.password):
log_to_client("✓ 登录成功！", user_id, account_id)
api_browser.save_cookies_for_playwright(account.username)
api_browser.save_cookies_for_screenshot(account.username)
database.reset_account_login_status(account_id)
if not account.remark: