feat(browser): migrate to CloakBrowser for browser emulation and streamline dependency management

- Replace Playwright-based browser emulation with CloakBrowser as default
- Update config to support CloakBrowser options and humanization presets
- Refactor browser helper to use CloakBrowser context and remove cf_clearance dependency
- Update Dockerfile, entrypoint, and update scripts to install CloakBrowser runtime
- Ensure CloakBrowser kernel is pre-installed during local setup and dependency updates
- Add tests for CloakBrowser integration and legacy compatibility
This commit is contained in:
jxxghp
2026-05-16 20:51:38 +08:00
parent 9069dccb2a
commit 0ee9fec1d2
10 changed files with 293 additions and 140 deletions

View File

@@ -198,68 +198,62 @@ class BrowseWebpageTool(MoviePilotTool):
cookies: Optional[str],
user_agent: Optional[str],
) -> str:
"""在同步上下文中执行 Playwright 浏览器操作"""
from playwright.sync_api import sync_playwright
"""在同步上下文中执行 CloakBrowser 浏览器操作"""
from cloakbrowser import launch_context
try:
with sync_playwright() as playwright:
browser = None
context = None
page = None
try:
# 启动浏览器
browser_type = settings.PLAYWRIGHT_BROWSER_TYPE or "chromium"
browser = playwright[browser_type].launch(headless=True)
# 创建上下文
context_kwargs = {}
if user_agent:
context_kwargs["user_agent"] = user_agent
# 设置视口大小
context_kwargs["viewport"] = {
context = None
page = None
try:
context_kwargs = {
"viewport": {
"width": SCREENSHOT_MAX_WIDTH,
"height": SCREENSHOT_MAX_HEIGHT,
}
}
if user_agent:
context_kwargs["user_agent"] = user_agent
context = browser.new_context(**context_kwargs)
page = context.new_page()
page.set_default_timeout(timeout * 1000)
context = launch_context(
headless=True,
humanize=settings.CLOAKBROWSER_HUMANIZE,
human_preset=settings.CLOAKBROWSER_HUMAN_PRESET,
**context_kwargs,
)
page = context.new_page()
page.set_default_timeout(timeout * 1000)
# 设置 cookies
if cookies:
page.set_extra_http_headers({"cookie": cookies})
# 设置 cookies
if cookies:
page.set_extra_http_headers({"cookie": cookies})
# 对于非 goto 操作,如果提供了 url 先导航
if url and browser_action != BrowserAction.GOTO:
page.goto(
url, wait_until="domcontentloaded", timeout=timeout * 1000
)
page.wait_for_load_state("networkidle", timeout=timeout * 1000)
# 对于非 goto 操作,如果提供了 url 先导航
if url and browser_action != BrowserAction.GOTO:
page.goto(url, wait_until="domcontentloaded", timeout=timeout * 1000)
page.wait_for_load_state("networkidle", timeout=timeout * 1000)
# 执行具体操作
result = self._do_action(
page,
browser_action,
url,
selector,
value,
script,
content_type,
timeout,
)
return result
# 执行具体操作
result = self._do_action(
page,
browser_action,
url,
selector,
value,
script,
content_type,
timeout,
)
return result
finally:
if page:
page.close()
if context:
context.close()
if browser:
browser.close()
finally:
if page:
page.close()
if context:
context.close()
except Exception as e:
logger.error(f"Playwright 执行失败: {e}", exc_info=True)
return f"Playwright 执行失败: {str(e)}"
logger.error(f"CloakBrowser 执行失败: {e}", exc_info=True)
return f"CloakBrowser 执行失败: {str(e)}"
def _do_action(
self,