fix: 避免复用浏览器时跨域 Cookie 过长导致请求失败

连接已有 Chrome 会把整个浏览器上下文的 cookie 带入平台 client。
除 xhs 外，多数平台仍直接读取全量 cookies，导致请求头过长并放大跨域污染。
本次将各平台的 cookie 读取统一收口到平台域名，并补上基础回归测试。

Constraint: 必须继续复用用户真实浏览器里的平台登录态
Rejected: 仅修复 xhs | 其他平台在连接已有浏览器时仍会携带超长 Cookie
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: 后续新增平台或调整 update_cookies 和 create client 流程时，只按平台域名读取 cookies
Tested: uv run pytest test/test_utils.py; python3 -m compileall tools/crawler_util.py media_platform/douyin/core.py media_platform/douyin/client.py media_platform/kuaishou/core.py media_platform/kuaishou/client.py media_platform/bilibili/core.py media_platform/bilibili/client.py media_platform/zhihu/core.py media_platform/zhihu/client.py media_platform/tieba/core.py media_platform/tieba/client.py media_platform/xhs/core.py media_platform/xhs/client.py media_platform/weibo/core.py media_platform/weibo/client.py test/test_utils.py
Not-tested: 各平台在真实 CDP 浏览器连接下的端到端抓取流程

media_platform/xhs/client.py

@@ -63,6 +63,7 @@ class XiaoHongShuClient(AbstractApiClient, ProxyRefreshMixin):
         else:
             self._host = "https://edith.xiaohongshu.com"
             self._domain = "https://www.xiaohongshu.com"
+        self.cookie_urls = [self._domain]
         self.IP_ERROR_STR = "Network connection error, please check network settings or restart"
         self.IP_ERROR_CODE = 300012
         self.NOTE_NOT_FOUND_CODE = -510000
@@ -260,7 +261,7 @@ class XiaoHongShuClient(AbstractApiClient, ProxyRefreshMixin):
         utils.logger.info(f"[XiaoHongShuClient.pong] Login state result: {ping_flag}")
         return ping_flag
 
-    async def update_cookies(self, browser_context: BrowserContext):
+    async def update_cookies(self, browser_context: BrowserContext, urls: Optional[list[str]] = None):
         """
         Update cookies method provided by API client, usually called after successful login
         Args:
@@ -269,7 +270,10 @@ class XiaoHongShuClient(AbstractApiClient, ProxyRefreshMixin):
         Returns:
 
         """
-        cookie_str, cookie_dict = utils.convert_cookies(await browser_context.cookies())
+        cookie_str, cookie_dict = await utils.convert_browser_context_cookies(
+            browser_context,
+            urls=urls or self.cookie_urls,
+        )
         self.headers["Cookie"] = cookie_str
         self.cookie_dict = cookie_dict
 

media_platform/xhs/core.py

@@ -56,6 +56,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
 
     def __init__(self) -> None:
         self.index_url = "https://www.rednote.com" if config.XHS_INTERNATIONAL else "https://www.xiaohongshu.com"
+        self.cookie_urls = [self.index_url]
         # self.user_agent = utils.get_user_agent()
         self.user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
         self.cdp_manager = None
@@ -105,7 +106,10 @@ class XiaoHongShuCrawler(AbstractCrawler):
                     cookie_str=config.COOKIES,
                 )
                 await login_obj.begin()
-                await self.xhs_client.update_cookies(browser_context=self.browser_context)
+                await self.xhs_client.update_cookies(
+                    browser_context=self.browser_context,
+                    urls=self.cookie_urls,
+                )
 
             crawler_type_var.set(config.CRAWLER_TYPE)
             if config.CRAWLER_TYPE == "search":
@@ -356,8 +360,9 @@ class XiaoHongShuCrawler(AbstractCrawler):
     async def create_xhs_client(self, httpx_proxy: Optional[str]) -> XiaoHongShuClient:
         """Create Xiaohongshu client"""
         utils.logger.info("[XiaoHongShuCrawler.create_xhs_client] Begin create Xiaohongshu API client ...")
-        cookie_str, cookie_dict = utils.convert_cookies(
-            await self.browser_context.cookies(self.index_url)
+        cookie_str, cookie_dict = await utils.convert_browser_context_cookies(
+            self.browser_context,
+            urls=self.cookie_urls,
         )
         xhs_client_obj = XiaoHongShuClient(
             proxy=httpx_proxy,