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/tieba/client.py

@@ -54,6 +54,7 @@ class BaiduTieBaClient(AbstractApiClient):
             "Cookie": "",
         }
         self._host = "https://tieba.baidu.com"
+        self.cookie_urls = [self._host]
         self._page_extractor = TieBaExtractor()
         self.default_ip_proxy = default_ip_proxy
         self.playwright_page = playwright_page  # Playwright page object
@@ -209,7 +210,10 @@ class BaiduTieBaClient(AbstractApiClient):
 
         try:
             # Get cookies from browser and check key login cookies
-            _, cookie_dict = utils.convert_cookies(await browser_context.cookies())
+            _, cookie_dict = await utils.convert_browser_context_cookies(
+                browser_context,
+                urls=self.cookie_urls,
+            )
 
             # Baidu Tieba login identifiers: STOKEN or PTOKEN
             stoken = cookie_dict.get("STOKEN")
@@ -227,7 +231,7 @@ class BaiduTieBaClient(AbstractApiClient):
             utils.logger.error(f"[BaiduTieBaClient.pong] Check login state failed: {e}, assume not logged in")
             return False
 
-    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:
@@ -236,7 +240,10 @@ class BaiduTieBaClient(AbstractApiClient):
         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
         utils.logger.info("[BaiduTieBaClient.update_cookies] Cookie has been updated")
 

media_platform/tieba/core.py

@@ -54,6 +54,7 @@ class TieBaCrawler(AbstractCrawler):
 
     def __init__(self) -> None:
         self.index_url = "https://tieba.baidu.com"
+        self.cookie_urls = [self.index_url]
         self.user_agent = utils.get_user_agent()
         self._page_extractor = TieBaExtractor()
         self.cdp_manager = None
@@ -123,7 +124,10 @@ class TieBaCrawler(AbstractCrawler):
                     cookie_str=config.COOKIES,
                 )
                 await login_obj.begin()
-                await self.tieba_client.update_cookies(browser_context=self.browser_context)
+                await self.tieba_client.update_cookies(
+                    browser_context=self.browser_context,
+                    urls=self.cookie_urls,
+                )
 
             crawler_type_var.set(config.CRAWLER_TYPE)
             if config.CRAWLER_TYPE == "search":
@@ -560,7 +564,10 @@ class TieBaCrawler(AbstractCrawler):
         user_agent = await self.context_page.evaluate("() => navigator.userAgent")
         utils.logger.info(f"[TieBaCrawler.create_tieba_client] Extracted User-Agent from browser: {user_agent}")
 
-        cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies())
+        cookie_str, cookie_dict = await utils.convert_browser_context_cookies(
+            self.browser_context,
+            urls=self.cookie_urls,
+        )
 
         # Build complete browser request headers, simulating real browser behavior
         tieba_client = BaiduTieBaClient(