mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-05-11 13:07:36 +08:00
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
This commit is contained in:
@@ -20,6 +20,10 @@
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from unittest.mock import AsyncMock
|
||||
|
||||
import pytest
|
||||
|
||||
from tools import utils
|
||||
|
||||
|
||||
@@ -28,3 +32,18 @@ def test_convert_cookies():
|
||||
cookie_dict = utils.convert_str_cookie_to_dict(xhs_cookies)
|
||||
assert cookie_dict.get("webId") == "1190c4d3cxxxx125xxx"
|
||||
assert cookie_dict.get("a1") == "x000101360"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_browser_context_cookies_uses_url_filter():
|
||||
browser_context = AsyncMock()
|
||||
browser_context.cookies.return_value = [{"name": "sessionid", "value": "abc"}]
|
||||
|
||||
cookie_str, cookie_dict = await utils.convert_browser_context_cookies(
|
||||
browser_context,
|
||||
urls=["https://www.douyin.com"],
|
||||
)
|
||||
|
||||
browser_context.cookies.assert_awaited_once_with(urls=["https://www.douyin.com"])
|
||||
assert cookie_str == "sessionid=abc"
|
||||
assert cookie_dict == {"sessionid": "abc"}
|
||||
|
||||
Reference in New Issue
Block a user