jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-09 03:17:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: ip proxy expired check

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-11-25 12:39:10 +08:00
parent 1da347cbf8
commit 6eef02d08c
16 changed files with 241 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
media_platform/xhs/core.py
View File

@@ -60,12 +60,13 @@ class XiaoHongShuCrawler(AbstractCrawler):
# 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
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self) -> None:
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
self.ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
@@ -380,6 +381,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return xhs_client_obj