mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-06-09 03:17:25 +08:00
feat: ip proxy expired check
This commit is contained in:
@@ -63,12 +63,13 @@ class WeiboCrawler(AbstractCrawler):
|
||||
self.user_agent = utils.get_user_agent()
|
||||
self.mobile_user_agent = utils.get_mobile_user_agent()
|
||||
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):
|
||||
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:
|
||||
@@ -334,6 +335,7 @@ class WeiboCrawler(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 weibo_client_obj
|
||||
|
||||
|
||||
Reference in New Issue
Block a user