fix: 修复代理Bug

docs/代理使用.md

@@ -1,5 +1,6 @@
 ## 代理 IP 使用说明
 > 还是得跟大家再次强调下，不要对一些自媒体平台进行大规模爬虫或其他非法行为，要踩缝纫机的哦🤣  
+> 另外如果要是用代理功能，请安装Redis并设置一个密码, 从下面的流程图讲解了redis在这个缓存功能中起到的作用
 ### 简易的流程图
 
 ![代理 IP 使用流程图](../static/images/代理IP%20流程图.drawio.png)

media_platform/bilibili/core.py

@@ -225,7 +225,7 @@ class BilibiliCrawler(AbstractCrawler):
             "password": ip_proxy_info.password,
         }
         httpx_proxy = {
-            f"{ip_proxy_info.protocol}{ip_proxy_info.ip}": f"{ip_proxy_info.protocol}{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
+            f"{ip_proxy_info.protocol}": f"http://{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
         }
         return playwright_proxy, httpx_proxy
 

media_platform/douyin/core.py

@@ -160,7 +160,7 @@ class DouYinCrawler(AbstractCrawler):
             "password": ip_proxy_info.password,
         }
         httpx_proxy = {
-            f"{ip_proxy_info.protocol}{ip_proxy_info.ip}": f"{ip_proxy_info.protocol}{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
+            f"{ip_proxy_info.protocol}": f"http://{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
         }
         return playwright_proxy, httpx_proxy
 

media_platform/kuaishou/core.py

@@ -191,7 +191,7 @@ class KuaishouCrawler(AbstractCrawler):
             "password": ip_proxy_info.password,
         }
         httpx_proxy = {
-            f"{ip_proxy_info.protocol}{ip_proxy_info.ip}": f"{ip_proxy_info.protocol}{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
+            f"{ip_proxy_info.protocol}": f"http://{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
         }
         return playwright_proxy, httpx_proxy
 

media_platform/weibo/core.py

@@ -243,7 +243,7 @@ class WeiboCrawler(AbstractCrawler):
             "password": ip_proxy_info.password,
         }
         httpx_proxy = {
-            f"{ip_proxy_info.protocol}{ip_proxy_info.ip}": f"{ip_proxy_info.protocol}{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
+            f"{ip_proxy_info.protocol}": f"http://{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
         }
         return playwright_proxy, httpx_proxy
 

media_platform/xhs/core.py

@@ -185,7 +185,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
             "password": ip_proxy_info.password,
         }
         httpx_proxy = {
-            f"{ip_proxy_info.protocol}{ip_proxy_info.ip}":f"{ip_proxy_info.protocol}{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
+            f"{ip_proxy_info.protocol}": f"http://{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
         }
         return playwright_proxy, httpx_proxy
 

proxy/proxy_ip_pool.py

@@ -38,12 +38,10 @@ class ProxyIpPool:
 
         utils.logger.info(f"[ProxyIpPool.is_valid_proxy] testing {proxy.ip} is it valid ")
         try:
-            httpx_proxy = f"{proxy.protocol}{proxy.ip}:{proxy.port}"
-            proxy_auth = httpx.BasicAuth(proxy.user, proxy.password)
-            proxies = {
-                f"{proxy.protocol}{proxy.ip}": httpx_proxy
+            httpx_proxy = {
+                f"{proxy.protocol}": f"http://{proxy.user}:{proxy.password}@{proxy.ip}:{proxy.port}"
             }
-            async with httpx.AsyncClient(proxies=proxies, auth=proxy_auth) as client:
+            async with httpx.AsyncClient(proxies=httpx_proxy) as client:
                 response = await client.get(self.valid_ip_url)
             if response.status_code == 200:
                 return True

requirements.txt

@@ -5,7 +5,7 @@ tenacity==8.2.2
 tornado==6.3.2
 PyExecJS==1.5.1
 opencv-python==4.7.0.72
-tortoise-orm
+tortoise-orm==0.20.0
 aiomysql==0.2.0
 aerich==0.7.2
 numpy~=1.24.4