fix: make SSL verification opt-in via config, extend fix to all platforms

- Add DISABLE_SSL_VERIFY = False to base_config.py (default: verification on)
- Add tools/httpx_util.py with make_async_client() factory that reads the config
- Replace all httpx.AsyncClient() call sites across all platforms (bilibili,
  weibo, zhihu, xhs, douyin, kuaishou) and crawler_util with make_async_client()
- Extends SSL fix to previously missed platforms: xhs, douyin, kuaishou

Users running behind an intercepting proxy can set DISABLE_SSL_VERIFY = True
in config/base_config.py. All other users retain certificate verification.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Wei Liu
2026-03-18 12:31:49 +13:00
parent eb45a6367f
commit 125e02a4b9
9 changed files with 41 additions and 15 deletions

View File

@@ -29,6 +29,7 @@ from urllib.parse import urlencode
import httpx
from playwright.async_api import BrowserContext, Page
from tools.httpx_util import make_async_client
import config
from base.base_crawler import AbstractApiClient
@@ -68,7 +69,7 @@ class BilibiliClient(AbstractApiClient, ProxyRefreshMixin):
# Check if proxy has expired before each request
await self._refresh_proxy_if_expired()
async with httpx.AsyncClient(proxy=self.proxy, verify=False) as client:
async with make_async_client(proxy=self.proxy) as client:
response = await client.request(method, url, timeout=self.timeout, **kwargs)
try:
data: Dict = response.json()
@@ -222,7 +223,7 @@ class BilibiliClient(AbstractApiClient, ProxyRefreshMixin):
async def get_video_media(self, url: str) -> Union[bytes, None]:
# Follow CDN 302 redirects and treat any 2xx as success (some endpoints return 206)
async with httpx.AsyncClient(proxy=self.proxy, follow_redirects=True, verify=False) as client:
async with make_async_client(proxy=self.proxy, follow_redirects=True) as client:
try:
response = await client.request("GET", url, timeout=self.timeout, headers=self.headers)
response.raise_for_status()