From d6fb255bdff66cd1cb99ecee4b4822ac21a43432 Mon Sep 17 00:00:00 2001
From: Relakkes <relakkes@gmail.com>
Date: Mon, 2 Sep 2024 21:45:12 +0800
Subject: [PATCH] fix: xhs note detail error

---
 base/base_crawler.py            | 14 ++++++++++++++
 main.py                         |  1 +
 media_platform/bilibili/core.py | 21 ++++++++++++++++++---
 media_platform/xhs/core.py      |  2 +-
 4 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/base/base_crawler.py b/base/base_crawler.py
index 6c78492..4951e2e 100644
--- a/base/base_crawler.py
+++ b/base/base_crawler.py
@@ -7,15 +7,29 @@ from playwright.async_api import BrowserContext, BrowserType
 class AbstractCrawler(ABC):
     @abstractmethod
     async def start(self):
+        """
+        start crawler
+        """
         pass
 
     @abstractmethod
     async def search(self):
+        """
+        search
+        """
         pass
 
     @abstractmethod
     async def launch_browser(self, chromium: BrowserType, playwright_proxy: Optional[Dict], user_agent: Optional[str],
                              headless: bool = True) -> BrowserContext:
+        """
+        launch browser
+        :param chromium: chromium browser
+        :param playwright_proxy: playwright proxy
+        :param user_agent: user agent
+        :param headless: headless mode
+        :return: browser context
+        """
         pass
 
 
diff --git a/main.py b/main.py
index e051b5e..15aa36d 100644
--- a/main.py
+++ b/main.py
@@ -45,6 +45,7 @@ async def main():
     if config.SAVE_DATA_OPTION == "db":
         await db.close()
 
+    
 
 if __name__ == '__main__':
     try:
diff --git a/media_platform/bilibili/core.py b/media_platform/bilibili/core.py
index 334a487..d26bd92 100644
--- a/media_platform/bilibili/core.py
+++ b/media_platform/bilibili/core.py
@@ -262,7 +262,11 @@ class BilibiliCrawler(AbstractCrawler):
                 return None
 
     async def create_bilibili_client(self, httpx_proxy: Optional[str]) -> BilibiliClient:
-        """Create xhs client"""
+        """
+        create bilibili client
+        :param httpx_proxy: httpx proxy
+        :return: bilibili client
+        """
         utils.logger.info(
             "[BilibiliCrawler.create_bilibili_client] Begin create bilibili API client ...")
         cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies())
@@ -282,7 +286,11 @@ class BilibiliCrawler(AbstractCrawler):
 
     @staticmethod
     def format_proxy_info(ip_proxy_info: IpInfoModel) -> Tuple[Optional[Dict], Optional[Dict]]:
-        """format proxy info for playwright and httpx"""
+        """
+        format proxy info for playwright and httpx
+        :param ip_proxy_info: ip proxy info
+        :return: playwright proxy, httpx proxy
+        """
         playwright_proxy = {
             "server": f"{ip_proxy_info.protocol}{ip_proxy_info.ip}:{ip_proxy_info.port}",
             "username": ip_proxy_info.user,
@@ -300,7 +308,14 @@ class BilibiliCrawler(AbstractCrawler):
             user_agent: Optional[str],
             headless: bool = True
     ) -> BrowserContext:
-        """Launch browser and create browser context"""
+        """ 
+        launch browser and create browser context
+        :param chromium: chromium browser
+        :param playwright_proxy: playwright proxy
+        :param user_agent: user agent
+        :param headless: headless mode
+        :return: browser context
+        """
         utils.logger.info(
             "[BilibiliCrawler.launch_browser] Begin create browser context ...")
         if config.SAVE_LOGIN_STATE:
diff --git a/media_platform/xhs/core.py b/media_platform/xhs/core.py
index 68e55b8..3334f06 100644
--- a/media_platform/xhs/core.py
+++ b/media_platform/xhs/core.py
@@ -220,7 +220,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
         """Get note detail"""
         async with semaphore:
             try:
-                note_detail: Dict = await self.xhs_client.get_note_by_id(note_id, xsec_source, xsec_token)
+                note_detail: Dict = await self.xhs_client.get_note_by_id_from_html(note_id)
                 if not note_detail:
                     utils.logger.error(
                         f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error, note_id: {note_id}")