feat: 轻量化支持爬取小红书二级评论

media_platform/xhs/client.py

@@ -7,6 +7,7 @@ from urllib.parse import urlencode
 import httpx
 from playwright.async_api import BrowserContext, Page
 
+import config
 from base.base_crawler import AbstactApiClient
 from tools import utils
 
@@ -274,39 +275,53 @@ class XiaoHongShuClient(AbstactApiClient):
                 await callback(note_id, comments)
             await asyncio.sleep(crawl_interval)
             result.extend(comments)
+            sub_comments = await self.get_comments_all_sub_comments(comments, crawl_interval, callback)
+            result.extend(sub_comments)
         return result
     
-    async def get_comment_all_sub_comments(self, note_id: str, root_comment_id: str, sub_comment_cursor: str, 
-                                    sub_comments: List[Dict], crawl_interval: float = 1.0,
+    async def get_comments_all_sub_comments(self, comments: List[Dict], crawl_interval: float = 1.0,
                                     callback: Optional[Callable] = None) -> List[Dict]:
         """
-        获取指定笔记下指定一级评论下的所有二级评论, 该方法会一直查找一个一级评论下的所有二级评论信息
+        获取指定一级评论下的所有二级评论, 该方法会一直查找一级评论下的所有二级评论信息
         Args:
-            note_id: 笔记ID
-            root_comment_id: 一级评论ID
-            sub_comment_cursor: 二级评论的初始分页游标
-            sub_comments: 爬取一级评论默认携带的二级评论列表
+            comments: 评论列表
             crawl_interval: 爬取一次评论的延迟单位（秒）
             callback: 一次评论爬取结束后
 
         Returns:
         
         """
+        if not config.ENABLE_GET_SUB_COMMENTS:
+            utils.logger.info(f"[XiaoHongShuCrawler.get_comments_all_sub_comments] Crawling sub_comment mode is not enabled")
+            return []
+        
         result = []
-        sub_comment_has_more = True
-        while sub_comment_has_more:
-            comments_res = await self.get_note_sub_comments(note_id, root_comment_id, 10, sub_comment_cursor)
-            sub_comment_has_more = comments_res.get("has_more", False)
-            sub_comment_cursor = comments_res.get("cursor", "")
-            if "comments" not in comments_res:
-                utils.logger.info(
-                    f"[XiaoHongShuClient.get_comment_all_sub_comments] No 'comments' key found in response: {comments_res}")
-                break
-            comments = comments_res["comments"]
-            if callback:
+        for comment in comments:
+            note_id = comment.get("note_id")
+            sub_comments = comment.get("sub_comments")
+            if sub_comments and callback:
                 await callback(note_id, sub_comments)
-            await asyncio.sleep(crawl_interval)
-            result.extend(comments)
+                
+            sub_comment_has_more = comment.get("sub_comment_has_more")
+            if not sub_comment_has_more:
+                continue
+
+            root_comment_id = comment.get("id")
+            sub_comment_cursor = comment.get("sub_comment_cursor")
+        
+            while sub_comment_has_more:
+                comments_res = await self.get_note_sub_comments(note_id, root_comment_id, 10, sub_comment_cursor)
+                sub_comment_has_more = comments_res.get("has_more", False)
+                sub_comment_cursor = comments_res.get("cursor", "")
+                if "comments" not in comments_res:
+                    utils.logger.info(
+                        f"[XiaoHongShuClient.get_comments_all_sub_comments] No 'comments' key found in response: {comments_res}")
+                    break
+                comments = comments_res["comments"]
+                if callback:
+                    await callback(note_id, comments)
+                await asyncio.sleep(crawl_interval)
+                result.extend(comments)
         return result
 
     async def get_creator_info(self, user_id: str) -> Dict: