Merge pull request #461 from FloRainRJY/xiaohongshu_comment_number_re…

…strict feat: xhs增加最大评论数量限制
NanmiCoder · Oct 23, 2024 · fa2bcc4 · fa2bcc4
2 parents 0bb9298 + 19269c6
commit fa2bcc4
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 3 deletions.
diff --git a/config/base_config.py b/config/base_config.py
@@ -59,6 +59,11 @@
 # 是否开启爬评论模式, 默认开启爬评论
 ENABLE_GET_COMMENTS = True
 
+# 爬取一级评论的数量控制(单视频/帖子)
+CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES = 10
+
+
+
 # 是否开启爬二级评论模式, 默认不开启爬二级评论
 # 老版本项目使用了 db, 则需参考 schema/tables.sql line 287 增加表字段
 ENABLE_GET_SUB_COMMENTS = False

diff --git a/media_platform/xhs/client.py b/media_platform/xhs/client.py
@@ -288,7 +288,8 @@ async def get_note_sub_comments(self, note_id: str, root_comment_id: str, num: i
         return await self.get(uri, params)
 
     async def get_note_all_comments(self, note_id: str, crawl_interval: float = 1.0,
-                                    callback: Optional[Callable] = None) -> List[Dict]:
+                                    callback: Optional[Callable] = None,
+                                    max_count: int = 10) -> List[Dict]:
         """
         获取指定笔记下的所有一级评论，该方法会一直查找一个帖子下的所有评论信息
         Args:
@@ -302,7 +303,7 @@ async def get_note_all_comments(self, note_id: str, crawl_interval: float = 1.0,
         result = []
         comments_has_more = True
         comments_cursor = ""
-        while comments_has_more:
+        while comments_has_more and len(result) < max_count:
             comments_res = await self.get_note_comments(note_id, comments_cursor)
             comments_has_more = comments_res.get("has_more", False)
             comments_cursor = comments_res.get("cursor", "")
@@ -311,6 +312,8 @@ async def get_note_all_comments(self, note_id: str, crawl_interval: float = 1.0,
                     f"[XiaoHongShuClient.get_note_all_comments] No 'comments' key found in response: {comments_res}")
                 break
             comments = comments_res["comments"]
+            if len(result) + len(comments) > max_count:
+                comments = comments[:max_count - len(result)]
             if callback:
                 await callback(note_id, comments)
             await asyncio.sleep(crawl_interval)

diff --git a/media_platform/xhs/core.py b/media_platform/xhs/core.py
@@ -21,6 +21,7 @@
 
 import config
 from base.base_crawler import AbstractCrawler
+from config import CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES
 from model.m_xiaohongshu import NoteUrlInfo
 from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import xhs as xhs_store
@@ -263,7 +264,8 @@ async def get_comments(self, note_id: str, semaphore: asyncio.Semaphore):
             await self.xhs_client.get_note_all_comments(
                 note_id=note_id,
                 crawl_interval=random.random(),
-                callback=xhs_store.batch_update_xhs_note_comments
+                callback=xhs_store.batch_update_xhs_note_comments,
+                max_count=CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES
             )
 
     @staticmethod