From 96309dcfee6c23f6ee97428a74e3087082d5f221 Mon Sep 17 00:00:00 2001
From: Relakkes <relakkes@gmail.com>
Date: Sun, 17 Mar 2024 14:50:10 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20=E5=B0=8F=E7=BA=A2=E4=B9=A6=E5=88=9B?=
 =?UTF-8?q?=E4=BD=9C=E8=80=85=E5=8A=9F=E8=83=BD=E6=95=B0=E6=8D=AE=E8=8E=B7?=
 =?UTF-8?q?=E5=8F=96=E4=BC=98=E5=8C=96?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                    |  49 ++++++-------
 config/base_config.py        |   6 +-
 media_platform/xhs/client.py | 134 +++++++++++++++++++++--------------
 media_platform/xhs/core.py   |  80 +++++++--------------
 store/xhs/__init__.py        |   3 +-
 5 files changed, 133 insertions(+), 139 deletions(-)

diff --git a/README.md b/README.md
index e406e7e..72f84da 100644
--- a/README.md
+++ b/README.md
@@ -18,13 +18,13 @@
 成为赞助者，展示你的产品在这里，联系作者：relakkes@gmail.com
 
 ## 功能列表
-| 平台  | Cookie 登录 | 二维码登录 | 手机号登录 | 关键词搜索 | 指定视频/帖子 ID 爬取 | 登录状态缓存 | 数据保存 | IP 代理池 | 滑块验证码 |
-|:---:|:---------:|:-----:|:-----:|:-----:|:-------------:|:------:|:----:|:------:|:-----:|
-| 小红书 |     ✅     |   ✅   | ✅     |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |   ✕   |
-| 抖音  |     ✅     |   ✅   | ✅     |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |   ✅   |
-| 快手  |     ✅     |   ✅   | ✕     |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |    ✕   |
-| B 站 |     ✅     |   ✅   | ✕     |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |   ✕   |
-| 微博  |     ✅      |   ✅    | ✕     |   ✅    |       ✅        |    ✅    |   ✅   |    ✅    |   ✕   |
+| 平台  | Cookie 登录 | 二维码登录 | 指定创作者主页 | 关键词搜索 | 指定视频/帖子 ID 爬取 | 登录状态缓存 | 数据保存 | IP 代理池 | 滑块验证码 |
+|:---:|:---------:|:-----:|:-------:|:-----:|:-------------:|:------:|:----:|:------:|:-----:|
+| 小红书 |     ✅     |   ✅   |    ✅    |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |   ✕   |
+| 抖音  |     ✅     |   ✅   |    ✕     |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |   ✅   |
+| 快手  |     ✅     |   ✅   |    ✕    |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |    ✕   |
+| B 站 |     ✅     |   ✅   |    ✕    |   ✅   |       ✅       |   ✅    |  ✅   |   ✅    |   ✕   |
+| 微博  |     ✅      |   ✅    |    ✕    |   ✅    |       ✅        |    ✅    |   ✅   |    ✅    |   ✕   |
 
 
 ## 使用方法
@@ -93,24 +93,25 @@
 
 PS：如果打赏时请备注捐赠者，如有遗漏请联系我添加（有时候消息多可能会漏掉，十分抱歉）
 
-| 捐赠者         | 捐赠金额  | 捐赠日期       |
-|-------------|-------|------------|
+| 捐赠者        | 捐赠金额  | 捐赠日期       |
+|------------|-------|------------|
+| *诚         | 20 元  | 2024-03-17 |
 | Strem Gamer | 20 元  | 2024-03-16 |
-| *鑫          | 20 元  | 2024-03-14 |
-| Yuzu        | 20 元  | 2024-03-07 |
-| **宁         | 100 元 | 2024-03-03 |
-| **媛         | 20 元  | 2024-03-03 |
-| Scarlett    | 20 元  | 2024-02-16 |
-| Asun        | 20 元  | 2024-01-30 |
-| 何*          | 100 元 | 2024-01-21 |
-| allen       | 20 元  | 2024-01-10 |
-| llllll      | 20 元  | 2024-01-07 |
-| 邝*元         | 20 元  | 2023-12-29 |
-| 50chen      | 50 元  | 2023-12-22 |
-| xiongot     | 20 元  | 2023-12-17 |
-| atom.hu     | 20 元  | 2023-12-16 |
-| 一呆          | 20 元  | 2023-12-01 |
-| 坠落          | 50 元  | 2023-11-08 |
+| *鑫         | 20 元  | 2024-03-14 |
+| Yuzu       | 20 元  | 2024-03-07 |
+| **宁        | 100 元 | 2024-03-03 |
+| **媛        | 20 元  | 2024-03-03 |
+| Scarlett   | 20 元  | 2024-02-16 |
+| Asun       | 20 元  | 2024-01-30 |
+| 何*         | 100 元 | 2024-01-21 |
+| allen      | 20 元  | 2024-01-10 |
+| llllll     | 20 元  | 2024-01-07 |
+| 邝*元        | 20 元  | 2023-12-29 |
+| 50chen     | 50 元  | 2023-12-22 |
+| xiongot    | 20 元  | 2023-12-17 |
+| atom.hu    | 20 元  | 2023-12-16 |
+| 一呆         | 20 元  | 2023-12-01 |
+| 坠落         | 50 元  | 2023-11-08 |
 
 ## 运行报错常见问题Q&A
 > 遇到问题先自行搜索解决下，现在AI很火，用ChatGPT大多情况下能解决你的问题 [免费的ChatGPT](https://sider.ai/invited?c=8e03db1a973401fdf114ed9cf9f8c183)  
diff --git a/config/base_config.py b/config/base_config.py
index da7885a..333c216 100644
--- a/config/base_config.py
+++ b/config/base_config.py
@@ -4,7 +4,7 @@ KEYWORDS = "python,golang"
 LOGIN_TYPE = "qrcode"  # qrcode or phone or cookie
 COOKIES = ""
 SORT_TYPE = "popularity_descending"  # 具体值参见media_platform.xxx.field下的枚举值，展示只支持小红书
-CRAWLER_TYPE = "search"
+CRAWLER_TYPE = "search" # 爬取类型，search(关键词搜索) | detail(帖子相亲)| creator(创作者主页数据)
 
 # 是否开启 IP 代理
 ENABLE_IP_PROXY = False
@@ -70,8 +70,6 @@ WEIBO_SPECIFIED_ID_LIST = [
 
 # 指定小红书创作者ID列表
 XHS_CREATOR_ID_LIST = [
-    "59d8cb33de5fb4696bf17217",
-    "61b87386000000001000b18b",
-    "5e8558100000000001005bc5",
+    "63e36c9a000000002703502b",
     # ........................
 ]
diff --git a/media_platform/xhs/client.py b/media_platform/xhs/client.py
index 72e9d89..7586578 100644
--- a/media_platform/xhs/client.py
+++ b/media_platform/xhs/client.py
@@ -1,7 +1,7 @@
 import asyncio
 import json
 import re
-from typing import Callable, Dict, List, Optional
+from typing import Callable, Dict, List, Optional, Union, Any
 from urllib.parse import urlencode
 
 import httpx
@@ -28,6 +28,7 @@ class XHSClient:
         self.timeout = timeout
         self.headers = headers
         self._host = "https://edith.xiaohongshu.com"
+        self._domain = "https://www.xiaohongshu.com"
         self.IP_ERROR_STR = "网络连接异常，请检查网络设置或重启试试"
         self.IP_ERROR_CODE = 300012
         self.NOTE_ABNORMAL_STR = "笔记状态异常，请稍后查看"
@@ -63,7 +64,7 @@ class XHSClient:
         self.headers.update(headers)
         return self.headers
 
-    async def request(self, method, url, **kwargs) -> Dict:
+    async def request(self, method, url, **kwargs) -> Union[str, Any]:
         """
         封装httpx的公共请求方法，对请求响应做一些处理
         Args:
@@ -82,10 +83,10 @@ class XHSClient:
                 method, url, timeout=self.timeout,
                 **kwargs
             )
-        
+
         if return_response:
             return response.text
-        
+
         data: Dict = response.json()
         if data["success"]:
             return data.get("data", data.get("success", {}))
@@ -186,56 +187,6 @@ class XHSClient:
         }
         return await self.post(uri, data)
 
-    async def get_creator_info_and_notes(self, creator: str) -> Dict:
-        """
-        获取博主的信息和第一页的笔记
-        Args:
-            creator: 博主ID
-        Returns:
-            {"creator":{}, "notes":[]}
-        """
-        path = '/user/profile/'+creator
-        content = await self.request(method="GET", url=f"https://www.xiaohongshu.com{path}", return_response=True)
-        match = re.search(r'<script>window.__INITIAL_STATE__=(.+)<\/script>', content, re.M)
-
-        if match == None:
-            return {}
-        
-        info = json.loads(match.group(1).replace(':undefined', ':null'), strict=False)
-        if info == None:
-            return {}
-        
-        return {
-            'creator': info.get('user').get('userPageData'),
-            'notes': info.get('user').get('notes')[0],
-            'cursor': info.get('user').get('noteQueries')[0].get('cursor'),
-            'has_more_notes': info.get('user').get('noteQueries')[0].get('hasMore')
-        }
-
-    async def get_notes_by_creator(
-            self, creator: str,
-            cursor: str, 
-            page_size: int = 30
-    ) -> Dict:
-        """
-        获取博主的笔记
-        Args:
-            creator: 博主ID
-            cursor: 上一页最后一条笔记的ID
-            page_size: 分页数据长度
-
-        Returns:
-
-        """
-        uri = "/api/sns/web/v1/user_posted"
-        data = {
-            "user_id": creator,
-            "cursor": cursor,
-            "num": page_size,
-            "image_formats": "jpg,webp,avif"
-        }
-        return await self.get(uri, data)
-
     async def get_note_by_id(self, note_id: str) -> Dict:
         """
         获取笔记详情API
@@ -268,7 +219,7 @@ class XHSClient:
         params = {
             "note_id": note_id,
             "cursor": cursor,
-            "top_comment_id":"",
+            "top_comment_id": "",
             "image_formats": "jpg,webp,avif"
         }
         return await self.get(uri, params)
@@ -323,3 +274,76 @@ class XHSClient:
             await asyncio.sleep(crawl_interval)
             result.extend(comments)
         return result
+
+    async def get_creator_info(self, user_id: str) -> Dict:
+        """
+        通过解析网页版的用户主页HTML，获取用户个人简要信息
+        PC端用户主页的网页存在window.__INITIAL_STATE__这个变量上的，解析它即可
+        eg: https://www.xiaohongshu.com/user/profile/59d8cb33de5fb4696bf17217
+        """
+        uri = f"/user/profile/{user_id}"
+        html_content = await self.request("GET", self._domain + uri, return_response=True, headers=self.headers)
+        match = re.search(r'<script>window.__INITIAL_STATE__=(.+)<\/script>', html_content, re.M)
+
+        if match is None:
+            return {}
+
+        info = json.loads(match.group(1).replace(':undefined', ':null'), strict=False)
+        if info is None:
+            return {}
+        return info.get('user').get('userPageData')
+
+    async def get_notes_by_creator(
+            self, creator: str,
+            cursor: str,
+            page_size: int = 30
+    ) -> Dict:
+        """
+        获取博主的笔记
+        Args:
+            creator: 博主ID
+            cursor: 上一页最后一条笔记的ID
+            page_size: 分页数据长度
+
+        Returns:
+
+        """
+        uri = "/api/sns/web/v1/user_posted"
+        data = {
+            "user_id": creator,
+            "cursor": cursor,
+            "num": page_size,
+            "image_formats": "jpg,webp,avif"
+        }
+        return await self.get(uri, data)
+
+    async def get_all_notes_by_creator(self, user_id: str, crawl_interval: float = 1.0,
+                                       callback: Optional[Callable] = None) -> List[Dict]:
+        """
+        获取指定用户下的所有发过的帖子，该方法会一直查找一个用户下的所有帖子信息
+        Args:
+            user_id: 用户ID
+            crawl_interval: 爬取一次的延迟单位（秒）
+            callback: 一次分页爬取结束后的更新回调函数
+
+        Returns:
+
+        """
+        result = []
+        notes_has_more = True
+        notes_cursor = ""
+        while notes_has_more:
+            notes_res = await self.get_notes_by_creator(user_id, notes_cursor)
+            notes_has_more = notes_res.get("has_more", False)
+            notes_cursor = notes_res.get("cursor", "")
+            if "notes" not in notes_res:
+                utils.logger.info(f"[XHSClient.get_all_notes_by_creator] No 'notes' key found in response: {notes_res}")
+                break
+
+            notes = notes_res["notes"]
+            utils.logger.info(f"[XHSClient.get_all_notes_by_creator] got user_id:{user_id} notes len : {len(notes)}")
+            if callback:
+                await callback(notes)
+            await asyncio.sleep(crawl_interval)
+            result.extend(notes)
+        return result
diff --git a/media_platform/xhs/core.py b/media_platform/xhs/core.py
index 987ba5f..bf8a941 100644
--- a/media_platform/xhs/core.py
+++ b/media_platform/xhs/core.py
@@ -126,65 +126,35 @@ class XiaoHongShuCrawler(AbstractCrawler):
     async def get_creators_and_notes(self) -> None:
         """Get creator's notes and retrieve their comment information."""
         utils.logger.info("[XiaoHongShuCrawler.get_creators_and_notes] Begin get xiaohongshu creators")
-        xhs_limit_count = 30
-        for creator in config.XHS_CREATOR_ID_LIST:
-            utils.logger.info(f"[XiaoHongShuCrawler.get_creators_and_notes] Current creator: {creator}")
-            page = 0
-            cursor = ''
-            has_more_notes = False
-            while page * xhs_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
-                note_id_list: List[str] = []
+        for user_id in config.XHS_CREATOR_ID_LIST:
+            # get creator detail info from web html content
+            createor_info: Dict = await self.xhs_client.get_creator_info(user_id=user_id)
+            if createor_info:
+                await xhs_store.save_creator(user_id, creator=createor_info)
 
-                if page == 0:
-                    # get creator info and notes
-                    creator_and_notes_info = await self.xhs_client.get_creator_info_and_notes(creator)
+            # Get all note information of the creator
+            all_notes_list = await self.xhs_client.get_all_notes_by_creator(
+                user_id=user_id,
+                crawl_interval=random.random(),
+                callback=self.fetch_creator_notes_detail
+            )
 
-                    if creator_and_notes_info == None or not creator_and_notes_info:
-                        utils.logger.error(f"[XiaoHongShuCrawler.get_creators_and_notes] get creator notes error")
-                        continue
+            note_ids = [note_item.get("note_id") for note_item in all_notes_list]
+            await self.batch_get_note_comments(note_ids)
 
-                    notes_res = creator_and_notes_info.get('notes')
-                    # utils.logger.info(f"[XiaoHongShuCrawler.get_creators_and_notes] get creator and notes:{notes_res}")
+    async def fetch_creator_notes_detail(self, note_list: List[Dict]):
+        """
+        Concurrently obtain the specified post list and save the data
+        """
+        semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
+        task_list = [
+            self.get_note_detail(post_item.get("note_id"), semaphore) for post_item in note_list
+        ]
 
-                    cursor = creator_and_notes_info.get('cursor')
-                    has_more_notes = creator_and_notes_info.get('has_more_notes')
-
-                    # save creator info
-                    await xhs_store.save_creator(creator, creator_and_notes_info.get('creator'))
-                    utils.logger.info(
-                        f"[XiaoHongShuCrawler.get_creators_and_notes] save creator info:{creator_and_notes_info.get('creator')}")
-                else:
-                    # get notes
-                    notes = await self.xhs_client.get_notes_by_creator(creator, cursor)
-                    # utils.logger.info(f"[XiaoHongShuCrawler.get_creators_and_notes] get notes res:{notes_res}")
-
-                    if notes == None or not notes:
-                        utils.logger.error(f"[XiaoHongShuCrawler.get_creators_and_notes] get creator's notes error")
-                        continue
-
-                    cursor = notes.get('cursor')
-                    has_more_notes = notes.get('has_more_notes')
-                    notes_res = notes.get('notes')
-                    utils.logger.info(
-                        f"[XiaoHongShuCrawler.get_creators_and_notes] get creator's notes res:{notes_res}")
-
-                semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
-                task_list = [
-                    self.get_note_detail(post_item.get('id'), semaphore)
-                    for post_item in notes_res
-                ]
-                note_details = await asyncio.gather(*task_list)
-                for note_detail in note_details:
-                    if note_detail is not None:
-                        await xhs_store.update_xhs_note(note_detail)
-                        note_id_list.append(note_detail.get('note_id'))
-                page += 1
-
-                utils.logger.info(f"[XiaoHongShuCrawler.get_creators_and_notes] Note details: {note_details}")
-                await self.batch_get_note_comments(note_id_list)
-
-                if not has_more_notes:
-                    break
+        note_details = await asyncio.gather(*task_list)
+        for note_detail in note_details:
+            if note_detail is not None:
+                await xhs_store.update_xhs_note(note_detail)
 
     async def get_specified_notes(self):
         """Get the information and comments of the specified post"""
diff --git a/store/xhs/__init__.py b/store/xhs/__init__.py
index 748bb90..7cc7ba2 100644
--- a/store/xhs/__init__.py
+++ b/store/xhs/__init__.py
@@ -26,6 +26,7 @@ class XhsStoreFactory:
         return store_class()
 
 
+
 async def update_xhs_note(note_item: Dict):
     note_id = note_item.get("note_id")
     user_info = note_item.get("user", {})
@@ -116,7 +117,7 @@ async def save_creator(user_id: str, creator: Dict):
         'follows': follows,
         'fans': fans,
         'interaction': interaction,
-        'tag_list': json.dumps({tag.get('tagType'): tag.get('name') for tag in creator.get('tags')}),
+        'tag_list': json.dumps({tag.get('tagType'): tag.get('name') for tag in creator.get('tags')}, ensure_ascii=False),
     }
     utils.logger.info(f"[store.xhs.save_creator] creator:{local_db_item}")
     await XhsStoreFactory.create_store().store_creator(local_db_item)