1. 同步MediaCrawler为最新版本

2. 修复数据库not null错误
3. 支持PG数据库
4. 规范环境变量及配置使用
5. 规范为uv安装
6. 使用loggru

MindSpider/DeepSentimentCrawling/MediaCrawler/media_platform/xhs/help.py

@@ -15,7 +15,7 @@ import random
 import time
 import urllib.parse
 
-from model.m_xiaohongshu import NoteUrlInfo
+from model.m_xiaohongshu import NoteUrlInfo, CreatorUrlInfo
 from tools.crawler_util import extract_url_params_to_dict
 
 
@@ -27,16 +27,17 @@ def sign(a1="", b1="", x_s="", x_t=""):
         "s0": 3,  # getPlatformCode
         "s1": "",
         "x0": "1",  # localStorage.getItem("b1b1")
-        "x1": "3.7.8-2",  # version
+        "x1": "4.2.2",  # version
         "x2": "Mac OS",
         "x3": "xhs-pc-web",
-        "x4": "4.27.2",
+        "x4": "4.74.0",
         "x5": a1,  # cookie of a1
         "x6": x_t,
         "x7": x_s,
         "x8": b1,  # localStorage.getItem("b1")
         "x9": mrc(x_t + x_s + b1),
         "x10": 154,  # getSigCount
+        "x11": "normal"
     }
     encode_str = encodeUtf8(json.dumps(common, separators=(',', ':')))
     x_s_common = b64Encode(encode_str)
@@ -306,6 +307,37 @@ def parse_note_info_from_note_url(url: str) -> NoteUrlInfo:
     return NoteUrlInfo(note_id=note_id, xsec_token=xsec_token, xsec_source=xsec_source)
 
 
+def parse_creator_info_from_url(url: str) -> CreatorUrlInfo:
+    """
+    从小红书创作者主页URL中解析出创作者信息
+    支持以下格式:
+    1. 完整URL: "https://www.xiaohongshu.com/user/profile/5eb8e1d400000000010075ae?xsec_token=AB1nWBKCo1vE2HEkfoJUOi5B6BE5n7wVrbdpHoWIj5xHw=&xsec_source=pc_feed"
+    2. 纯ID: "5eb8e1d400000000010075ae"
+
+    Args:
+        url: 创作者主页URL或user_id
+    Returns:
+        CreatorUrlInfo: 包含user_id, xsec_token, xsec_source的对象
+    """
+    # 如果是纯ID格式(24位十六进制字符),直接返回
+    if len(url) == 24 and all(c in "0123456789abcdef" for c in url):
+        return CreatorUrlInfo(user_id=url, xsec_token="", xsec_source="")
+
+    # 从URL中提取user_id: /user/profile/xxx
+    import re
+    user_pattern = r'/user/profile/([^/?]+)'
+    match = re.search(user_pattern, url)
+    if match:
+        user_id = match.group(1)
+        # 提取xsec_token和xsec_source参数
+        params = extract_url_params_to_dict(url)
+        xsec_token = params.get("xsec_token", "")
+        xsec_source = params.get("xsec_source", "")
+        return CreatorUrlInfo(user_id=user_id, xsec_token=xsec_token, xsec_source=xsec_source)
+
+    raise ValueError(f"无法从URL中解析出创作者信息: {url}")
+
+
 if __name__ == '__main__':
     _img_url = "https://sns-img-bd.xhscdn.com/7a3abfaf-90c1-a828-5de7-022c80b92aa3"
     # 获取一个图片地址在多个cdn下的url地址
@@ -313,4 +345,19 @@ if __name__ == '__main__':
     final_img_url = get_img_url_by_trace_id(get_trace_id(_img_url))
     print(final_img_url)
 
+    # 测试创作者URL解析
+    print("\n=== 创作者URL解析测试 ===")
+    test_creator_urls = [
+        "https://www.xiaohongshu.com/user/profile/5eb8e1d400000000010075ae?xsec_token=AB1nWBKCo1vE2HEkfoJUOi5B6BE5n7wVrbdpHoWIj5xHw=&xsec_source=pc_feed",
+        "5eb8e1d400000000010075ae",
+    ]
+    for url in test_creator_urls:
+        try:
+            result = parse_creator_info_from_url(url)
+            print(f"✓ URL: {url[:80]}...")
+            print(f"  结果: {result}\n")
+        except Exception as e:
+            print(f"✗ URL: {url}")
+            print(f"  错误: {e}\n")
+