修复小红书用户主页信息获取失败

README.md

@@ -89,7 +89,8 @@ xhs comments "<url>" --all --json      # All comments as JSON
 xhs comments <note_id> --xsec-token T  # Use note_id + explicit xsec_token
 xhs comments <note_id>                 # Reuse cached token if available
 xhs sub-comments <note_id> <cmt_id>   # View replies to a comment
-xhs user <user_id>                     # User profile
+xhs user <user_id_or_url>              # User profile; profile URL may include xsec_token/xsec_source
+xhs user <user_id> --xsec-token T --xsec-source pc_search  # User profile with explicit xsec context
 xhs user-posts <user_id>              # User's published notes
 xhs user-posts <user_id> --cursor X   # Paginate with cursor
 
@@ -382,7 +383,8 @@ xhs comments "<url>" --all --json      # 全部评论，JSON 格式
 xhs comments <note_id> --xsec-token T  # 用 note_id + 显式 xsec_token
 xhs comments <note_id>                 # 如果之前访问过 URL，会复用缓存 token
 xhs sub-comments <note_id> <cmt_id>   # 查看评论的回复
-xhs user <user_id>                     # 用户主页
+xhs user <user_id_or_url>              # 用户主页；主页 URL 可携带 xsec_token/xsec_source
+xhs user <user_id> --xsec-token T --xsec-source pc_search  # 显式传 xsec 上下文
 xhs user-posts <user_id>              # 用户发布的笔记
 
 # 发现

tests/test_cli.py

@@ -351,6 +351,37 @@ def test_search_empty_results_clear_previous_index(self, monkeypatch):
 
         assert saved == [[]]
 
+    def test_user_profile_url_passes_xsec_context(self, monkeypatch):
+        called = {}
+
+        class FakeClient:
+            def get_user_info(self, user_id, xsec_token="", xsec_source=""):
+                called["user_id"] = user_id
+                called["xsec_token"] = xsec_token
+                called["xsec_source"] = xsec_source
+                return {}
+
+        def fake_handle_command(ctx, action, render, as_json, as_yaml):
+            action(FakeClient())
+            return None
+
+        monkeypatch.setattr("xhs_cli.commands.reading.handle_command", fake_handle_command)
+
+        result = runner.invoke(
+            cli,
+            [
+                "user",
+                "https://www.xiaohongshu.com/user/profile/user-1?xsec_token=token-abc&xsec_source=pc_search",
+            ],
+        )
+
+        assert result.exit_code == 0
+        assert called == {
+            "user_id": "user-1",
+            "xsec_token": "token-abc",
+            "xsec_source": "pc_search",
+        }
+
     def test_user_posts_saves_index_entries(self, monkeypatch):
         saved = []
         monkeypatch.setattr("xhs_cli.note_refs.save_note_index", lambda items: saved.append(items))

tests/test_client.py

@@ -69,6 +69,44 @@ def fake_post(self, uri, data):
             client.close()
 
 
+class TestUserProfileEndpoint:
+    def test_get_user_info_fetches_profile_html_with_xsec_context(self, monkeypatch):
+        captured = {}
+        html = (
+            '<script>window.__INITIAL_STATE__={"user":{"userPageData":{'
+            '"basicInfo":{"nickname":"Alice","redId":"alice001","userId":"user-1","ipLocation":"Shanghai","gender":1},'
+            '"interactions":[{"type":"fans","count":"123"}],'
+            '"tags":[]'
+            "}}}</script>"
+        )
+
+        def fake_request(self, method, url, **kwargs):
+            captured["method"] = method
+            captured["url"] = url
+            captured["headers"] = kwargs.get("headers", {})
+            return httpx.Response(200, text=html)
+
+        monkeypatch.setattr(XhsClient, "_request_with_retry", fake_request)
+
+        client = XhsClient({"a1": "cookie"})
+        try:
+            result = client.get_user_info(
+                "user-1",
+                xsec_token="token-abc",
+                xsec_source="pc_search",
+            )
+        finally:
+            client.close()
+
+        assert captured["method"] == "GET"
+        assert captured["url"] == (
+            "https://www.xiaohongshu.com/user/profile/user-1"
+            "?xsec_token=token-abc&xsec_source=pc_search"
+        )
+        assert "a1=cookie" in captured["headers"]["cookie"]
+        assert result["basicInfo"]["nickname"] == "Alice"
+
+
 class TestTransportCookies:
     def test_request_with_retry_merges_response_cookies(self, monkeypatch):
         request = httpx.Request("POST", "https://edith.xiaohongshu.com/api/test")

xhs_cli/cli.py

@@ -5,7 +5,7 @@
     xhs search <keyword> [--sort popular|latest] [--type video|image] [--page N]
     xhs read <id_or_url> [--xsec-token TOKEN]
     xhs comments <id_or_url>
-    xhs user <user_id>
+    xhs user <user_id_or_url> [--xsec-token TOKEN] [--xsec-source SOURCE]
     xhs user-posts <user_id> [--cursor CURSOR]
     xhs feed
     xhs hot [--category CATEGORY]

xhs_cli/client_mixins.py

@@ -12,6 +12,7 @@
 from collections import OrderedDict
 from pathlib import Path
 from typing import Any
+from urllib.parse import urlencode
 
 from .constants import CREATOR_HOST, HOME_URL, UPLOAD_HOST, USER_AGENT
 from .cookies import (
@@ -22,7 +23,7 @@
     invalidate_note_context,
 )
 from .exceptions import NeedVerifyError, UnsupportedOperationError, XhsApiError
-from .html_parser import extract_note_from_html
+from .html_parser import extract_note_from_html, extract_user_from_html
 
 logger = logging.getLogger(__name__)
 
@@ -219,6 +220,27 @@ def _fetch_note_html(
         )
         return resp.text
 
+    def _fetch_user_html(
+        self,
+        user_id: str,
+        xsec_token: str = "",
+        xsec_source: str = "",
+    ) -> str:
+        url = f"{HOME_URL}/user/profile/{user_id}"
+        if xsec_token and xsec_source:
+            url = f"{url}?{urlencode({'xsec_token': xsec_token, 'xsec_source': xsec_source})}"
+
+        resp = self._request_with_retry(
+            "GET",
+            url,
+            headers={
+                "user-agent": USER_AGENT,
+                "referer": f"{HOME_URL}/",
+                "cookie": cookies_to_string(self.cookies),
+            },
+        )
+        return resp.text
+
     def resolve_xsec_context(
         self,
         note_id: str,
@@ -258,10 +280,14 @@ def resolve_xsec_token(self, note_id: str, preferred_token: str = "") -> str:
     def get_self_info(self) -> dict[str, Any]:
         return self._main_api_get("/api/sns/web/v2/user/me")
 
-    def get_user_info(self, user_id: str) -> dict[str, Any]:
-        return self._main_api_get("/api/sns/web/v1/user/otherinfo", {
-            "target_user_id": user_id,
-        })
+    def get_user_info(
+        self,
+        user_id: str,
+        xsec_token: str = "",
+        xsec_source: str = "",
+    ) -> dict[str, Any]:
+        html = self._fetch_user_html(user_id, xsec_token=xsec_token, xsec_source=xsec_source)
+        return extract_user_from_html(html)
 
     def get_user_notes(self, user_id: str, cursor: str = "") -> dict[str, Any]:
         return self._main_api_get("/api/sns/web/v1/user_posted", {

xhs_cli/commands/reading.py

@@ -6,6 +6,7 @@
 from ..cookies import cache_note_context
 from ..formatter import (
     maybe_print_structured,
+    parse_user_reference,
     print_info,
     render_comments,
     render_feed,
@@ -149,13 +150,20 @@ def _render_comments(data):
 
 @click.command()
 @click.argument("user_id")
+@click.option("--xsec-token", default="", help="Security token from a profile URL")
+@click.option("--xsec-source", default="", help="Security source from a profile URL")
 @structured_output_options
 @click.pass_context
-def user(ctx, user_id: str, as_json: bool, as_yaml: bool):
+def user(ctx, user_id: str, xsec_token: str, xsec_source: str, as_json: bool, as_yaml: bool):
     """View user profile info."""
+    parsed_user_id, url_token, url_source = parse_user_reference(user_id)
     handle_command(
         ctx,
-        action=lambda client: client.get_user_info(user_id),
+        action=lambda client: client.get_user_info(
+            parsed_user_id,
+            xsec_token=xsec_token or url_token,
+            xsec_source=xsec_source or url_source,
+        ),
         render=render_user_info,
         as_json=as_json,
         as_yaml=as_yaml,

xhs_cli/formatter.py

@@ -65,3 +65,18 @@ def extract_note_id(id_or_url: str) -> str:
     """Extract note ID from URL or return as-is (drops query params)."""
     note_id, _ = parse_note_url(id_or_url)
     return note_id
+
+
+def parse_user_reference(id_or_url: str) -> tuple[str, str, str]:
+    """Extract user ID, xsec_token, and xsec_source from a profile URL or plain ID."""
+    if "xiaohongshu.com" in id_or_url:
+        from urllib.parse import parse_qs, urlparse
+
+        parsed = urlparse(id_or_url)
+        parts = parsed.path.rstrip("/").split("/")
+        user_id = parts[-1]
+        qs = parse_qs(parsed.query)
+        xsec_token = qs.get("xsec_token", [""])[0]
+        xsec_source = qs.get("xsec_source", [""])[0]
+        return user_id, xsec_token, xsec_source
+    return id_or_url, "", ""

xhs_cli/formatter_normalizers.py

@@ -19,7 +19,7 @@ def _coerce_int(value: Any, default: int = 0) -> int:
 
 
 def normalize_user_info(data: dict[str, Any]) -> dict[str, Any]:
-    basic = data.get("basic_info", data)
+    basic = data.get("basic_info", data.get("basicInfo", data))
     interactions = data.get("interactions", [])
 
     stats = {}
@@ -28,10 +28,13 @@ def normalize_user_info(data: dict[str, Any]) -> dict[str, Any]:
 
     return {
         "nickname": basic.get("nickname", basic.get("nick_name", "Unknown")),
-        "red_id": basic.get("red_id", ""),
+        "red_id": basic.get("red_id", basic.get("redId", "")),
         "desc": basic.get("desc", ""),
-        "ip_location": basic.get("ip_location", ""),
-        "user_id": basic.get("user_id", data.get("user_id", "")),
+        "ip_location": basic.get("ip_location", basic.get("ipLocation", "")),
+        "user_id": basic.get(
+            "user_id",
+            basic.get("userId", data.get("user_id", data.get("userId", ""))),
+        ),
         "gender": basic.get("gender"),
         "stats": stats,
     }

xhs_cli/html_parser.py

@@ -71,3 +71,18 @@ def extract_note_from_html(html: str, note_id: str) -> dict[str, Any]:
     """High-level: parse HTML → extract note in one step."""
     state = parse_initial_state(html)
     return extract_note_from_state(state, note_id)
+
+
+def extract_user_from_state(state: dict[str, Any]) -> dict[str, Any]:
+    """Extract profile data from a parsed XHS user homepage state."""
+    user_page_data = state.get("user", {}).get("userPageData")
+    if isinstance(user_page_data, dict):
+        return user_page_data
+
+    raise XhsApiError("User profile not found in HTML state")
+
+
+def extract_user_from_html(html: str) -> dict[str, Any]:
+    """High-level: parse HTML → extract user profile in one step."""
+    state = parse_initial_state(html)
+    return extract_user_from_state(state)