diff --git a/yunke-server/app/api/routers/groups.py b/yunke-server/app/api/routers/groups.py index a909cf1..0e823c1 100644 --- a/yunke-server/app/api/routers/groups.py +++ b/yunke-server/app/api/routers/groups.py @@ -5,6 +5,10 @@ ``owner_user_id`` column) and ``q`` (substring match on ``room_name``, ``%``/``_`` escaped as literals — the 通讯录群 tab search box), ordered by ``last_chat_time desc`` (nulls last) so recently-active groups surface first. + 微信群统计扩展(2026-09-09,云客「微信群统计」同款):``msg_start``/``msg_end`` + 统计时段(窗内输出沟通消息数/新增/退出成员数聚合)、``last_start``/ + ``last_end`` 最新消息时间段、``group_remark`` 群备注子串;行补员工微信/ + 员工信息列(wechat_account/staff 关联)。 * ``GET /api/groups/{room_id}/members`` -> ``list[GroupMemberOut]`` — the members of a single group (small set, no pagination needed). """ @@ -19,7 +23,15 @@ from sqlalchemy.ext.asyncio import AsyncSession from app.api.deps import get_session from app.api.schemas import GroupMemberOut, GroupOut, Page -from app.db.models import ChatGroup, GroupMember +from app.db.models import ( + ChatGroup, + ChatGroupMemberStats, + GroupMember, + MsgDailyStats, + Staff, + WechatAccount, +) +from app.storage.summary import day_key router = APIRouter(prefix="/api", tags=["groups"]) @@ -38,6 +50,11 @@ async def list_groups( user_id: Annotated[str | None, Query()] = None, room_id: Annotated[str | None, Query()] = None, q: Annotated[str | None, Query()] = None, + group_remark: Annotated[str | None, Query()] = None, + last_start: Annotated[int | None, Query(ge=0)] = None, + last_end: Annotated[int | None, Query(ge=0)] = None, + msg_start: Annotated[int | None, Query(ge=0)] = None, + msg_end: Annotated[int | None, Query(ge=0)] = None, ) -> Page[GroupOut]: """List chat groups with optional ``channel`` / ``owner_account_id`` / ``user_id`` / ``room_id`` / ``q`` filters. @@ -47,6 +64,13 @@ async def list_groups( filter on ``GET /api/customers``. ``room_id`` is an exact-match lookup (composite PK: the same room may return one row per owner; chat page group-name resolution). ``q`` is a substring match on ``room_name``. + + 微信群统计参数(2026-09-09):``last_start``/``last_end`` 过滤 + ``last_chat_time`` 范围(最新消息时间段);``msg_start``/``msg_end`` + 统计时段——窗内聚合三列(``window_msg_count`` 沟通消息数= + msg_daily_stats 按天求和、``window_added``/``window_lost`` 成员进出= + chat_group_member_stats 按天求和,上线日起有数据);``group_remark`` + 群备注子串。员工微信/员工信息列经 wechat_account/staff 关联补齐。 """ conditions = [] if channel is not None: @@ -57,10 +81,17 @@ async def list_groups( # LIKE 通配符转义: %/_ 按字面匹配(镜像 customers/messages 的 q 处理) escaped = q.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_") conditions.append(ChatGroup.room_name.like(f"%{escaped}%", escape="\\")) + if group_remark: + escaped_r = group_remark.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_") + conditions.append(ChatGroup.group_remark.like(f"%{escaped_r}%", escape="\\")) if room_id is not None: conditions.append(ChatGroup.room_id == room_id) if user_id is not None: conditions.append(ChatGroup.owner_user_id == user_id) + if last_start is not None: + conditions.append(ChatGroup.last_chat_time >= last_start) + if last_end is not None: + conditions.append(ChatGroup.last_chat_time <= last_end) total_stmt = sa.select(sa.func.count()).select_from(ChatGroup) if conditions: @@ -79,7 +110,84 @@ async def list_groups( .offset((page - 1) * page_size) ) rows = (await session.execute(list_stmt)).scalars().all() - items = [GroupOut.model_validate(row) for row in rows] + + # ---- 员工微信/员工信息列(wechat_account/staff 关联,本页行集) ---- + acc_map: dict[str, tuple[str | None, str | None, str | None]] = {} + owners = {r.owner_account_id for r in rows if r.owner_account_id} + if owners: + for wx, nick, alias, raw in (await session.execute( + sa.select( + WechatAccount.wx_id, WechatAccount.nick_name, + WechatAccount.alias, WechatAccount.raw_json, + ).where(WechatAccount.wx_id.in_(owners)) + )).all(): + avatar = None + if isinstance(raw, dict): + h = raw.get("headImageUrl") + avatar = h if isinstance(h, str) else None + acc_map[wx] = (nick, alias, avatar) + staff_map: dict[str, tuple[str | None, str | None]] = {} + uids = {r.owner_user_id for r in rows if r.owner_user_id} + if uids: + for uid, name, phone in (await session.execute( + sa.select(Staff.user_id, Staff.name, Staff.phone) + .where(Staff.user_id.in_(uids)) + )).all(): + staff_map[uid] = (name, phone) + + # ---- 统计时段窗内聚合(msg_daily_stats 沟通消息数 + member_stats 进出) ---- + msg_cnt: dict[tuple[str, str], int] = {} + added_map: dict[tuple[str, str], int] = {} + lost_map: dict[tuple[str, str], int] = {} + if msg_start is not None and msg_end is not None and rows: + d0, d1 = day_key(msg_start), day_key(msg_end) + pairs = [(r.owner_account_id, r.room_id) for r in rows] + owners_in = {p[0] for p in pairs} + rooms_in = {p[1] for p in pairs} + for owner, room, cnt in (await session.execute( + sa.select( + MsgDailyStats.owner_account_id, MsgDailyStats.peer_id, + sa.func.coalesce(sa.func.sum( + MsgDailyStats.send_cnt + MsgDailyStats.recv_cnt), 0), + ).where( + MsgDailyStats.channel == (channel or "wechat"), + MsgDailyStats.peer_kind == "room", + MsgDailyStats.owner_account_id.in_(owners_in), + MsgDailyStats.peer_id.in_(rooms_in), + MsgDailyStats.day >= d0, MsgDailyStats.day <= d1, + ).group_by(MsgDailyStats.owner_account_id, MsgDailyStats.peer_id) + )).all(): + msg_cnt[(owner, room)] = int(cnt) + for owner, room, a, l in (await session.execute( + sa.select( + ChatGroupMemberStats.owner_account_id, ChatGroupMemberStats.room_id, + sa.func.coalesce(sa.func.sum(ChatGroupMemberStats.added), 0), + sa.func.coalesce(sa.func.sum(ChatGroupMemberStats.lost), 0), + ).where( + ChatGroupMemberStats.channel == (channel or "wechat"), + ChatGroupMemberStats.owner_account_id.in_(owners_in), + ChatGroupMemberStats.room_id.in_(rooms_in), + ChatGroupMemberStats.day >= d0, ChatGroupMemberStats.day <= d1, + ).group_by(ChatGroupMemberStats.owner_account_id, ChatGroupMemberStats.room_id) + )).all(): + added_map[(owner, room)] = int(a) + lost_map[(owner, room)] = int(l) + + items = [] + for r in rows: + out = GroupOut.model_validate(r) + acc = acc_map.get(r.owner_account_id or "") + if acc: + out.staff_nickname, out.staff_wx_alias, out.staff_avatar = acc + st = staff_map.get(r.owner_user_id or "") + if st: + out.staff_name, out.staff_phone = st + if msg_start is not None and msg_end is not None: + key = (r.owner_account_id or "", r.room_id) + out.window_msg_count = msg_cnt.get(key, 0) + out.window_added = added_map.get(key, 0) + out.window_lost = lost_map.get(key, 0) + items.append(out) return Page(items=items, total=total, page=page, page_size=page_size) diff --git a/yunke-server/app/api/schemas.py b/yunke-server/app/api/schemas.py index 6f4086b..c27abfa 100644 --- a/yunke-server/app/api/schemas.py +++ b/yunke-server/app/api/schemas.py @@ -199,6 +199,17 @@ class GroupOut(BaseModel): owner_avatar: str | None = None friend_count: int | None = None create_time: int | None = None # 建群时间 ms epoch + # 微信群统计页(2026-09-09,云客 getChatroomList 同款) + group_remark: str | None = None # 群备注 + staff_nickname: str | None = None # 员工微信·昵称(wechat_account.nick_name) + staff_wx_alias: str | None = None # 员工微信·微信号(wechat_account.alias) + staff_avatar: str | None = None # 员工微信·头像 + staff_name: str | None = None # 员工信息·姓名(staff.name) + staff_phone: str | None = None # 员工信息·手机(staff.phone) + # 统计时段窗内聚合(仅请求带 msg_start/msg_end 时非 None): + window_msg_count: int | None = None # 沟通消息数(窗内,msg_daily_stats) + window_added: int | None = None # 新增成员数(窗内,按天表求和) + window_lost: int | None = None # 退出成员数(窗内) raw_json: dict[str, Any] | None = None diff --git a/yunke-server/app/db/models.py b/yunke-server/app/db/models.py index 2de19a0..0cd3d01 100644 --- a/yunke-server/app/db/models.py +++ b/yunke-server/app/db/models.py @@ -344,6 +344,9 @@ class ChatGroup(Base): owner_avatar: Mapped[str | None] = mapped_column(String(1024), nullable=True) friend_count: Mapped[int | None] = mapped_column(Integer, nullable=True) # 群成员中员工好友数 create_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True) # 建群时间 ms epoch + # 群备注(微信群统计页「群备注」列;getChatroomList.remark / + # friend_list/es 的 friendWxRemark,2026-09-09) + group_remark: Mapped[str | None] = mapped_column(String(255), nullable=True) version: Mapped[str | None] = mapped_column(String(64), nullable=True) raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True) @@ -362,6 +365,34 @@ class ChatGroup(Base): ) +class ChatGroupMemberStats(Base): + """群成员进出按天统计(chat_group_member_stats,2026-09-09)。 + + 云客「微信群统计」的新增/退出成员数是 ``getChatroomList`` 按 + ``startTime~endTime`` 任意窗实时算的;本地无成员进出事件流,改为每夜 + 抓一次「当日窗」的 addMembers/lossMembers 落一行,页面任意日窗=按天 + 求和。**上线日起积累**(历史日期无数据;chat_group.add_members/ + loss_members 旧列保留作最近一次抓取窗的快照)。 + """ + + __tablename__ = "chat_group_member_stats" + + channel: Mapped[str] = mapped_column(String(16), primary_key=True) + owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True) + room_id: Mapped[str] = mapped_column(String(128), primary_key=True) + # yyyymmdd(上海自然日,同 msg_daily_stats 口径) + day: Mapped[int] = mapped_column(Integer, primary_key=True) + added: Mapped[int] = mapped_column( + Integer, nullable=False, default=0, server_default=sa.text("0") + ) + lost: Mapped[int] = mapped_column( + Integer, nullable=False, default=0, server_default=sa.text("0") + ) + + fetched_at: Mapped[dt.datetime] = _fetched_at() + updated_at: Mapped[dt.datetime] = _updated_at() + + class GroupMember(Base): """群成员 — composite PK (channel, room_id, member_id). diff --git a/yunke-server/app/scraper/wechat.py b/yunke-server/app/scraper/wechat.py index 7ef1dfa..20c4348 100644 --- a/yunke-server/app/scraper/wechat.py +++ b/yunke-server/app/scraper/wechat.py @@ -901,7 +901,7 @@ def _normalize_chat_group(record: dict[str, Any]) -> dict[str, Any]: ``'YYYY-MM-DD HH:mm:ss'`` 字符串,另兼容 ms-int/数字串,统一归一为 ms-epoch int,复用 ``_parse_add_time`` 的双形态解析) """ - return { + rec = { "room_id": record.get("friendWxId"), "channel": "wechat", "room_name": record.get("friendWxNickname"), @@ -929,6 +929,12 @@ def _normalize_chat_group(record: dict[str, Any]) -> dict[str, Any]: "version": record.get("version"), "raw_json": record, } + # 群备注(2026-09-09 微信群统计):friend_list/es 是唯一备注源 + # (getChatroomList 行无备注键);**有值才写**——空值不放键,upsert 不 + # 更新该列,不会被无备注的抓取轮次清空 + if record.get("friendWxRemark"): + rec["group_remark"] = record["friendWxRemark"] + return rec async def scrape_wechat_groups( diff --git a/yunke-server/app/storage/repos.py b/yunke-server/app/storage/repos.py index 9dedd85..c82c18d 100644 --- a/yunke-server/app/storage/repos.py +++ b/yunke-server/app/storage/repos.py @@ -62,6 +62,7 @@ from sqlalchemy.orm import DeclarativeBase from app.db.models import ( ChatGroup, + ChatGroupMemberStats, Customer, CustomerAccountLink, Department, @@ -82,6 +83,7 @@ _logger = logging.getLogger(__name__) __all__ = [ "upsert_chat_group", + "upsert_chat_group_member_stats", "upsert_customer", "upsert_customers", "prune_customer_links", @@ -631,6 +633,18 @@ async def upsert_chat_group(session: AsyncSession, rec: dict[str, Any]) -> None: await _upsert_one(session, GroupMember, member_rec) +async def upsert_chat_group_member_stats( + session: AsyncSession, rec: dict[str, Any] +) -> None: + """Idempotently upsert one :class:`ChatGroupMemberStats` day row. + + PK = (channel, owner_account_id, room_id, day)。每夜「当日窗」抓取的 + addMembers/lossMembers 落一行;同日重跑刷新(幂等)。页面任意日窗的 + 新增/退出 = 按天求和(2026-09-09 微信群统计对齐)。 + """ + await _upsert_one(session, ChatGroupMemberStats, rec) + + # --------------------------------------------------------------------------- # PhoneCall (voice_call) upsert (M2, Task 2.4) # --------------------------------------------------------------------------- diff --git a/yunke-server/migrations/versions/c9d0e1f2a3b4_group_remark_and_member_stats.py b/yunke-server/migrations/versions/c9d0e1f2a3b4_group_remark_and_member_stats.py new file mode 100644 index 0000000..ae5022c --- /dev/null +++ b/yunke-server/migrations/versions/c9d0e1f2a3b4_group_remark_and_member_stats.py @@ -0,0 +1,80 @@ +"""chat_group 补 group_remark 列 + chat_group_member_stats 按天进出表 + +Revision ID: c9d0e1f2a3b4 +Revises: b7c8d9e0f1a2 +Create Date: 2026-09-09 + +内容 +---- +微信群列表对齐云客「微信群统计」页(2026-09-09 真机探明,数据源切 +``getChatroomList``): + +* ``chat_group.group_remark`` —— 群备注列(getChatroomList.remark / + friend_list/es 的 friendWxRemark,此前只存 raw_json); +* ``chat_group_member_stats`` —— 群成员进出**按天**统计表。云客的新增/ + 退出成员数是按任意时间窗实时算的,本地无成员进出事件流,改为每夜抓 + 一次「当日窗」的 addMembers/lossMembers 落行,页面任意日窗=按天求和; + 上线日起积累,历史日期无数据。 + +幂等:列/表存在即跳过。SQLite/MySQL 通用。 +""" +from collections.abc import Sequence + +import sqlalchemy as sa +from alembic import op + +# revision identifiers, used by Alembic. +revision: str = 'c9d0e1f2a3b4' +down_revision: str | Sequence[str] | None = 'b7c8d9e0f1a2' +branch_labels: str | Sequence[str] | None = None +depends_on: str | Sequence[str] | None = None + +_TABLE = 'chat_group_member_stats' +_COL = 'group_remark' + + +def _has_table(table: str) -> bool: + insp = sa.inspect(op.get_bind()) + return table in insp.get_table_names() + + +def _has_column(table: str, column: str) -> bool: + insp = sa.inspect(op.get_bind()) + return column in {c["name"] for c in insp.get_columns(table)} + + +def upgrade() -> None: + """Upgrade schema.""" + if not _has_column("chat_group", _COL): + op.add_column("chat_group", sa.Column(_COL, sa.String(255), nullable=True)) + # 回填:群备注从存量 raw_json.friendWxRemark 提取(friend_list/es 来源; + # getChatroomList 行无备注键)。幂等:只补 NULL 行。MySQL 方言 + # (JSON_UNQUOTE),SQLite(测试库,不走生产迁移)跳过。 + if op.get_bind().dialect.name == "mysql": + op.execute( + "UPDATE chat_group SET group_remark = JSON_UNQUOTE(JSON_EXTRACT(raw_json, '$.friendWxRemark')) " + "WHERE group_remark IS NULL " + "AND JSON_UNQUOTE(JSON_EXTRACT(raw_json, '$.friendWxRemark')) IS NOT NULL " + "AND JSON_UNQUOTE(JSON_EXTRACT(raw_json, '$.friendWxRemark')) != ''" + ) + if _has_table(_TABLE): + return # 已建过,幂等跳过 + op.create_table( + _TABLE, + sa.Column('channel', sa.String(16), primary_key=True), + sa.Column('owner_account_id', sa.String(128), primary_key=True), + sa.Column('room_id', sa.String(128), primary_key=True), + sa.Column('day', sa.Integer(), primary_key=True), + sa.Column('added', sa.Integer(), nullable=False, server_default='0'), + sa.Column('lost', sa.Integer(), nullable=False, server_default='0'), + sa.Column('fetched_at', sa.DateTime(), nullable=True), + sa.Column('updated_at', sa.DateTime(), nullable=True), + ) + + +def downgrade() -> None: + """Downgrade schema.""" + if _has_table(_TABLE): + op.drop_table(_TABLE) + if _has_column("chat_group", _COL): + op.drop_column("chat_group", _COL) diff --git a/yunke-server/scripts/full_sync_all.sh b/yunke-server/scripts/full_sync_all.sh index 66599d7..194a159 100644 --- a/yunke-server/scripts/full_sync_all.sh +++ b/yunke-server/scripts/full_sync_all.sh @@ -26,6 +26,12 @@ echo "$(date) --- 5/10 WeChat groups ---" $PY scripts/scrape_via_page.py --entity groups --max-employees 100 echo "$(date) --- 5b/10 WA groups ---" $PY scripts/scrape_via_page.py --entity wa-groups +# 5c: 微信群统计(getChatroomList,云客「微信群统计」同款)——全窗刷档案列 +# (真成员数/群备注/员工信息)+ 昨日窗落成员进出日行(页面窗内新增/退出) +echo "$(date) --- 5c/10 WeChat chatroom stats ---" +$PY scripts/scrape_via_page.py --entity chatroom-stats +YDAY=$(date -d "yesterday" +%F) +$PY scripts/scrape_via_page.py --entity chatroom-stats --day "$YDAY" echo "$(date) --- 6/10 Voice calls (WeChat + WA) ---" $PY scripts/scrape_via_page.py --entity voice-calls # 语音重扫会把 record_media_hash 覆盖回 None —— 必须紧跟录音重链接 diff --git a/yunke-server/scripts/scrape_via_page.py b/yunke-server/scripts/scrape_via_page.py index acf17fd..395ed1d 100644 --- a/yunke-server/scripts/scrape_via_page.py +++ b/yunke-server/scripts/scrape_via_page.py @@ -1631,6 +1631,163 @@ async def scrape_wa_groups(cookie_str: str, max_pages: int = 200): return total_fetched, total_upserted +# --------------------------------------------------------------------------- +# 微信群统计 getChatroomList(2026-09-09 真机探明,云客同款数据源) +# +# 云客「沟通→微信号管理→微信群统计」页(/cms/wechat/wechatgroup)数据源: +# POST /wechatweb/chatroom/getChatroomList(form-urlencoded) +# departmentId + startTime/endTime('YYYY-MM-DD HH:MM:SS' 时间窗) + 分页; +# 信封 data.overviews[] + totalCount(1,854 行,员工×群维度)。 +# 行含:真 memberCount(群成员数量——friend_list/es 的 friendNum 其实是 +# 员工好友数,旧映射存反了)、remark(群备注)、员工微信(wechatId=微信号 +# alias/wechatNickName/头像)、员工信息(userName/userPhone)、以及**窗内** +# addMembers/lossMembers(新增/退出成员数,任意窗实时算)。 +# +# 本地无成员进出事件流 → add/loss 只能按天积累:每夜抓「当日窗」落 +# chat_group_member_stats 日行,页面任意日窗=按天求和(历史无数据)。 +# --------------------------------------------------------------------------- + +CHATROOM_LIST_PATH = "/wechatweb/chatroom/getChatroomList" + + +def _normalize_chatroom_stat_row(row: dict, owner_wxid: str) -> dict: + """getChatroomList 行 → ChatGroup 补列记录。 + + 只放该端点有的字段——未出现的列不参与 upsert 的 UPDATE 子句, + friend_list/es 抓的群主信息等旧值得以保留。 + """ + rec = { + "room_id": row.get("chatRoomId"), + "channel": "wechat", + "owner_account_id": owner_wxid, + "room_name": row.get("chatRoomName"), + # 真群成员数(修正:旧源 friendNum 是「员工好友数」被误存此列) + "member_count": row.get("memberCount"), + "head_image_url": row.get("headImageUrl"), + "owner_account_nickname": row.get("wechatNickName"), + "owner_user_id": row.get("userId"), + "owner_user_phone": row.get("userPhone"), + "message_count": row.get("messageCount"), + "own_message_count": row.get("ownMessageCount"), + "add_members": row.get("addMembers"), # 本窗快照(日窗=当日进出) + "loss_members": row.get("lossMembers"), + "last_chat_time": row.get("lastChatTime"), + "update_time": row.get("updateTime"), + "raw_json": row, + } + # 群备注:getChatroomList 行通常无 remark 键(云客页面也显示 -);有才写, + # 无则不放该键——upsert 不更新未出现的列,friend_list/es 来源的 + # friendWxRemark 备注得以保留 + if row.get("remark"): + rec["group_remark"] = row["remark"] + return rec + + +async def _chatroom_rows(page, dept: str, start_str: str, end_str: str, max_pages: int = 100): + """翻完 getChatroomList 一个窗,返回全部行(list)。""" + rows_all: list[dict] = [] + page_num = 1 + while page_num <= max_pages: + body = await _browser_fetch( + page, CHATROOM_LIST_PATH, + form_body={ + "departmentId": dept, "startTime": start_str, "endTime": end_str, + "pageNum": page_num, "pageSize": 50, + }, + ) + data = body.get("data") or {} + rows = data.get("overviews") or [] + rows_all.extend(rows) + total = data.get("totalCount") or 0 + logger.info(f" chatroom-list page {page_num}: {len(rows)} rows (total {total})") + if not rows or page_num * 50 >= (total or 0): + break + page_num += 1 + await asyncio.sleep(1.2) + return rows_all + + +async def _owner_alias_map(conn): + """wechat_account 的 alias/nick_name → wx_id 映射。 + + getChatroomList 行的 wechatId 是员工**微信号**(alias,如 Nancyjade) + 而非 wxId,owner 归属需经此解析;miss 时回退存原值(不影响其余列)。 + """ + from sqlalchemy import text as sa_text + + result = await conn.execute(sa_text( + "SELECT alias, nick_name, wx_id FROM wechat_account " + "WHERE wx_id IS NOT NULL AND wx_id != ''" + )) + mapping: dict[str, str] = {} + for alias, nick, wx in result.fetchall(): + if alias: + mapping[str(alias)] = wx + if nick: + mapping.setdefault(str(nick), wx) + return mapping + + +async def scrape_chatroom_stats(cookie_str: str, day: str | None = None): + """getChatroomList 抓取(云客微信群统计同款)。 + + * ``day=None``:全窗(2020 起)——chat_group 档案补列基线(真成员数/ + 群备注/员工信息列;add/loss 存全窗快照); + * ``day='YYYY-MM-DD'``:单日窗——落 chat_group_member_stats 当日行 + (页面任意日窗的新增/退出=按天求和)。 + """ + import datetime as _dt + + from app.db.base import async_engine + from app.storage.repos import upsert_chat_group, upsert_chat_group_member_stats + + dept = await _root_dept_id() + async with async_engine.connect() as conn: + alias_map = await _owner_alias_map(conn) + + if day: + start_str, end_str = f"{day} 00:00:00", f"{day} 23:59:59" + day_key = int(day.replace("-", "")) + else: + start_str = "2020-01-01 00:00:00" + end_str = f"{_dt.date.today()} 23:59:59" + day_key = None + + group_recs: list[dict] = [] + stats_recs: list[dict] = [] + async with PageScraper(cookie_str) as scraper: + page = await _open_fetch_page(scraper) + for row in await _chatroom_rows(page, dept, start_str, end_str): + rid = row.get("chatRoomId") + if not rid: + continue + owner_wxid = ( + alias_map.get(str(row.get("wechatId") or "")) + or alias_map.get(str(row.get("wechatNickName") or "")) + or str(row.get("wechatId") or "") + ) + group_recs.append(_normalize_chatroom_stat_row(row, owner_wxid)) + if day_key is not None: + stats_recs.append({ + "channel": "wechat", + "owner_account_id": owner_wxid, + "room_id": rid, + "day": day_key, + "added": row.get("addMembers") or 0, + "lost": row.get("lossMembers") or 0, + }) + + if group_recs: + await _upsert_all(upsert_chat_group, group_recs) + if stats_recs: + await _upsert_all(upsert_chat_group_member_stats, stats_recs) + logger.info( + f"DONE: chatroom-stats day={day or '全窗'} groups={len(group_recs)} " + f"stats_rows={len(stats_recs)}" + ) + return len(group_recs), len(stats_recs) + + # --------------------------------------------------------------------------- # 员工朋友圈 Moments (browser fetch, per employee) # --------------------------------------------------------------------------- @@ -2301,6 +2458,7 @@ async def main(): "wa-accounts", # WA员工账号 (waBusiness/userlist interception) "wa-friends", # WA客户 (waBusiness/friendlist interception) "wa-groups", # WA群 (browser fetch businessFriendList type=1) + "chatroom-stats", # 微信群统计 (getChatroomList 带窗,云客同款) "voice-calls", # 语音通话记录 (voice-call-list + wavoicecalllist) "voice-clips", # 长语音 (browser fetch call/list per employee) "wa-messages", # WA消息 (browser fetch chatRecords per conversation) @@ -2315,6 +2473,7 @@ async def main(): parser.add_argument("--max-pages", type=int, default=200, help="列表翻页上限 (accounts/wa-accounts/wa-friends/voice-calls/moments)") parser.add_argument("--batch-size", type=int, default=50, help="媒体下载批次大小 (media)") parser.add_argument("--full-history", action="store_true", help="消息类实体强制全量翻历史(默认增量水位)") + parser.add_argument("--day", type=str, default=None, help="chatroom-stats:单日窗 YYYY-MM-DD(落按天进出表);缺省=全窗档案基线") args = parser.parse_args() cookie = _load_cookie() @@ -2348,6 +2507,8 @@ async def _dispatch_entity(args, cookie: str) -> None: await scrape_wa_friends(cookie, args.max_pages) elif args.entity == "wa-groups": await scrape_wa_groups(cookie, args.max_pages) + elif args.entity == "chatroom-stats": + await scrape_chatroom_stats(cookie, args.day) elif args.entity == "voice-calls": await scrape_voice_calls(cookie, args.max_pages) elif args.entity == "voice-clips": diff --git a/yunke-server/tests/test_api_groups.py b/yunke-server/tests/test_api_groups.py index f1211c8..d949a67 100644 --- a/yunke-server/tests/test_api_groups.py +++ b/yunke-server/tests/test_api_groups.py @@ -344,3 +344,79 @@ async def test_q_room_name_substring_filter(make_client): # 空串 -> 不过滤 r3 = await client.get("/api/groups", params={"q": ""}) assert r3.json()["total"] == 3 + + +# --------------------------------------------------------------------------- +# 微信群统计扩展(2026-09-09):统计时段窗聚合 + 员工列 + 群备注/最新消息筛选 +# --------------------------------------------------------------------------- + +async def _seed_stat(session: AsyncSession) -> None: + from app.db.models import ChatGroupMemberStats, MsgDailyStats, Staff, WechatAccount + + session.add_all([ + WechatAccount(wx_id="wx_owner_1", nick_name="玉", alias="Nancyjade", + user_id="u_wx_1", raw_json={"headImageUrl": "http://a/h.png"}), + Staff(user_id="u_wx_1", name="聂玉婷", phone="18500000000"), + ChatGroup(room_id="stat_room@chatroom", channel="wechat", room_name="统计群", + owner_account_id="wx_owner_1", owner_user_id="u_wx_1", + member_count=46, group_remark="VIP群", last_chat_time=5000), + # 窗内两天日行(0907+0908):沟通 3+4=7 条 + MsgDailyStats(channel="wechat", owner_account_id="wx_owner_1", peer_kind="room", + peer_id="stat_room@chatroom", day=20260907, send_cnt=1, recv_cnt=2), + MsgDailyStats(channel="wechat", owner_account_id="wx_owner_1", peer_kind="room", + peer_id="stat_room@chatroom", day=20260908, send_cnt=2, recv_cnt=2), + # 窗外日行(0901)不应计入 + MsgDailyStats(channel="wechat", owner_account_id="wx_owner_1", peer_kind="room", + peer_id="stat_room@chatroom", day=20260901, send_cnt=99, recv_cnt=99), + # 窗内进出:0907 +2/-1 + ChatGroupMemberStats(channel="wechat", owner_account_id="wx_owner_1", + room_id="stat_room@chatroom", day=20260907, added=2, lost=1), + ]) + await session.commit() + + +async def test_group_window_aggregates_and_staff_columns(make_client): + """msg_start/msg_end 窗内三聚合 + 员工微信/员工信息关联列。""" + client = await make_client(_seed_stat) + # 2026-09-07 ~ 2026-09-09(上海日 20260907..20260909,UTC ms) + r = await client.get("/api/groups", params={ + "channel": "wechat", "room_id": "stat_room@chatroom", + "msg_start": 1788758400000, "msg_end": 1789017600000, + }) + assert r.status_code == 200 + it = r.json()["items"][0] + assert it["window_msg_count"] == 7 # 窗内日行求和,0901 排除 + assert it["window_added"] == 2 + assert it["window_lost"] == 1 + assert it["group_remark"] == "VIP群" + assert it["staff_nickname"] == "玉" + assert it["staff_wx_alias"] == "Nancyjade" + assert it["staff_avatar"] == "http://a/h.png" + assert it["staff_name"] == "聂玉婷" + assert it["staff_phone"] == "18500000000" + + # 无窗请求 → 聚合三列为 None(不误显 0) + r2 = await client.get("/api/groups", params={ + "channel": "wechat", "room_id": "stat_room@chatroom"}) + it2 = r2.json()["items"][0] + assert it2["window_msg_count"] is None + assert it2["window_added"] is None + + +async def test_group_remark_and_last_window_filters(make_client): + """群备注子串 + 最新消息时间段过滤。""" + client = await make_client(_seed_stat) + r = await client.get("/api/groups", params={ + "channel": "wechat", "group_remark": "VIP"}) + assert [i["room_id"] for i in r.json()["items"]] == ["stat_room@chatroom"] + r2 = await client.get("/api/groups", params={ + "channel": "wechat", "group_remark": "不存在"}) + assert r2.json()["total"] == 0 + + # last_chat_time=5000 → last_start=4000 命中,last_start=6000 排除 + r3 = await client.get("/api/groups", params={ + "channel": "wechat", "last_start": 4000, "last_end": 9999}) + assert "stat_room@chatroom" in [i["room_id"] for i in r3.json()["items"]] + r4 = await client.get("/api/groups", params={ + "channel": "wechat", "last_start": 6000, "last_end": 9999}) + assert r4.json()["total"] == 0 diff --git a/yunkes/src/api/index.ts b/yunkes/src/api/index.ts index fce496a..86fcfba 100644 --- a/yunkes/src/api/index.ts +++ b/yunkes/src/api/index.ts @@ -178,6 +178,14 @@ export interface GroupQuery { room_id?: string /** 群名称模糊搜索(通讯录群 tab 搜索框)。 */ q?: string + /** 群备注子串(微信群统计筛选)。 */ + group_remark?: string + /** 最新消息时间段(ms,含端点)。 */ + last_start?: number + last_end?: number + /** 统计时段(ms,含端点)——窗内输出沟通消息数/新增/退出成员数聚合。 */ + msg_start?: number + msg_end?: number page?: number page_size?: number } @@ -191,6 +199,11 @@ export function getGroups(query: GroupQuery = {}): Promise> { user_id: query.user_id, room_id: query.room_id, q: query.q, + group_remark: query.group_remark, + last_start: query.last_start, + last_end: query.last_end, + msg_start: query.msg_start, + msg_end: query.msg_end, page: query.page ?? 1, page_size: query.page_size ?? 20, }), diff --git a/yunkes/src/api/types.ts b/yunkes/src/api/types.ts index 915a415..7bbeb7f 100644 --- a/yunkes/src/api/types.ts +++ b/yunkes/src/api/types.ts @@ -113,6 +113,19 @@ export interface Group { friend_count?: number | null /** 建群时间 ms-epoch */ create_time?: number | null + /** 群备注(微信群统计页;getChatroomList.remark,2026-09-09) */ + group_remark?: string | null + /** 员工微信列(getChatroomList 同款):昵称/微信号/头像 */ + staff_nickname?: string | null + staff_wx_alias?: string | null + staff_avatar?: string | null + /** 员工信息列:姓名/手机(staff 关联) */ + staff_name?: string | null + staff_phone?: string | null + /** 统计时段窗内聚合(仅请求带 msg_start/msg_end 时非 null) */ + window_msg_count?: number | null + window_added?: number | null + window_lost?: number | null /** * Verbatim upstream chatroom record (camelCase keys: chatRoomId/chatRoomName, * memberCount/memberIds, headImageUrl, wechatId/wechatNickName, userName/ diff --git a/yunkes/src/views/GroupList.vue b/yunkes/src/views/GroupList.vue index e8116fd..1a55877 100644 --- a/yunkes/src/views/GroupList.vue +++ b/yunkes/src/views/GroupList.vue @@ -3,14 +3,13 @@ import { computed, onMounted, reactive, ref, watch } from 'vue' import { useRoute, useRouter } from 'vue-router' import { ElMessage } from 'element-plus' import { Download } from '@element-plus/icons-vue' -import { getGroups } from '@/api' +import { getAccounts, getGroups } from '@/api' import { downloadBlob } from '@/api/client' -import type { Channel, Group } from '@/api/types' +import type { Account, Channel, Group } from '@/api/types' import { useChannelStore } from '@/stores/channel' import { channelLabel, formatTime } from '@/utils/format' import { exportListToCsv } from '@/utils/csvExport' import { buildGroupSections, readField } from '@/utils/groupFields' -import { fromTypeLabel } from '@/utils/customerFields' /** * 群列表 — channel-tabbed view mirroring 云客「沟通」板块的群列表. @@ -84,10 +83,6 @@ function cellNum(row: Group, camelKey: string, fallback = 0): number { const v = cell(row, camelKey) return typeof v === 'number' && Number.isFinite(v) ? v : fallback } -/** 数据来源列：fromType 代码→文案（复用 customerFields.fromTypeLabel）。 */ -function fromTypeText(row: Group): string { - return fromTypeLabel(cell(row, 'fromType')) -} function imageCell(row: Group, camelKey: string): string | undefined { const v = cell(row, camelKey) return typeof v === 'string' && v !== '' ? v : undefined @@ -108,7 +103,16 @@ async function loadTab(ch: TabKey): Promise { channel: ch, page: st.page, page_size: st.pageSize, - owner_account_id: ownerId.value ?? undefined, + owner_account_id: ch === 'wechat' ? (staffOwner.value || ownerId.value) || undefined : ownerId.value ?? undefined, + // 微信群统计筛选(云客「微信群统计」同款,2026-09-09) + ...(ch === 'wechat' + ? { + q: gName.value.trim() || undefined, + group_remark: gRemark.value.trim() || undefined, + ...(lastRange.value ? { last_start: dayStart(lastRange.value[0]), last_end: dayEnd(lastRange.value[1]) } : {}), + ...(statRange.value ? { msg_start: dayStart(statRange.value[0]), msg_end: dayEnd(statRange.value[1]) } : {}), + } + : {}), }) st.items = res.items st.total = res.total @@ -120,6 +124,47 @@ async function loadTab(ch: TabKey): Promise { st.loading = false } } + +// ---- 微信群统计筛选(云客同款:统计时段/最新消息时间段/群名称/群备注/员工) ---- +function defaultStatRange(): [Date, Date] { + // 云客默认近 7 天(截图 09-03→09-09) + const end = new Date() + const start = new Date(end.getTime() - 6 * 86_400_000) + return [start, end] +} +const statRange = ref<[Date, Date] | null>(defaultStatRange()) +const lastRange = ref<[Date, Date] | null>(null) +const gName = ref('') +const gRemark = ref('') +/** 员工筛选(下拉;入口 query 的 owner_account_id 作初值,选择后接管)。 */ +const staffOwner = ref(ownerId.value ?? '') +const staffOptions = ref([]) + +function dayStart(d: Date): number { + const x = new Date(d) + x.setHours(0, 0, 0, 0) + return x.getTime() +} +function dayEnd(d: Date): number { + const x = new Date(d) + x.setHours(23, 59, 59, 999) + return x.getTime() +} + +async function loadStaffOptions(): Promise { + try { + const res = await getAccounts({ channel: 'wechat', page: 1, page_size: 100 }) + staffOptions.value = res.items + if (ownerId.value && !staffOwner.value) staffOwner.value = ownerId.value + } catch { + // 静默降级:员工筛选为空 + } +} + +function onSearch(): void { + tabState.wechat.page = 1 + loadTab('wechat') +} function handlePageChange(ch: TabKey, p: number): void { tabState[ch].page = p loadTab(ch) @@ -262,6 +307,7 @@ watch( ) onMounted(() => { + loadStaffOptions() loadTab(activeTab.value) }) @@ -287,9 +333,52 @@ onMounted(() => {