feat: wechat group+member and talker scrapers

Add scrape_wechat_groups (POST /wechatweb/chatroom/getChatroomList) and scrape_wechat_talkers (POST /wechatweb/wxFriends/talkerList), both reusing the page-number paginator. Groups parse the semicolon-joined memberIds into a member_ids_list so upsert_chat_group can mirror GroupMember rows (composite PK channel/room_id/member_id) idempotently alongside the ChatGroup row. Talkers are a sync-planning input (member_count>0 marks a group conversation); no dedicated table. Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-01 13:54:16 +08:00
parent 2b79e7a232
commit 2a74d3888d
7 changed files with 1163 additions and 4 deletions
@@ -0,0 +1,231 @@
+"""Tests for the WeChat chat-group scraper (M2).
+
+Drives the real page-number pagination + normalization logic through
+``respx`` by wiring a real ``YunkeClient`` (primed with a fake session so the
+login flow is skipped) against a mocked transport.
+
+The fixture ships 3 records across 2 pages of size 2, plus a terminating
+empty page (the documented primary stop signal for page-number endpoints):
+
+* page 1 -> 2 records, ``total=3``
+* page 2 -> 1 record, ``total=3``
+* page 3 -> empty ``data`` array (no more rows)
+
+The scraper must yield exactly the 3 records (normalized to ``ChatGroup``
+snake_case columns + ``raw_json``), parse ``memberIds`` into
+``member_ids_list`` (dropping empty segments), make exactly 3 calls, and stop
+without a 4th.
+"""
+
+from __future__ import annotations
+
+import json as _json
+
+import httpx
+import respx
+
+from app.scraper.wechat import scrape_wechat_groups
+from app.session.yunke_client import YunkeClient
+from tests.cassettes.chatroom_fixture import (
+    CHATROOM_RECORDS,
+    DEFAULT_PAGE_SIZE,
+    TOTAL,
+    make_chatroom_list_response,
+)
+
+BASE = "https://crm2.yunkecn.com"
+CHATROOM_LIST_URL = f"{BASE}/wechatweb/chatroom/getChatroomList"
+
+USERID = "a" * 32
+COMPANY = "8m0atd"
+
+
+def _primed_client() -> YunkeClient:
+    """A YunkeClient already in a logged-in state (login flow skipped)."""
+    return YunkeClient(base_url=BASE, userid=USERID, company=COMPANY)
+
+
+# ---------------------------------------------------------------------------
+# End-to-end: pagination + field mapping + member_ids_list parsing
+# ---------------------------------------------------------------------------
+
+
+@respx.mock
+async def test_scrape_wechat_groups_yields_records_and_paginates():
+    """Two full pages + a terminating empty page -> 3 records, 3 calls."""
+    page1 = make_chatroom_list_response(
+        CHATROOM_RECORDS[:2], total=TOTAL, page_num=1, page_size=DEFAULT_PAGE_SIZE
+    )
+    page2 = make_chatroom_list_response(
+        CHATROOM_RECORDS[2:], total=TOTAL, page_num=2, page_size=DEFAULT_PAGE_SIZE
+    )
+    page3 = make_chatroom_list_response(
+        [], total=TOTAL, page_num=3, page_size=DEFAULT_PAGE_SIZE
+    )
+
+    route = respx.post(CHATROOM_LIST_URL).mock(
+        side_effect=[
+            httpx.Response(200, json=page1),
+            httpx.Response(200, json=page2),
+            httpx.Response(200, json=page3),
+        ]
+    )
+
+    client = _primed_client()
+    try:
+        results = [
+            r async for r in scrape_wechat_groups(client, page_size=DEFAULT_PAGE_SIZE)
+        ]
+    finally:
+        await client.aclose()
+
+    # Pagination: exactly 3 calls (page1, page2, empty-page stop).
+    assert route.call_count == 3
+
+    # Exactly the 3 fixture records (not duplicated, not dropped).
+    assert len(results) == 3
+    assert {r["room_id"] for r in results} == {
+        rec["chatRoomId"] for rec in CHATROOM_RECORDS
+    }
+
+    # Field mapping for each record (compare against the source record).
+    for result, record in zip(results, CHATROOM_RECORDS, strict=True):
+        # Identity + channel.
+        assert result["room_id"] == record["chatRoomId"]
+        assert result["channel"] == "wechat"
+
+        # Naming + ownership.
+        assert result["room_name"] == record["chatRoomName"]
+        assert result["owner_account_id"] == record["wechatId"]
+        assert result["owner_account_nickname"] == record["wechatNickName"]
+        assert result["owner_user_id"] == record["userId"]
+        assert result["owner_user_phone"] == record["userPhone"]
+
+        # Counts.
+        assert result["member_count"] == record["memberCount"]
+        assert result["message_count"] == record["messageCount"]
+        assert result["own_message_count"] == record["ownMessageCount"]
+        assert result["loss_members"] == record["lossMembers"]
+        assert result["add_members"] == record["addMembers"]
+
+        # Avatar + timestamps.
+        assert result["head_image_url"] == record["headImageUrl"]
+        assert result["last_chat_time"] == record["lastChatTime"]
+        assert result["update_time"] == record["updateTime"]
+
+        # member_ids carried raw; member_ids_list parsed (empties dropped).
+        assert result["member_ids"] == record["memberIds"]
+        assert result["member_ids_list"] == [
+            seg for seg in record["memberIds"].split(";") if seg
+        ]
+
+        # Version carried verbatim; raw_json preserves the original record.
+        assert result["version"] == record["version"]
+        assert result["raw_json"] == record
+
+
+# ---------------------------------------------------------------------------
+# member_ids_list parsing edge cases
+# ---------------------------------------------------------------------------
+
+
+@respx.mock
+async def test_scrape_wechat_groups_drops_empty_member_id_segments():
+    """Trailing/empty ``memberIds`` segments are dropped from member_ids_list."""
+    # Record 2 has a trailing ";" -> one empty segment that must be dropped.
+    page1 = make_chatroom_list_response(
+        [CHATROOM_RECORDS[1]], total=1, page_num=1, page_size=DEFAULT_PAGE_SIZE
+    )
+    page2 = make_chatroom_list_response([], total=1, page_num=2)
+    respx.post(CHATROOM_LIST_URL).mock(
+        side_effect=[httpx.Response(200, json=page1), httpx.Response(200, json=page2)]
+    )
+
+    client = _primed_client()
+    try:
+        results = [r async for r in scrape_wechat_groups(client, page_size=DEFAULT_PAGE_SIZE)]
+    finally:
+        await client.aclose()
+
+    assert len(results) == 1
+    # "wxid_member_b1;wxid_member_b2;" -> 2 ids (trailing empty dropped).
+    assert results[0]["member_ids_list"] == ["wxid_member_b1", "wxid_member_b2"]
+
+
+@respx.mock
+async def test_scrape_wechat_groups_handles_missing_member_ids():
+    """A group with no ``memberIds`` field yields an empty member_ids_list."""
+    record = {"chatRoomId": "x@chatroom", "chatRoomName": "Empty"}
+    page1 = make_chatroom_list_response([record], total=1, page_num=1)
+    page2 = make_chatroom_list_response([], total=1, page_num=2)
+    respx.post(CHATROOM_LIST_URL).mock(
+        side_effect=[httpx.Response(200, json=page1), httpx.Response(200, json=page2)]
+    )
+
+    client = _primed_client()
+    try:
+        results = [r async for r in scrape_wechat_groups(client, page_size=DEFAULT_PAGE_SIZE)]
+    finally:
+        await client.aclose()
+
+    assert len(results) == 1
+    assert results[0]["member_ids"] is None
+    assert results[0]["member_ids_list"] == []
+
+
+# ---------------------------------------------------------------------------
+# Pagination body: pageNum/pageSize advanced correctly
+# ---------------------------------------------------------------------------
+
+
+@respx.mock
+async def test_scrape_wechat_groups_sends_pagination_body():
+    """Outgoing request body carries pageNum/pageSize; advances per page."""
+    page1 = make_chatroom_list_response(
+        [CHATROOM_RECORDS[0]], total=TOTAL, page_num=1, page_size=1
+    )
+    page2 = make_chatroom_list_response([], total=TOTAL, page_num=2, page_size=1)
+    route = respx.post(CHATROOM_LIST_URL).mock(
+        side_effect=[httpx.Response(200, json=page1), httpx.Response(200, json=page2)]
+    )
+
+    client = _primed_client()
+    try:
+        results = [r async for r in scrape_wechat_groups(client, page_size=1)]
+    finally:
+        await client.aclose()
+
+    # One record on page 1, empty page 2 stops the loop.
+    assert len(results) == 1
+    assert route.call_count == 2
+
+    body1 = _json.loads(route.calls[0].request.content.decode())
+    assert body1["pageNum"] == 1
+    assert body1["pageSize"] == 1
+
+    body2 = _json.loads(route.calls[1].request.content.decode())
+    assert body2["pageNum"] == 2
+    assert body2["pageSize"] == 1
+
+
+# ---------------------------------------------------------------------------
+# Empty first page -> no yields, single call
+# ---------------------------------------------------------------------------
+
+
+@respx.mock
+async def test_scrape_wechat_groups_stops_on_empty_first_page():
+    """If the very first page is empty, scraper stops without over-fetching."""
+    empty = make_chatroom_list_response([], total=0, page_num=1)
+    route = respx.post(CHATROOM_LIST_URL).mock(
+        return_value=httpx.Response(200, json=empty)
+    )
+
+    client = _primed_client()
+    try:
+        results = [r async for r in scrape_wechat_groups(client)]
+    finally:
+        await client.aclose()
+
+    assert results == []
+    assert route.call_count == 1