浅念
59de51c062
- constants 规则库 v1：AI/引擎/社交域名表、搜索词参数白名单、付费点击参数、 应用内 UA 标记、CHANNELS 枚举；page_view 白名单开 nav_type/prerendering - services/attribution.classify 纯函数：付费>AI>引擎>社交>referral 分层， UTM 证据叠加（combined/conflict/label_only），应用内 UA 叠加/兜底， 引擎 TLD 国家 variant，搜索词白名单提取（Google 恒空不虚构） - SourceClassification 派生表（迁移 0004）：first_touch/session_entry 双 scope， rule_version 可追溯 - ingest 增量 best-effort：首访客/新会话时分类落库（savepoint+静默， 失败不影响采集）；validation 对 page_view referrer 完整 URL 参数清洗+截500 - recompute_attribution 命令：全量/按站幂等重算 - API：访客列表归因五字段+channel 筛选、详情 attribution 块（含最近5会话入口）、 dashboard channels 聚合（sources 原口径保留）；TS VisitorListParams 加 channel - 测试 97 → 124（引擎20 + 集成/接口7） Co-Authored-By: Claude Code <noreply@anthropic.com>
315 lines
16 KiB
Python
315 lines
16 KiB
Python
"""访客列表/详情/跨天时间线/单会话接口（管理台）。
|
||
|
||
M1 单组织多站点：访客列表支持 ?site= 可选过滤（缺省聚合全部站点），行内随带站点归属
|
||
（site_id/site_name）——多站点下分辨访客来自哪个站；访客数据本身已按站点隔离。
|
||
访客列表查询按 (site,-last_seen_at) 索引逐站扫描或全表 order_by——M1 规模（万级访客）可接受，
|
||
量级上来后按站点分片即可（索引已就位）。
|
||
"""
|
||
from datetime import datetime, time, timedelta
|
||
|
||
from django.db.models import Count, OuterRef, Q, Subquery, Sum
|
||
from django.utils import timezone
|
||
from rest_framework.response import Response
|
||
from rest_framework.views import APIView
|
||
|
||
from tracker.api.envelope import EnvelopeMixin, ok
|
||
from tracker.models import Event, RawBatch, Site, SourceClassification, VisitSession, Visitor
|
||
|
||
PAGE_SIZE = 20
|
||
RAW_PAGE_SIZE = 10 # 原始批次 body 较大，页小一些
|
||
TIMELINE_DEFAULT_DAYS = 30
|
||
TIMELINE_MAX_DAYS = 90
|
||
TIMELINE_MAX_EVENTS = 1000
|
||
ONLINE_WINDOW = timedelta(minutes=5) # 与 dashboard active_now 同口径
|
||
ATTR_SESSION_ENTRIES = 5 # 详情页归因块带出的最近会话入口分类数
|
||
|
||
|
||
def _source(referrer_domain, utm):
|
||
"""来源三级兜底：referrer_domain → utm.utm_source → 直接访问（访客档案/会话共用）。"""
|
||
return referrer_domain or (utm or {}).get("utm_source") or "直接访问"
|
||
|
||
|
||
def _iso(dt):
|
||
"""输出给前端的时间统一按当前时区（上海）序列化：USE_TZ=True 下 isoformat() 是 UTC
|
||
（"+00:00"），前端切串直显会与 Dashboard 的上海自然日口径同屏矛盾（差 8 小时）。"""
|
||
return timezone.localtime(dt).isoformat() if dt else None
|
||
|
||
|
||
def _row(visitor, last_session, online_cutoff, ft=None):
|
||
"""列表/详情共用行字段。last_source 依赖最近会话（由调用方批量取好传入，防 N+1）。
|
||
channel 等归因五字段来自该访客 first_touch 分类（无分类行 → 空串，前端回落 first_source 展示）。"""
|
||
return {
|
||
"visitor_id": visitor.visitor_id,
|
||
# 站点归属：visitor.site 需随行 select_related("site")，否则逐行多一条查询
|
||
"site_id": visitor.site.site_id, "site_name": visitor.site.name,
|
||
"country": visitor.country, "province": visitor.province, "city": visitor.city,
|
||
"device_type": visitor.device_type, "os": visitor.os,
|
||
"browser": visitor.browser, "language": visitor.language,
|
||
"first_seen_at": _iso(visitor.first_seen_at),
|
||
"last_seen_at": _iso(visitor.last_seen_at),
|
||
"visit_count": visitor.visit_count, "active_days": visitor.active_days,
|
||
"session_count": visitor.session_count,
|
||
"total_stay_ms": visitor.total_stay_ms or 0, # 无会话时 Sum 为 None → 0
|
||
"first_source": _source(visitor.first_referrer_domain, visitor.first_utm),
|
||
"last_source": _source(last_session.referrer_domain, last_session.utm)
|
||
if last_session else "直接访问", # 无会话访客（仅采集异常场景）
|
||
"channel": ft.channel if ft else "",
|
||
"platform": ft.platform if ft else "",
|
||
"variant": ft.variant if ft else "",
|
||
"search_term": ft.search_term if ft else "",
|
||
"resolution": ft.resolution if ft else "",
|
||
"online": visitor.last_seen_at > online_cutoff, # Python 侧比对（last_seen_at 已随行取出）
|
||
}
|
||
|
||
|
||
def _classification(sc, with_session=False):
|
||
"""SourceClassification → API dict（详情归因块用，含证据可信度与规则版本）。"""
|
||
if not sc:
|
||
return None
|
||
d = {"channel": sc.channel, "platform": sc.platform, "variant": sc.variant,
|
||
"search_term": sc.search_term, "evidence_kind": sc.evidence_kind,
|
||
"resolution": sc.resolution, "detail": sc.detail or {},
|
||
"rule_version": sc.rule_version, "computed_at": _iso(sc.computed_at)}
|
||
if with_session:
|
||
d["session_id"] = sc.session.session_id if sc.session_id else None
|
||
return d
|
||
|
||
|
||
def _session_summary(s):
|
||
# duration_ms 仅内部字段不展示——前端时长一律用 stay_ms（有效停留口径）
|
||
return {"session_id": s.session_id,
|
||
"started_at": _iso(s.started_at), "ended_at": _iso(s.ended_at),
|
||
"referrer_domain": s.referrer_domain, "utm": s.utm,
|
||
"landing_path": s.landing_path, "event_count": s.event_count,
|
||
"stay_ms": s.stay_ms}
|
||
|
||
|
||
def _annotate(qs):
|
||
"""会话数/有效停留/最近会话标记一次注解到位。
|
||
|
||
last_source 不逐行 sessions.order_by("-started_at").first()（页大小 20 即 N+1）：
|
||
先用相关子查询把每个访客最近会话的 pk 标到行上（走 (visitor,-started_at) 索引），
|
||
分页后一次 IN 查询取回整页会话——全程只多 2 条 SQL。
|
||
"""
|
||
latest = (VisitSession.objects.filter(visitor=OuterRef("pk"))
|
||
.order_by("-started_at", "-pk")) # -pk 平局次序跨请求稳定
|
||
return qs.annotate(
|
||
session_count=Count("sessions"),
|
||
total_stay_ms=Sum("sessions__stay_ms"), # 有效停留口径（非 duration_ms）
|
||
latest_session_pk=Subquery(latest.values("pk")[:1]),
|
||
)
|
||
|
||
|
||
def _page_visitors(qs, request):
|
||
"""过滤 + 分页 + 批量取最近会话，返回 (rows, total, page)。"""
|
||
p = request.query_params
|
||
if p.get("show_bot") != "1": # 默认排除爬虫；show_bot=1 才包含
|
||
qs = qs.filter(is_bot=False)
|
||
if p.get("country"):
|
||
qs = qs.filter(country=p["country"])
|
||
if p.get("device_type"):
|
||
qs = qs.filter(device_type=p["device_type"])
|
||
if p.get("online") == "1":
|
||
qs = qs.filter(last_seen_at__gt=timezone.now() - ONLINE_WINDOW)
|
||
if p.get("is_new") == "1": # first_seen_at 落在今天（USE_TZ 下 __date 按当前时区取日期）
|
||
qs = qs.filter(first_seen_at__date=timezone.localdate())
|
||
if p.get("search"):
|
||
q = p["search"]
|
||
qs = qs.filter(Q(visitor_id__istartswith=q) | Q(last_ip__istartswith=q))
|
||
if p.get("channel"):
|
||
# 渠道筛选（值=CHANNELS 枚举）：按 first_touch 分类内连接过滤。
|
||
# distinct 防御分类表脏重复行（无唯一约束，并发极端下可能同键两行）撑大 count。
|
||
qs = qs.filter(source_classifications__scope="first_touch",
|
||
source_classifications__channel=p["channel"]).distinct()
|
||
date_from = _parse_date(p.get("date_from"))
|
||
date_to = _parse_date(p.get("date_to"))
|
||
if date_from:
|
||
qs = qs.filter(last_seen_at__date__gte=date_from)
|
||
if date_to:
|
||
qs = qs.filter(last_seen_at__date__lte=date_to)
|
||
|
||
total = qs.count() # 注解前 count：不必为计数做会话表 join
|
||
try:
|
||
page = int(p.get("page", 1))
|
||
except (TypeError, ValueError):
|
||
page = 1
|
||
page = max(1, page)
|
||
|
||
page_qs = _annotate(qs).select_related("site").order_by("-last_seen_at", "-pk")
|
||
visitors = list(page_qs[(page - 1) * PAGE_SIZE: page * PAGE_SIZE])
|
||
latest = {s.pk: s for s in VisitSession.objects.filter(
|
||
pk__in=[v.latest_session_pk for v in visitors if v.latest_session_pk])}
|
||
# 归因字段批量取：整页一次 IN 查询（同 latest 的做法），不做 select_related N+1
|
||
fts = {sc.visitor_id: sc for sc in SourceClassification.objects.filter(
|
||
visitor__in=[v.pk for v in visitors], scope="first_touch")}
|
||
cutoff = timezone.now() - ONLINE_WINDOW
|
||
rows = [_row(v, latest.get(v.latest_session_pk), cutoff, fts.get(v.pk))
|
||
for v in visitors]
|
||
return rows, total, page
|
||
|
||
|
||
def _parse_date(raw):
|
||
"""YYYY-MM-DD 宽松解析：非法/缺失返回 None（该筛选不生效，不为此 400）。"""
|
||
try:
|
||
return datetime.strptime(raw, "%Y-%m-%d").date()
|
||
except (TypeError, ValueError):
|
||
return None
|
||
|
||
|
||
def _get_visitor(visitor_id):
|
||
"""visitor_id 仅 (site,visitor_id) 唯一——跨站重名时取最近活跃者（M1 单组织，SDK id 撞名概率可忽略）。"""
|
||
return (Visitor.objects.filter(visitor_id=visitor_id)
|
||
.order_by("-last_seen_at", "-pk").first())
|
||
|
||
|
||
def _not_found(message):
|
||
return Response({"code": 404, "data": None, "message": message}, status=404)
|
||
|
||
|
||
def _merge_page_stay(events):
|
||
"""page_view/page_stay 服务端合并（时间线/单会话共用）。
|
||
|
||
按 occurred_at 正序迭代：page_view 追加条目（active_ms=0）；page_stay 向前找同 session 内
|
||
最近一条同 path 的 page_view 条目，把 active_ms 累加进去（同页多段隐藏/恢复多次累加）；
|
||
找不到匹配（含 page_stay 早于任何 page_view 出现）则独立成条目（event_name 保持 page_stay）。
|
||
作用域天然限定在本组事件序列（单会话/时间线单会话桶）——跨会话绝不合并。
|
||
只出 time/event_name/path/title/active_ms 白名单字段，不透出 properties 原文（隐私）。
|
||
"""
|
||
items = []
|
||
for e in events:
|
||
if e.event_name == "page_stay":
|
||
ms = int((e.properties or {}).get("active_ms") or 0)
|
||
for it in reversed(items): # 逆序 = "最近一条"
|
||
if it["event_name"] == "page_view" and it["path"] == e.path:
|
||
it["active_ms"] += ms
|
||
break
|
||
else:
|
||
items.append({"time": _iso(e.occurred_at), "event_name": e.event_name,
|
||
"path": e.path, "title": e.title, "active_ms": ms})
|
||
else:
|
||
# page_view 初始 active_ms=0；其余（sdk_loaded/自定义事件）无停留概念 → null
|
||
active = 0 if e.event_name == "page_view" else None
|
||
items.append({"time": _iso(e.occurred_at), "event_name": e.event_name,
|
||
"path": e.path, "title": e.title, "active_ms": active})
|
||
return items
|
||
|
||
|
||
class VisitorListView(EnvelopeMixin, APIView):
|
||
def get(self, request):
|
||
qs = Visitor.objects.all()
|
||
sid = request.query_params.get("site") # 可选站点过滤，缺省聚合全部（与 dashboard 同款）
|
||
if sid:
|
||
site = Site.objects.filter(site_id=sid).first()
|
||
if not site:
|
||
return _not_found("site_not_found")
|
||
qs = qs.filter(site=site)
|
||
rows, total, page = _page_visitors(qs, request)
|
||
return ok({"list": rows, "total": total, "page": page})
|
||
|
||
|
||
class VisitorDetailView(EnvelopeMixin, APIView):
|
||
def get(self, request, visitor_id):
|
||
visitor = _annotate(Visitor.objects.filter(visitor_id=visitor_id)
|
||
.select_related("site")) \
|
||
.order_by("-last_seen_at", "-pk").first()
|
||
if not visitor:
|
||
return _not_found("visitor_not_found")
|
||
last_session = (VisitSession.objects.filter(pk=visitor.latest_session_pk).first()
|
||
if visitor.latest_session_pk else None)
|
||
# 全量会话摘要（visitor,-started_at 索引）；M1 访客会话量有限不分页
|
||
sessions = VisitSession.objects.filter(visitor=visitor).order_by("-started_at", "-pk")
|
||
cutoff = timezone.now() - ONLINE_WINDOW
|
||
ft = (SourceClassification.objects.filter(visitor=visitor, scope="first_touch")
|
||
.first())
|
||
entries = (SourceClassification.objects
|
||
.filter(visitor=visitor, scope="session_entry")
|
||
.select_related("session") # session_id 随行带出，免逐行查询
|
||
.order_by("-session__started_at", "-pk")[:ATTR_SESSION_ENTRIES])
|
||
return ok({**_row(visitor, last_session, cutoff, ft),
|
||
"screen": visitor.screen, "timezone_name": visitor.timezone_name,
|
||
"last_ip": visitor.last_ip, "first_utm": visitor.first_utm or {},
|
||
"first_landing_path": visitor.first_landing_path,
|
||
"first_referrer_domain": visitor.first_referrer_domain,
|
||
"attribution": {"first_touch": _classification(ft),
|
||
"session_entries": [_classification(e, with_session=True)
|
||
for e in entries]},
|
||
"sessions": [_session_summary(s) for s in sessions]})
|
||
|
||
|
||
class VisitorTimelineView(EnvelopeMixin, APIView):
|
||
def get(self, request, visitor_id):
|
||
visitor = _get_visitor(visitor_id)
|
||
if not visitor:
|
||
return _not_found("visitor_not_found")
|
||
try:
|
||
days = int(request.query_params.get("days", TIMELINE_DEFAULT_DAYS))
|
||
except (TypeError, ValueError):
|
||
days = TIMELINE_DEFAULT_DAYS
|
||
days = max(1, min(days, TIMELINE_MAX_DAYS)) # 1-90 夹紧，非法值回落默认
|
||
|
||
today = timezone.localdate()
|
||
start = timezone.make_aware(
|
||
datetime.combine(today - timedelta(days=days - 1), time.min)) # 上海自然日窗口
|
||
# 倒序取满上限再翻正：截断保最新（更早的事件连同其独属会话不出现——若某会话事件被整段
|
||
# 截掉，该会话不出组；部分截掉的 page_view 缺失时其 page_stay 按规则独立成条）。
|
||
events = list(Event.objects.filter(visitor=visitor, occurred_at__gte=start)
|
||
.select_related("session") # 会话信息随行带出，免逐事件查询
|
||
.order_by("-occurred_at", "-pk")[:TIMELINE_MAX_EVENTS])
|
||
truncated = len(events) >= TIMELINE_MAX_EVENTS # 切片取满即窗口内可能还有更多
|
||
events.reverse()
|
||
|
||
groups = {} # date -> {session.pk/None: {"session":..., "events":[...]}}，插入序即正序
|
||
for e in events:
|
||
day = groups.setdefault(timezone.localtime(e.occurred_at).date(), {})
|
||
key = e.session.pk if e.session else None # session 为 NULL 的孤立事件并成一组
|
||
bucket = day.setdefault(key, {"session": e.session, "events": []})
|
||
bucket["events"].append(e)
|
||
|
||
return ok({"days": [{"date": d.isoformat(),
|
||
"sessions": [{"session_id": b["session"].session_id if b["session"] else None,
|
||
"started_at": _iso(b["session"].started_at)
|
||
if b["session"] else None,
|
||
"events": _merge_page_stay(b["events"])}
|
||
for b in groups[d].values()]}
|
||
for d in sorted(groups, reverse=True)], # 日期组倒序，日内会话/事件正序
|
||
"truncated": truncated}) # 前端区分"没动静"和"被截断"
|
||
|
||
|
||
class VisitorSessionView(EnvelopeMixin, APIView):
|
||
def get(self, request, visitor_id, session_id):
|
||
visitor = _get_visitor(visitor_id)
|
||
if not visitor:
|
||
return _not_found("visitor_not_found")
|
||
session = VisitSession.objects.filter(visitor=visitor, session_id=session_id).first()
|
||
if not session:
|
||
return _not_found("session_not_found")
|
||
events = Event.objects.filter(session=session).order_by("occurred_at", "pk") # (session,occurred_at) 索引
|
||
return ok({**_session_summary(session), "events": _merge_page_stay(events)})
|
||
|
||
|
||
class VisitorRawBatchesView(EnvelopeMixin, APIView):
|
||
"""访客原始上报批次（raw_batch）：排查"上报了为何没进报表"。
|
||
|
||
body 是脱敏后的整包 JSON 文本（敏感值已 [FILTERED]、被拒批次已截断），
|
||
前端以 <pre> 文本渲染（禁 v-html）。按 -received_at 倒序分页，走 (visitor,-received_at) 索引。
|
||
"""
|
||
|
||
def get(self, request, visitor_id):
|
||
visitor = _get_visitor(visitor_id)
|
||
if not visitor:
|
||
return _not_found("visitor_not_found")
|
||
qs = RawBatch.objects.filter(visitor=visitor)
|
||
total = qs.count()
|
||
try:
|
||
page = int(request.query_params.get("page", 1))
|
||
except (TypeError, ValueError):
|
||
page = 1
|
||
page = max(1, page)
|
||
batches = qs.order_by("-received_at", "-pk")[
|
||
(page - 1) * RAW_PAGE_SIZE: page * RAW_PAGE_SIZE]
|
||
return ok({"list": [{"id": b.id, "batch_id": b.batch_id, "status": b.status,
|
||
"event_count": b.event_count, "rejected_count": b.rejected_count,
|
||
"received_at": _iso(b.received_at), "body": b.body}
|
||
for b in batches],
|
||
"total": total, "page": page})
|