Files
MediaCrawler/tests/test_platforms.py
T
butubb e77e5e2f15
Deploy VitePress site to Pages / build (push) Canceled after 0s
Deploy VitePress site to Pages / Deploy (push) Canceled after 0s
fix(report): 空的任务集合被当成了「不限制平台」,导致报表串平台数据
现象:切到抖音,报表里显示的是小红书的数据。

根因是报告聚合里的一行真值判断:

    scope = list(task_ids) if task_ids else None

空列表是假值,而空列表在这里的含义是「这个平台一个任务都没有」,不是「不限制平台」。
于是 platform=dy 且抖音还没有任务时,_resolve_scope 返回的 [] 被翻译成了 None,
聚合范围从「抖音的任务」变成了**全部任务** —— 小红书的数字就这么显示在了抖音页面上。
顺带 task_ids 也回成 None,界面会显示成「全部任务」。

改成 `is not None`。空列表进去就让 in_([]) 恒假,结果为空,这才是对的。

排查时把所有同类写法过了一遍,只有这一处错,其余(service.py 的 10 处作用域judgement、
_resolve_scope、export)用的都是 `is not None`。

测试:新增两条,并且**验证过它们在修复前会红**(失败信息就是 assert 42 == 0 ——
查一个没有任何任务的平台,却返回了小红书那条作品的 42 个赞)。

同时修掉一条空跑的测试:test_a_platform_with_no_tasks_yields_empty_not_everything
原先种了任务却没有作品/指标数据,于是过滤生效与否结果都是 0,什么都测不出来 ——
这正是这个 bug 能活下来的原因。现在它会真的塞一条作品+快照进去,并在末尾断言
「小红书自己的报表看得到那条数据」,用来证明前面那两个 0 是过滤出来的而不是没数据。
2026-10-10 15:00:12 +08:00

369 lines
15 KiB
Python

# -*- coding: utf-8 -*-
# Copyright (c) 2025 [email protected]
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/tests/test_platforms.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
# 声明:本代码仅供学习和研究目的使用。使用者应遵守以下原则:
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
# 3. 不得进行大规模爬取或对平台造成运营干扰。
# 4. 应合理控制请求频率,避免给目标平台带来不必要的负担。
# 5. 不得用于任何非法或不当的用途。
#
# 详细许可条款请参阅根目录下的LICENSE文件。
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
"""Platform capability matrix, platform scoping, and per-platform settings."""
import httpx
import pytest
import pytest_asyncio
from sqlalchemy import select, text
from tools.time_util import get_current_timestamp
from api.main import app
from api.monitor import adapters
from api.monitor import db as monitor_db
from api.monitor import platforms
from api.monitor.models import MonitorNote, MonitorNoteMetric, MonitorTask
XHS_TARGET = "5f58bd990000000001003753"
@pytest_asyncio.fixture
async def client(tmp_path):
monitor_db.set_sqlite_path(tmp_path / "monitor.db")
await monitor_db.init_db()
transport = httpx.ASGITransport(app=app)
async with httpx.AsyncClient(transport=transport, base_url="http://test") as http_client:
yield http_client
await monitor_db.dispose_engine()
async def _seed_note_with_one_snapshot(task_name: str) -> None:
"""给某个任务塞一条作品和一次指标快照。
过滤类测试**必须有真数据**才有意义 —— 库里空着的话,过滤有没有生效结果都是 0,
测试就变成了空跑(这个坑踩过一次:一个报表串数据的 bug 因此没被拦住)。
"""
async with monitor_db.get_session() as session:
task = await session.scalar(select(MonitorTask).where(MonitorTask.name == task_name))
now = get_current_timestamp()
session.add(
MonitorNote(
task_id=task.id, note_id="seed-note", title="seed", note_url="",
cover="", creator_hash="", source_kind="", published_at=None,
first_seen_run_id=1, first_seen_at=now,
last_seen_run_id=1, last_seen_at=now,
)
)
session.add(
MonitorNoteMetric(
task_id=task.id, note_id="seed-note", run_id=1, captured_at=now,
liked_count=42, comment_count=0, collected_count=0, share_count=0,
raw_liked_count="42", raw_comment_count="0",
raw_collected_count="0", raw_share_count="0",
)
)
class TestCapabilityMatrix:
@pytest.mark.asyncio
async def test_matrix_is_exposed_to_the_ui(self, client):
body = (await client.get("/api/config/platforms")).json()
by_value = {p["value"]: p for p in body["platforms"]}
assert set(by_value) == {"xhs", "dy", "ks", "bili", "wb", "tieba", "zhihu"}
# Every entry must say whether monitoring is actually wired up -- this is
# what stops the UI offering a platform that can never produce data.
assert all("monitor_wired" in p for p in body["platforms"])
assert by_value["xhs"]["monitor_wired"] is True
assert by_value["dy"]["monitor_wired"] is True
def test_every_wired_platform_has_an_adapter(self):
"""能力矩阵说「接通了」,就必须真的有一套适配管子。
两个注册表(platforms.PLATFORM_CAPABILITIES 与 adapters.ADAPTERS)分开是有意的
—— 前者是给前端看的能力描述,后者是爬虫的管道细节。代价是它们可能漂移,
所以在这里钉一条:凡声明接通的,必须能找到适配器。
"""
for platform in platforms.all_platforms():
if platforms.is_monitor_wired(platform):
assert adapters.has_adapter(platform), f"{platform} 声明接通但没有适配器"
@pytest.mark.asyncio
async def test_target_hints_are_exposed_for_wired_platforms(self, client):
"""前端的目标输入框拿它做 placeholder —— 让用户看到本平台该粘什么样的链接。"""
body = (await client.get("/api/config/platforms")).json()
by_value = {p["value"]: p for p in body["platforms"]}
assert "douyin.com/user/" in by_value["dy"]["target_hints"]["creator"]
assert "douyin.com/video/" in by_value["dy"]["target_hints"]["note"]
assert "xiaohongshu.com" in by_value["xhs"]["target_hints"]["creator"]
@pytest.mark.asyncio
async def test_metrics_are_per_platform_and_labelled(self, client):
body = (await client.get("/api/config/platforms")).json()
by_value = {p["value"]: p for p in body["platforms"]}
# Bilibili has play count and danmaku; Xiaohongshu has neither.
assert "video_play_count" in by_value["bili"]["metrics"]
assert "video_danmaku" in by_value["bili"]["metrics"]
assert "video_play_count" not in by_value["xhs"]["metrics"]
# Every metric shown to a user must have a human label.
for capability in body["platforms"]:
for metric in capability["metrics"]:
assert capability["metric_labels"][metric]
def test_unknown_platform_is_not_monitor_wired(self):
assert platforms.is_known("xhs") is True
assert platforms.is_known("myspace") is False
assert platforms.is_monitor_wired("myspace") is False
class TestTaskCreationGuard:
@pytest.mark.asyncio
async def test_unwired_platform_is_rejected_with_an_explanation(self, client):
"""Accepting it would create a task that silently never produces data.
用 B站 而不是抖音:抖音现在接通了,不再是「已知但未接通」的例子。
"""
response = await client.post(
"/api/monitor/tasks",
json={"name": "B站任务", "mode": "creator", "platform": "bili", "targets": ["x"]},
)
assert response.status_code == 400
detail = response.json()["detail"]
assert "B站" in detail
assert "尚未接通" in detail
@pytest.mark.asyncio
async def test_unknown_platform_is_rejected(self, client):
response = await client.post(
"/api/monitor/tasks",
json={"name": "x", "mode": "creator", "platform": "myspace", "targets": ["x"]},
)
assert response.status_code == 400
@pytest.mark.asyncio
async def test_no_task_row_is_created_when_rejected(self, client):
await client.post(
"/api/monitor/tasks",
json={"name": "B站任务", "mode": "creator", "platform": "bili", "targets": ["x"]},
)
assert (await client.get("/api/monitor/tasks")).json()["tasks"] == []
@pytest.mark.asyncio
async def test_xhs_still_works_and_is_the_default(self, client):
explicit = await client.post(
"/api/monitor/tasks",
json={"name": "显式", "mode": "creator", "platform": "xhs", "targets": [XHS_TARGET]},
)
assert explicit.status_code == 201
defaulted = await client.post(
"/api/monitor/tasks",
json={"name": "默认", "mode": "creator", "targets": [XHS_TARGET]},
)
assert defaulted.status_code == 201
tasks = (await client.get("/api/monitor/tasks")).json()["tasks"]
assert {t["platform"] for t in tasks} == {"xhs"}
class TestPlatformScoping:
async def _seed_two_platforms(self, client):
"""One XHS task created through the API, plus a Douyin task inserted
directly so its fields can be pinned exactly."""
await client.post(
"/api/monitor/tasks",
json={"name": "小红书任务", "mode": "creator", "targets": [XHS_TARGET]},
)
async with monitor_db.get_session() as session:
session.add(
MonitorTask(
name="抖音任务", platform="dy", mode="creator", enabled=True,
interval_minutes=60, max_notes_count=20, enable_comments=True,
max_comments_count=50, run_timeout_seconds=3600,
notify_enabled=False, created_at=0, updated_at=0,
)
)
@pytest.mark.asyncio
async def test_tasks_are_filtered_by_platform(self, client):
await self._seed_two_platforms(client)
all_tasks = (await client.get("/api/monitor/tasks")).json()["tasks"]
assert len(all_tasks) == 2
xhs_only = (await client.get("/api/monitor/tasks", params={"platform": "xhs"})).json()
assert [t["name"] for t in xhs_only["tasks"]] == ["小红书任务"]
dy_only = (await client.get("/api/monitor/tasks", params={"platform": "dy"})).json()
assert [t["name"] for t in dy_only["tasks"]] == ["抖音任务"]
@pytest.mark.asyncio
async def test_overview_is_scoped(self, client):
await self._seed_two_platforms(client)
assert (await client.get("/api/monitor/overview")).json()["tasks"] == 2
assert (
await client.get("/api/monitor/overview", params={"platform": "xhs"})
).json()["tasks"] == 1
@pytest.mark.asyncio
async def test_a_platform_with_no_tasks_yields_empty_not_everything(self, client):
"""空的任务集合不能退化成「不加过滤」。
**这里必须真的有数据。** 没有数据时,过滤生效与否结果都是 0 —— 这条测试原先
就栽在这个空跑上,所以没能拦下一个报表串数据的 bug(切到抖音,报表里却出现
小红书的数据)。最后那段「小红书自己的报表看得到」就是为了证明这些数据确实
存在、上面那两个 0 是过滤出来的。
"""
await self._seed_two_platforms(client)
await _seed_note_with_one_snapshot("小红书任务")
body = (await client.get("/api/monitor/notes", params={"platform": "bili"})).json()
assert body["notes"] == []
report = (
await client.get("/api/monitor/report", params={"platform": "bili"})
).json()
assert report["totals"]["liked_count_delta"] == 0
assert report["note_count"] == 0
xhs = (
await client.get("/api/monitor/report", params={"platform": "xhs"})
).json()
assert xhs["note_count"] == 1
class TestPerPlatformSettings:
@pytest.mark.asyncio
async def test_each_platform_keeps_its_own_values(self, client):
await client.put(
"/api/settings",
params={"platform": "xhs"},
json={"platform.xhs.crawl_sleep_sec": 3},
)
await client.put(
"/api/settings",
params={"platform": "dy"},
json={"platform.dy.crawl_sleep_sec": 9},
)
xhs = (await client.get("/api/settings", params={"platform": "xhs"})).json()
dy = (await client.get("/api/settings", params={"platform": "dy"})).json()
assert xhs["values"]["platform.xhs.crawl_sleep_sec"] == 3
assert dy["values"]["platform.dy.crawl_sleep_sec"] == 9
@pytest.mark.asyncio
async def test_system_settings_are_shared_across_platforms(self, client):
await client.put(
"/api/settings",
params={"platform": "xhs"},
json={"system.active_hours_start": 8},
)
dy = (await client.get("/api/settings", params={"platform": "dy"})).json()
assert dy["values"]["system.active_hours_start"] == 8
# ...and the system specs are present in every platform's response.
assert "system.active_hours_end" in dy["values"]
@pytest.mark.asyncio
async def test_a_key_for_another_platform_is_rejected(self, client):
"""Writing xhs's key while scoped to dy would land somewhere unexpected."""
response = await client.put(
"/api/settings",
params={"platform": "dy"},
json={"platform.xhs.crawl_sleep_sec": 5},
)
assert response.status_code == 400
@pytest.mark.asyncio
async def test_cookies_are_per_platform(self, client):
await client.post(
"/api/monitor/cookie",
params={"platform": "xhs"},
json={"cookie": "web_session=xhs-secret"},
)
xhs = (await client.get("/api/monitor/cookie", params={"platform": "xhs"})).json()
dy = (await client.get("/api/monitor/cookie", params={"platform": "dy"})).json()
assert xhs["present"] is True
assert dy["present"] is False
# The old endpoint still defaults to Xiaohongshu.
assert (await client.get("/api/monitor/cookie")).json()["present"] is True
class TestLegacyKeyMigration:
@pytest.mark.asyncio
async def test_old_flat_keys_are_moved_to_the_new_namespace(self, tmp_path):
"""Existing installs must not lose their cookie on upgrade."""
monitor_db.set_sqlite_path(tmp_path / "monitor.db")
await monitor_db.init_db()
async with monitor_db.get_engine().begin() as conn:
await conn.execute(
text(
"INSERT INTO monitor_setting (key, value, updated_at) "
"VALUES ('xhs_cookie', 'web_session=legacy', 1)"
)
)
await conn.execute(
text(
"INSERT INTO monitor_setting (key, value, updated_at) "
"VALUES ('wecom_webhook', 'https://qyapi.weixin.qq.com/x', 1)"
)
)
# Re-running init performs the rename.
await monitor_db.init_db()
async with monitor_db.get_engine().begin() as conn:
rows = dict(
(await conn.execute(text("SELECT key, value FROM monitor_setting"))).all()
)
assert rows.get("platform.xhs.cookie") == "web_session=legacy"
assert rows.get("system.wecom_webhook") == "https://qyapi.weixin.qq.com/x"
assert "xhs_cookie" not in rows
assert "wecom_webhook" not in rows
await monitor_db.dispose_engine()
@pytest.mark.asyncio
async def test_migration_is_idempotent_and_keeps_the_newer_value(self, tmp_path):
monitor_db.set_sqlite_path(tmp_path / "monitor.db")
await monitor_db.init_db()
async with monitor_db.get_engine().begin() as conn:
await conn.execute(
text(
"INSERT INTO monitor_setting (key, value, updated_at) VALUES "
"('platform.xhs.cookie', 'current', 2), ('xhs_cookie', 'stale', 1)"
)
)
await monitor_db.init_db()
async with monitor_db.get_engine().begin() as conn:
rows = dict(
(await conn.execute(text("SELECT key, value FROM monitor_setting"))).all()
)
assert rows.get("platform.xhs.cookie") == "current"
assert "xhs_cookie" not in rows
await monitor_db.dispose_engine()