butubb
4e60524f37
在上游 MediaCrawler 之上新增一层： - 监控层 api/monitor/ —— 多博主/多笔记的定时采集、指标快照差分、报表、 企业微信通知。每轮采集写入独立目录，差分才成立。 - WebUI 登录鉴权 api/auth.py —— PBKDF2 口令 + 服务端会话，/api 全接口防护。 WebSocket 单独加依赖：BaseHTTPMiddleware 对 ws 作用域直接放行，覆盖不到。 - 全局平台切换 + 能力矩阵 —— 如实区分「爬虫模块支持」与「监控层已接线」， 未接通的平台直接拒绝建任务，而不是静默跑空。 - 监控库改用 MySQL 5.7（可回退 SQLite 供测试）：逐表强制 utf8mb4 （服务端与库默认都是 latin1），启动校验所连 schema 以防写错库， 连接池 recycle + pre_ping 应对 MySQL 的 8 小时空闲断连。 修复上游缺陷： - xhs/core.py: 主页抓取失败会跳掉整个博主，导致一条作品都抓不到， 而那份资料只喂给一个空函数。改为尽力而为，失败不中断。 - xhs/login.py: cookie 登录只注入 web_session，冷启动签名会失败。 新增 INJECT_ALL_COOKIES 开关（默认关闭，原有行为不变）。 - requirements.txt: 补上 websockets。它在上游 pyproject.toml 里有声明、 这里漏了，导致 uvicorn 没有 WebSocket 能力，实时日志流从未工作。 改动过的上游文件清单及合并方式见 UPSTREAM.md。 测试：492 passed（另有 1 个既有的 Windows/gbk 上游测试失败，与本改动无关）
303 lines
12 KiB
Python
303 lines
12 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 text
|
|
|
|
from api.main import app
|
|
from api.monitor import db as monitor_db
|
|
from api.monitor import platforms
|
|
from api.monitor.models import 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()
|
|
|
|
|
|
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 False
|
|
|
|
@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."""
|
|
response = await client.post(
|
|
"/api/monitor/tasks",
|
|
json={"name": "抖音任务", "mode": "creator", "platform": "dy", "targets": ["x"]},
|
|
)
|
|
assert response.status_code == 400
|
|
detail = response.json()["detail"]
|
|
assert "抖音" 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": "抖音任务", "mode": "creator", "platform": "dy", "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 real XHS task plus a Douyin task inserted directly, since the API
|
|
refuses to create the latter."""
|
|
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):
|
|
"""An empty task set must not degrade into "no filter"."""
|
|
await self._seed_two_platforms(client)
|
|
|
|
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
|
|
|
|
|
|
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()
|