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)
233 lines
9.0 KiB
Python
233 lines
9.0 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_monitor_comments.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项目根目录下的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。
|
|
|
|
"""Comment note-association, grouping, and the export endpoint."""
|
|
|
|
import csv
|
|
import io
|
|
|
|
import httpx
|
|
import pytest
|
|
import pytest_asyncio
|
|
|
|
from api.main import app
|
|
from api.monitor import db as monitor_db
|
|
from api.monitor.models import (
|
|
MODE_CREATOR,
|
|
MonitorComment,
|
|
MonitorNote,
|
|
MonitorTask,
|
|
)
|
|
|
|
TASK_NAME = "评论归属测试"
|
|
|
|
|
|
async def _seed():
|
|
"""Two works; three comments on the first, one on the second."""
|
|
async with monitor_db.get_session() as session:
|
|
task = MonitorTask(
|
|
name=TASK_NAME, platform="xhs", mode=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,
|
|
)
|
|
session.add(task)
|
|
await session.flush()
|
|
|
|
for note_id, title in (("note-a", "作品甲"), ("note-b", "作品乙")):
|
|
session.add(
|
|
MonitorNote(
|
|
task_id=task.id, note_id=note_id, title=title,
|
|
note_url=f"https://www.xiaohongshu.com/explore/{note_id}",
|
|
cover=f"https://img/{note_id}.jpg", creator_hash="h",
|
|
source_kind="video", published_at=None,
|
|
first_seen_run_id=1, first_seen_at=1_700_000_000_000,
|
|
last_seen_run_id=1, last_seen_at=1_700_000_000_000,
|
|
)
|
|
)
|
|
|
|
# note-a has three comments, note-b has one.
|
|
plan = [
|
|
("c1", "note-a", 1_700_000_001_000),
|
|
("c2", "note-a", 1_700_000_002_000),
|
|
("c3", "note-a", 1_700_000_003_000),
|
|
("c4", "note-b", 1_700_000_004_000),
|
|
]
|
|
for comment_id, note_id, seen_at in plan:
|
|
session.add(
|
|
MonitorComment(
|
|
task_id=task.id, note_id=note_id, comment_id=comment_id,
|
|
content=f"内容-{comment_id}", nickname="u***r", creator_hash="h",
|
|
create_time=seen_at, like_count=1, sub_comment_count=0,
|
|
parent_comment_id="", first_seen_run_id=1, first_seen_at=seen_at,
|
|
)
|
|
)
|
|
return task.id
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
async def client(tmp_path):
|
|
monitor_db.set_sqlite_path(tmp_path / "monitor.db")
|
|
await monitor_db.init_db()
|
|
await _seed()
|
|
|
|
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 TestCommentsCarryTheirNote:
|
|
@pytest.mark.asyncio
|
|
async def test_each_comment_names_its_work(self, client):
|
|
"""A bare note_id is unreadable -- the title is the whole point."""
|
|
response = await client.get("/api/monitor/comments")
|
|
assert response.status_code == 200
|
|
|
|
comments = response.json()["comments"]
|
|
assert len(comments) == 4
|
|
|
|
by_id = {c["comment_id"]: c for c in comments}
|
|
assert by_id["c1"]["note_title"] == "作品甲"
|
|
assert by_id["c1"]["note_url"].endswith("note-a")
|
|
assert by_id["c1"]["note_cover"].endswith("note-a.jpg")
|
|
assert by_id["c4"]["note_title"] == "作品乙"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_note_id_filters_the_stream(self, client):
|
|
response = await client.get("/api/monitor/comments", params={"note_id": "note-a"})
|
|
comments = response.json()["comments"]
|
|
assert {c["comment_id"] for c in comments} == {"c1", "c2", "c3"}
|
|
|
|
|
|
class TestGroupByNote:
|
|
@pytest.mark.asyncio
|
|
async def test_groups_bucket_by_work(self, client):
|
|
response = await client.get("/api/monitor/comments", params={"group_by": "note"})
|
|
body = response.json()
|
|
|
|
assert "groups" in body
|
|
assert body["total"] == 4
|
|
|
|
groups = {g["note_id"]: g for g in body["groups"]}
|
|
assert set(groups) == {"note-a", "note-b"}
|
|
assert len(groups["note-a"]["comments"]) == 3
|
|
assert len(groups["note-b"]["comments"]) == 1
|
|
assert groups["note-a"]["note_title"] == "作品甲"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_newest_group_comes_first(self, client):
|
|
"""The UI expands the first group by default, so it must be the newest."""
|
|
response = await client.get("/api/monitor/comments", params={"group_by": "note"})
|
|
groups = response.json()["groups"]
|
|
# note-b's only comment is the most recent overall.
|
|
assert groups[0]["note_id"] == "note-b"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_flat_shape_is_unchanged_without_the_flag(self, client):
|
|
body = (await client.get("/api/monitor/comments")).json()
|
|
assert "comments" in body and "groups" not in body
|
|
|
|
|
|
class TestCommentNoteFilterOptions:
|
|
@pytest.mark.asyncio
|
|
async def test_options_carry_counts_and_titles(self, client):
|
|
response = await client.get("/api/monitor/comment-notes")
|
|
assert response.status_code == 200
|
|
|
|
notes = {n["note_id"]: n for n in response.json()["notes"]}
|
|
assert notes["note-a"]["comment_count"] == 3
|
|
assert notes["note-b"]["comment_count"] == 1
|
|
assert notes["note-a"]["note_title"] == "作品甲"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_scoped_to_a_task(self, client):
|
|
tasks = (await client.get("/api/monitor/tasks")).json()["tasks"]
|
|
task_id = tasks[0]["id"]
|
|
|
|
scoped = await client.get("/api/monitor/comment-notes", params={"task_id": task_id})
|
|
assert len(scoped.json()["notes"]) == 2
|
|
|
|
# A task with no comments yields an empty list, not an error.
|
|
other = await client.get("/api/monitor/comment-notes", params={"task_id": 9999})
|
|
assert other.json()["notes"] == []
|
|
|
|
|
|
class TestExport:
|
|
@pytest.mark.asyncio
|
|
async def test_csv_has_a_bom_so_excel_does_not_mangle_chinese(self, client):
|
|
response = await client.get("/api/monitor/export", params={"kind": "comments"})
|
|
assert response.status_code == 200
|
|
assert response.content.startswith(b"\xef\xbb\xbf")
|
|
assert "attachment" in response.headers["content-disposition"]
|
|
|
|
text = response.content.decode("utf-8-sig")
|
|
rows = list(csv.DictReader(io.StringIO(text)))
|
|
assert len(rows) == 4
|
|
assert rows[0]["所属作品"] in ("作品甲", "作品乙")
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_notes_export(self, client):
|
|
response = await client.get(
|
|
"/api/monitor/export", params={"kind": "notes", "format": "csv"}
|
|
)
|
|
rows = list(csv.DictReader(io.StringIO(response.content.decode("utf-8-sig"))))
|
|
assert {r["作品ID"] for r in rows} == {"note-a", "note-b"}
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_xlsx_is_a_readable_workbook(self, client):
|
|
from openpyxl import load_workbook
|
|
|
|
response = await client.get(
|
|
"/api/monitor/export", params={"kind": "comments", "format": "xlsx"}
|
|
)
|
|
assert response.status_code == 200
|
|
|
|
workbook = load_workbook(io.BytesIO(response.content))
|
|
sheet = workbook.active
|
|
assert sheet.max_row == 5 # header + four comments
|
|
assert sheet.cell(row=1, column=1).value == "所属作品"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_report_export(self, client):
|
|
response = await client.get(
|
|
"/api/monitor/export",
|
|
params={"kind": "report", "days": 3},
|
|
)
|
|
rows = list(csv.DictReader(io.StringIO(response.content.decode("utf-8-sig"))))
|
|
assert len(rows) == 3
|
|
assert "日期" in rows[0]
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_unknown_kind_and_format_are_rejected(self, client):
|
|
assert (
|
|
await client.get("/api/monitor/export", params={"kind": "nope"})
|
|
).status_code == 400
|
|
assert (
|
|
await client.get("/api/monitor/export", params={"kind": "notes", "format": "pdf"})
|
|
).status_code == 400
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_empty_selection_is_a_404_not_an_empty_file(self, client):
|
|
"""An empty download looks like a bug; say so instead."""
|
|
response = await client.get(
|
|
"/api/monitor/export", params={"kind": "comments", "note_id": "no-such-note"}
|
|
)
|
|
assert response.status_code == 404
|