14 changed files with 766 additions and 158 deletions
+5 -1
View File
@@ -5,6 +5,7 @@ from datetime import UTC, datetime
from sqlalchemy import Engine, create_engine, event
from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
from sqlalchemy.pool import NullPool
from app.config import get_settings
@@ -20,7 +21,10 @@ def create_sqlite_engine(database_url: str):
db_path.parent.mkdir(parents=True, exist_ok=True)
connect_args = {"check_same_thread": False, "timeout": 10}
engine = create_engine(database_url, connect_args=connect_args)
engine_kwargs = {"connect_args": connect_args}
if database_url.startswith("sqlite:///") and database_url != "sqlite:///:memory:":
engine_kwargs["poolclass"] = NullPool
engine = create_engine(database_url, **engine_kwargs)
engine.dialect.connect_args = connect_args
@event.listens_for(engine, "connect")
+26 -5
View File
@@ -94,15 +94,36 @@ class TikHubClient:
status_code=response.status_code,
)
if response.is_error:
raise PlatformAPIError(
f"External API returned HTTP {response.status_code}",
error_type="api_error",
status_code=response.status_code,
)
if attempt >= self.max_retries:
raise PlatformAPIError(
self._format_api_error(response),
error_type="api_error",
status_code=response.status_code,
)
time.sleep(2**attempt)
continue
return response.json()
raise PlatformAPIError("External API request failed", error_type="api_error", status_code=last_status)
def _format_api_error(self, response: httpx.Response) -> str:
message = f"External API returned HTTP {response.status_code}"
detail = self._response_error_detail(response)
return f"{message}: {detail}" if detail else message
def _response_error_detail(self, response: httpx.Response) -> str | None:
try:
payload = response.json()
except ValueError:
text = response.text.strip()
return text[:200] if text else None
if isinstance(payload, dict):
for key in ("message_zh", "message", "error", "detail"):
value = payload.get(key)
if value:
return str(value)[:200]
return None
def parse_timestamp(value: Any) -> datetime | None:
if value in (None, ""):
+4 -5
View File
@@ -3,6 +3,7 @@ import json
from concurrent.futures import ThreadPoolExecutor
from collections.abc import Callable
from datetime import UTC, datetime
from zoneinfo import ZoneInfo
from sqlalchemy import func, select
from sqlalchemy.orm import Session, sessionmaker
@@ -22,6 +23,7 @@ RUNNING_TASK_MESSAGE = "当前有正在运行的任务,请稍后再试"
RESTART_ERROR_MESSAGE = "系统重启,任务被中断"
STALE_PROGRESS_THRESHOLD_SECONDS = 10 * 60
STALE_PROGRESS_ERROR_TYPE = "stale_progress_timeout"
DISPLAY_TIMEZONE = ZoneInfo("Asia/Shanghai")
task_executor = ThreadPoolExecutor(max_workers=1)
@@ -183,10 +185,7 @@ def hydrate_task_progress(session: Session, task: Task) -> Task:
task.display_number = display_number
task.display_id = str(display_number)
task.created_at_label = format_datetime_minute(task.created_at)
task.scale_label = (
f"{PLATFORM_LABELS.get(task.platform, task.platform)} · "
f"{task.hotspot_limit}热点 × {task.item_limit_per_hotspot}内容 × {task.comment_limit_per_item}评论"
)
task.scale_label = f"{task.hotspot_limit}热点 × {task.item_limit_per_hotspot}内容 × {task.comment_limit_per_item}评论"
task.error_summary = build_task_error_summary(task)
task.hotspots_count = session.scalar(select(func.count(Hotspot.id)).where(Hotspot.task_id == task.id)) or 0
task.comments_count = session.scalar(select(func.count(Comment.id)).where(Comment.task_id == task.id)) or 0
@@ -230,7 +229,7 @@ def calculate_task_display_number(session: Session, task: Task) -> int:
def format_datetime_minute(value: datetime | None) -> str:
value = ensure_utc_datetime(value)
return value.strftime("%Y-%m-%d %H:%M") if value else ""
return value.astimezone(DISPLAY_TIMEZONE).strftime("%Y-%m-%d %H:%M") if value else ""
def build_task_error_summary(task: Task) -> str | None:
+502 -66
View File
@@ -1,101 +1,537 @@
:root {
--background: #f8fafc;
--foreground: #0f172a;
--muted: #f1f5f9;
--muted-foreground: #64748b;
--card: #ffffff;
--card-foreground: #0f172a;
--border: #e2e8f0;
--input: #cbd5e1;
--primary: #0f172a;
--primary-foreground: #ffffff;
--secondary: #f1f5f9;
--secondary-foreground: #0f172a;
--accent: #f8fafc;
--accent-foreground: #0f172a;
--destructive: #dc2626;
--success: #16a34a;
--warning: #d97706;
--ring: rgba(15, 23, 42, 0.18);
--radius: 8px;
}
body {
background: #f5f7fb;
color: #172033;
}
.card {
border-radius: 8px;
border: 1px solid #dfe5ef;
box-shadow: 0 10px 28px rgba(31, 42, 68, 0.06);
}
.navbar {
background: #fff !important;
}
.hero-band {
align-items: flex-end;
background:
linear-gradient(135deg, rgba(12, 22, 40, 0.92), rgba(29, 80, 108, 0.78)),
url("https://images.unsplash.com/photo-1551288049-bebda4e38f71?auto=format&fit=crop&w=1600&q=80");
background-position: center;
background-size: cover;
border-radius: 8px;
color: #fff;
display: flex;
justify-content: space-between;
min-height: 300px;
padding: 42px;
}
.hero-copy {
max-width: 680px;
}
.hero-copy h1 {
font-size: 48px;
font-weight: 700;
background: var(--background);
color: var(--foreground);
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
letter-spacing: 0;
margin-bottom: 14px;
min-height: 100vh;
}
.hero-copy p:not(.eyebrow) {
color: rgba(255, 255, 255, 0.84);
font-size: 18px;
line-height: 1.7;
a {
color: inherit;
}
.container {
max-width: 1180px;
}
.app-navbar {
background: rgba(255, 255, 255, 0.92) !important;
border-bottom: 1px solid var(--border);
backdrop-filter: blur(14px);
}
.app-navbar .container {
min-height: 56px;
}
.navbar-brand {
color: var(--foreground);
font-size: 15px;
letter-spacing: 0;
}
.nav-link {
border-radius: 6px;
color: var(--muted-foreground);
font-size: 14px;
padding: 6px 10px;
}
.nav-link:hover {
background: var(--secondary);
color: var(--foreground);
}
.breadcrumb {
color: var(--muted-foreground);
font-size: 13px;
margin-bottom: 20px;
}
.breadcrumb a {
color: var(--muted-foreground);
text-decoration: none;
}
.breadcrumb a:hover {
color: var(--foreground);
}
.tool-card,
.card,
.accordion-item {
background: var(--card);
border: 1px solid var(--border);
border-radius: var(--radius);
box-shadow: 0 1px 2px rgba(15, 23, 42, 0.04);
color: var(--card-foreground);
overflow: hidden;
}
.card-body {
padding: 20px;
}
.card-header,
.section-heading {
background: var(--card);
border-bottom: 1px solid var(--border);
padding: 16px 20px;
}
.section-heading {
align-items: center;
display: flex;
gap: 16px;
justify-content: space-between;
}
.section-heading h2,
.page-heading h1,
.page-title {
color: var(--foreground);
font-size: 22px;
font-weight: 650;
letter-spacing: 0;
line-height: 1.25;
margin: 0;
}
.hero-actions {
.page-heading {
align-items: flex-start;
display: flex;
flex-wrap: wrap;
gap: 12px;
gap: 16px;
justify-content: space-between;
margin-bottom: 18px;
}
.section-kicker,
.eyebrow {
color: #71d4c7;
font-size: 13px;
font-weight: 700;
color: var(--muted-foreground);
font-size: 12px;
font-weight: 650;
letter-spacing: 0;
margin: 0 0 6px;
text-transform: uppercase;
}
.metric-box {
background: #f8fafc;
border: 1px solid #e3e9f2;
border-radius: 8px;
.hero-band {
background: var(--card);
border: 1px solid var(--border);
border-radius: var(--radius);
box-shadow: 0 1px 2px rgba(15, 23, 42, 0.04);
color: var(--foreground);
padding: 30px;
}
.hero-shell {
align-items: flex-end;
display: flex;
gap: 28px;
justify-content: space-between;
}
.hero-copy {
max-width: 700px;
}
.hero-copy h1 {
color: var(--foreground);
font-size: 34px;
font-weight: 700;
letter-spacing: 0;
line-height: 1.15;
margin: 0 0 12px;
}
.hero-copy p:not(.eyebrow) {
color: var(--muted-foreground);
font-size: 15px;
line-height: 1.75;
margin: 0;
}
.hero-metrics {
display: grid;
gap: 10px;
grid-template-columns: repeat(3, minmax(84px, 1fr));
min-width: 320px;
}
.hero-metric {
background: var(--muted);
border: 1px solid var(--border);
border-radius: var(--radius);
padding: 12px;
}
.hero-metric strong {
display: block;
font-size: 18px;
line-height: 1.2;
}
.hero-metric span {
color: var(--muted-foreground);
display: block;
font-size: 12px;
margin-top: 4px;
}
.btn {
border-radius: 6px;
font-size: 14px;
font-weight: 500;
}
.btn-primary {
background: var(--primary);
border-color: var(--primary);
color: var(--primary-foreground);
}
.btn-primary:hover,
.btn-primary:focus {
background: #1e293b;
border-color: #1e293b;
}
.btn-outline-primary,
.btn-outline-secondary {
background: var(--card);
border-color: var(--border);
color: var(--foreground);
}
.btn-outline-primary:hover,
.btn-outline-secondary:hover {
background: var(--secondary);
border-color: var(--border);
color: var(--foreground);
}
.form-label {
color: var(--foreground);
font-size: 13px;
font-weight: 600;
}
.form-control,
.form-select {
border-color: var(--input);
border-radius: 6px;
color: var(--foreground);
font-size: 14px;
min-height: 40px;
}
.form-control:focus,
.form-select:focus {
border-color: var(--foreground);
box-shadow: 0 0 0 3px var(--ring);
}
.form-text {
color: var(--muted-foreground) !important;
}
.badge {
border-radius: 999px;
font-size: 12px;
font-weight: 600;
letter-spacing: 0;
padding: 5px 9px;
}
.bg-success,
.text-bg-success {
background-color: #dcfce7 !important;
color: #166534 !important;
}
.bg-danger,
.text-bg-danger {
background-color: #fee2e2 !important;
color: #991b1b !important;
}
.bg-warning,
.text-bg-warning {
background-color: #fef3c7 !important;
color: #92400e !important;
}
.bg-secondary,
.text-bg-secondary {
background-color: var(--secondary) !important;
color: var(--secondary-foreground) !important;
}
.text-bg-light {
background: var(--secondary) !important;
color: var(--foreground) !important;
}
.alert {
border-radius: var(--radius);
font-size: 14px;
margin-bottom: 16px;
}
.alert-info {
background: #eff6ff;
border-color: #bfdbfe;
color: #1e3a8a;
}
.alert-warning {
background: #fffbeb;
border-color: #fde68a;
color: #92400e;
}
.alert-danger {
background: #fef2f2;
border-color: #fecaca;
color: #991b1b;
}
.alert-secondary {
background: var(--secondary);
border-color: var(--border);
color: var(--foreground);
}
.metric-box,
.stat-card {
background: var(--card);
border: 1px solid var(--border);
border-radius: var(--radius);
height: 100%;
padding: 14px;
padding: 16px;
}
.status-panel {
background: #fff;
border: 1px solid #dfe5ef;
border-radius: 8px;
padding: 32px;
.metric-box strong,
.stat-card strong {
color: var(--foreground);
display: block;
font-size: 18px;
font-weight: 650;
line-height: 1.35;
margin: 4px 0;
}
.status-panel-danger {
border-color: #f1b8b8;
.app-table {
color: var(--foreground);
min-width: 760px;
}
.app-table thead th {
background: var(--muted);
border-bottom: 1px solid var(--border);
color: var(--muted-foreground);
font-size: 12px;
font-weight: 650;
height: 42px;
letter-spacing: 0;
text-transform: none;
white-space: nowrap;
}
.app-table td {
border-color: var(--border);
padding-bottom: 14px;
padding-top: 14px;
vertical-align: middle;
}
.app-table tbody tr:hover {
background: var(--accent);
}
.task-number {
align-items: center;
background: var(--secondary);
border: 1px solid var(--border);
border-radius: 999px;
color: var(--foreground);
display: inline-flex;
font-weight: 650;
height: 30px;
justify-content: center;
min-width: 30px;
padding: 0 9px;
}
.task-progress {
height: 10px;
background: var(--secondary);
border-radius: 999px;
height: 8px;
}
.progress-bar {
background-color: var(--primary);
}
.report-progress {
height: 10px;
background: var(--secondary);
height: 8px;
}
.task-overview {
border-top: 0;
}
.progress-summary {
align-items: center;
display: flex;
flex-wrap: wrap;
gap: 10px;
}
.hotspot-item {
border-color: var(--border);
margin-bottom: 10px;
}
.accordion-button {
background: var(--card);
color: var(--foreground);
font-size: 15px;
font-weight: 600;
gap: 10px;
padding: 16px 18px;
}
.accordion-button:not(.collapsed) {
background: var(--muted);
box-shadow: none;
color: var(--foreground);
}
.accordion-button:focus {
border-color: var(--border);
box-shadow: 0 0 0 3px var(--ring);
}
.content-item-row {
align-items: center;
display: flex;
gap: 14px;
justify-content: space-between;
}
.content-item-title {
color: var(--foreground);
display: block;
font-weight: 600;
line-height: 1.45;
overflow-wrap: anywhere;
}
.content-item-meta {
color: var(--muted-foreground);
display: block;
font-size: 12px;
margin-top: 3px;
overflow-wrap: anywhere;
}
.report-summary {
background: var(--muted);
border: 1px solid var(--border);
border-radius: var(--radius);
padding: 16px;
}
.comment-card {
background: var(--card);
border: 1px solid var(--border);
border-radius: var(--radius);
padding: 12px;
}
.empty-state,
.status-panel {
background: var(--card);
border: 1px solid var(--border);
border-radius: var(--radius);
padding: 32px;
text-align: center;
}
.status-panel-danger {
border-color: #fecaca;
}
@media (max-width: 992px) {
.hero-shell {
align-items: flex-start;
flex-direction: column;
}
.hero-metrics {
min-width: 0;
width: 100%;
}
}
@media (max-width: 768px) {
main.container {
padding-left: 14px;
padding-right: 14px;
}
.hero-band {
align-items: flex-start;
flex-direction: column;
min-height: 360px;
padding: 28px;
padding: 22px;
}
.hero-copy h1 {
font-size: 36px;
font-size: 28px;
}
.hero-metrics {
grid-template-columns: 1fr;
}
.section-heading,
.page-heading,
.content-item-row {
align-items: flex-start;
flex-direction: column;
}
.card-body {
padding: 16px;
}
.content-item-row .btn {
width: 100%;
}
.accordion-button {
align-items: flex-start;
}
}
+3 -3
View File
@@ -5,14 +5,14 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{% block title %}热榜评论分析工具{% endblock %}</title>
<link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
<link href="/static/app.css" rel="stylesheet">
<link href="/static/app.css?v=shadcn-ui-refresh" rel="stylesheet">
<script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
<script src="/static/app.js" defer></script>
</head>
<body>
<nav class="navbar navbar-expand-lg bg-body-tertiary border-bottom">
<nav class="navbar navbar-expand-lg app-navbar">
<div class="container">
<a class="navbar-brand" href="/">热榜评论分析工具</a>
<a class="navbar-brand fw-semibold" href="/">热榜评论雷达</a>
<div class="navbar-nav">
<a class="nav-link" href="/">任务列表</a>
</div>
+8 -4
View File
@@ -8,15 +8,19 @@
</ol></nav>
{% endblock %}
{% block content %}
<div class="d-flex justify-content-between align-items-center mb-3">
<h1 class="h3 mb-0">{{ hotspot.title }} 汇总报告</h1>
<div class="page-heading">
<div>
<p class="section-kicker">热点报告</p>
<h1>{{ hotspot.title }} 汇总报告</h1>
</div>
<span class="badge text-bg-light border">热点 #{{ hotspot.rank }}</span>
</div>
{% if report %}
{% include "partials/report_panel.html" %}
{% else %}
<div class="text-center text-muted py-5">
<div class="empty-state text-muted py-5">
<div class="spinner-border text-warning mb-3" role="status"></div>
<p>报告生成中,请稍候...</p>
<p class="mb-0">报告生成中,请稍候...</p>
</div>
{% endif %}
{% endblock %}
+36 -15
View File
@@ -3,19 +3,37 @@
{% block title %}热榜评论雷达 - 热榜评论分析工具{% endblock %}
{% block content %}
<section class="hero-band mb-4">
<div class="hero-copy">
<p class="eyebrow">Hot Comment Radar</p>
<h1>热榜评论雷达</h1>
<p>从小红书和抖音热点出发,抓取真实评论,生成 AI 情绪、标签和可导出的分析报告。</p>
</div>
<div class="hero-actions">
<a class="btn btn-light" href="#create-task">创建新任务</a>
<a class="btn btn-outline-light" href="#task-history">查看 Demo 数据</a>
<div class="hero-shell">
<div class="hero-copy">
<p class="eyebrow">Hot Comment Radar</p>
<h1>热榜评论雷达</h1>
<p>从小红书和抖音热点出发,抓取真实评论,生成 AI 情绪、标签和可导出的分析报告。</p>
</div>
<div class="hero-metrics" aria-label="默认任务规模">
<div class="hero-metric">
<strong>5</strong>
<span>默认热点</span>
</div>
<div class="hero-metric">
<strong>25</strong>
<span>默认内容</span>
</div>
<div class="hero-metric">
<strong>1,250</strong>
<span>评论上限</span>
</div>
</div>
</div>
</section>
<section class="card mb-4" id="create-task">
<div class="card-header">创建抓取任务</div>
<section class="tool-card mb-4" id="create-task">
<div class="section-heading">
<div>
<p class="section-kicker">采集配置</p>
<h2>创建抓取任务</h2>
</div>
<span class="badge text-bg-light border">默认规模 5 × 5 × 50</span>
</div>
<div class="card-body">
<div id="form-error" class="alert alert-danger d-none" role="alert"></div>
<form id="task-form" onsubmit="submitTask(event)">
@@ -50,13 +68,16 @@
</div>
</section>
<section class="card" id="task-history">
<div class="card-header d-flex justify-content-between align-items-center">
<span>最近任务与 Demo 数据</span>
<button class="btn btn-outline-secondary btn-sm" onclick="window.location.href='/'">手动刷新</button>
<section class="tool-card" id="task-history">
<div class="section-heading">
<div>
<p class="section-kicker">任务历史</p>
<h2>最近任务</h2>
</div>
{% if has_running_tasks %}<span class="badge text-bg-warning">自动更新中</span>{% endif %}
</div>
<div class="table-responsive">
<table class="table table-hover align-middle mb-0">
<table class="table app-table align-middle mb-0">
<thead>
<tr>
<th>任务 ID</th>
+10 -6
View File
@@ -9,21 +9,25 @@
</ol></nav>
{% endblock %}
{% block content %}
<div class="d-flex justify-content-between align-items-center mb-3">
<h1 class="h3 mb-0">{{ item.title or item.source_item_id }}</h1>
<div class="page-heading">
<div>
<p class="section-kicker">内容详情</p>
<h1>{{ item.title or item.source_item_id }}</h1>
</div>
<span class="badge text-bg-light border">{{ item.status }}</span>
</div>
{% if report %}
{% include "partials/report_panel.html" %}
{% else %}
<div class="text-center text-muted py-5">
<div class="empty-state text-muted py-5">
<div class="spinner-border text-warning mb-3" role="status"></div>
<p>报告生成中,请稍候...</p>
<p class="mb-0">报告生成中,请稍候...</p>
</div>
{% endif %}
<section class="card"><div class="card-header">评论明细</div><div class="table-responsive">
<table class="table mb-0"><thead><tr><th>评论内容</th><th>情绪</th><th>标签</th><th>点赞</th></tr></thead><tbody>
<table class="table app-table mb-0"><thead><tr><th>评论内容</th><th>情绪</th><th>标签</th><th>点赞</th></tr></thead><tbody>
{% for comment in comments %}
<tr><td>{{ comment.content }}</td><td>{{ comment.sentiment }}</td><td>{% for label in comment.labels | from_json %}<span class="badge bg-secondary me-1">{{ label }}</span>{% else %}-{% endfor %}</td><td>{{ comment.like_count or 0 }}</td></tr>
<tr><td>{{ comment.content }}</td><td><span class="badge text-bg-light border">{{ comment.sentiment }}</span></td><td>{% for label in comment.labels | from_json %}<span class="badge text-bg-light border me-1">{{ label }}</span>{% else %}<span class="text-muted">-</span>{% endfor %}</td><td>{{ comment.like_count or 0 }}</td></tr>
{% else %}
<tr><td colspan="4" class="text-center text-muted">暂无评论数据(该内容无评论或评论抓取为空)</td></tr>
{% endfor %}
+5 -5
View File
@@ -13,28 +13,28 @@
<div class="row g-3 mb-4">
<div class="col-md-3">
<div class="border rounded p-3 h-100">
<div class="stat-card">
<div class="text-muted small">评论样本</div>
<div class="h4 mb-0">{{ sample_count }}</div>
</div>
</div>
{% if item_count is not none %}
<div class="col-md-3">
<div class="border rounded p-3 h-100">
<div class="stat-card">
<div class="text-muted small">关联内容</div>
<div class="h4 mb-0">{{ item_count }}</div>
</div>
</div>
{% endif %}
<div class="col-md-3">
<div class="border rounded p-3 h-100">
<div class="stat-card">
<div class="text-muted small">AI 成功率</div>
<div class="h4 mb-0">{{ rate_percent(task.analysis_success_rate) }}%</div>
</div>
</div>
</div>
<div class="p-3 bg-info-subtle border border-info-subtle rounded mb-4">
<div class="report-summary mb-4">
<div class="fw-semibold mb-2">AI 总结</div>
<p class="mb-0">{{ report.summary or "总结生成失败,请查看上方统计数据。" }}</p>
</div>
@@ -77,7 +77,7 @@
<div class="col-md-4">
<h3 class="h6">{{ sentiment_label(key) }}</h3>
{% for comment in typical.get(key, []) %}
<div class="border rounded p-2 mb-2">
<div class="comment-card mb-2">
<p class="mb-1">{{ comment.get("content") }}</p>
<small class="text-muted">点赞 {{ comment.get("like_count", 0) }}</small>
</div>
+10 -10
View File
@@ -4,14 +4,11 @@
{% set ai_percent = rate_percent(task.analysis_success_rate) %}
<tr>
<td>
<strong>{{ task.display_id or loop.index }}</strong>
{% if task.is_demo %}
<br><span class="badge text-bg-info">Demo 数据</span>
{% endif %}
<span class="task-number">{{ task.display_id or loop.index }}</span>
</td>
<td>{{ task.platform | platform_label }}</td>
<td>{{ task.created_at_label }}</td>
<td><small class="text-muted">{{ task.scale_label }}</small></td>
<td><span class="badge text-bg-light border">{{ task.platform | platform_label }}</span></td>
<td><span class="text-muted small">{{ task.created_at_label }}</span></td>
<td><span class="text-muted small">{{ task.scale_label }}</span></td>
<td class="task-progress-cell">
<div class="d-flex justify-content-between align-items-center gap-2">
<span class="small">已处理 {{ task.processed_items_count }} / 共 {{ task.total_items_count }} 条内容</span>
@@ -20,9 +17,12 @@
<div class="progress task-progress mt-1" role="progressbar" aria-label="任务进度" aria-valuenow="{{ percent }}" aria-valuemin="0" aria-valuemax="100">
<div class="progress-bar" style="width: {{ percent }}%"></div>
</div>
<div class="small text-muted mt-1">成功 {{ task.successful_items_count }} / 失败 {{ task.failed_items_count }}</div>
<div class="progress-summary mt-2">
<span class="small text-muted">成功 {{ task.successful_items_count }} / 失败 {{ task.failed_items_count }}</span>
<span class="small text-muted">评论 {{ task.comments_count or 0 }}</span>
<span class="small text-muted">报告 {{ task.reports_count or 0 }}</span>
</div>
<div class="small text-muted mt-1">阶段:{{ task.current_stage_label or "等待启动" }}</div>
<div class="small text-muted mt-1">评论 {{ task.comments_count or 0 }} / 报告 {{ task.reports_count or 0 }}</div>
<div class="small {% if task.analysis_status == 'insufficient' %}text-warning{% else %}text-muted{% endif %}">
AI 成功率 {{ ai_percent }}%
{% if task.analysis_status == "insufficient" %}
@@ -36,7 +36,7 @@
<br><small class="text-danger">{{ task.error_summary }}</small>
{% endif %}
</td>
<td><a class="btn btn-sm btn-outline-primary" href="/tasks/{{ task.id }}">查看</a></td>
<td><a class="btn btn-sm btn-outline-secondary" href="/tasks/{{ task.id }}">查看</a></td>
</tr>
{% else %}
<tr>
+42 -26
View File
@@ -7,21 +7,27 @@
</ol></nav>
{% endblock %}
{% block content %}
<div class="d-flex justify-content-between align-items-center mb-3">
<h1 class="h3 mb-0">任务 {{ task.display_id }}</h1>
<button class="btn btn-outline-secondary btn-sm" onclick="window.location.reload()">手动刷新</button>
</div>
<section class="card mb-4" {% if task.status == "running" %}data-task-id="{{ task.id }}" data-auto-poll="true"{% endif %}><div class="card-body">
<div class="page-heading mb-3">
<div>
<p class="section-kicker">任务详情</p>
<h1>任务 {{ task.display_id }}</h1>
</div>
{% set label, cls = status_badge_config(task.status) %}
<span class="badge {{ cls }}">{{ label }}</span>
</div>
<section class="tool-card task-overview mb-4" {% if task.status == "running" %}data-task-id="{{ task.id }}" data-auto-poll="true"{% endif %}>
<div class="card-body">
{% set percent = progress_percent(task.processed_items_count, task.total_items_count) %}
{% set ai_percent = rate_percent(task.analysis_success_rate) %}
{% set target_comments = task.hotspot_limit * task.item_limit_per_hotspot * task.comment_limit_per_item %}
<div class="d-flex flex-wrap justify-content-between gap-3 mb-3">
<p class="mb-0">平台:{{ task.platform | platform_label }} <span class="badge {{ cls }}">{{ label }}</span>{% if task.is_demo %}<span class="badge text-bg-info ms-1">Demo 数据</span>{% endif %}</p>
<p class="mb-0 text-muted">阶段:{{ task.current_stage_label or "等待启动" }}</p>
<div class="d-flex flex-wrap justify-content-between align-items-start gap-3 mb-4">
<div>
<span class="badge text-bg-light border">{{ task.platform | platform_label }}</span>
<span class="badge text-bg-light border ms-1">{{ task.current_stage_label or "等待启动" }}</span>
</div>
<p class="mb-0 text-muted small">创建时间 {{ task.created_at_label }} · 阶段 {{ task.current_stage_label or "等待启动" }}</p>
</div>
<div class="small text-muted mb-3">创建时间 {{ task.created_at_label }} · 完整 ID {{ task.id }}</div>
<div class="mb-3">
<div class="mb-4">
<div class="d-flex justify-content-between align-items-center gap-2">
<span>已处理 {{ task.processed_items_count }} / 共 {{ task.total_items_count }} 条内容</span>
<span class="text-muted">{{ percent }}%</span>
@@ -29,7 +35,10 @@
<div class="progress task-progress mt-2" role="progressbar" aria-label="任务进度" aria-valuenow="{{ percent }}" aria-valuemin="0" aria-valuemax="100">
<div class="progress-bar" style="width: {{ percent }}%"></div>
</div>
<div class="small text-muted mt-2">成功 {{ task.successful_items_count }} / 失败 {{ task.failed_items_count }}</div>
<div class="progress-summary mt-2">
<span class="small text-muted">成功 {{ task.successful_items_count }} / 失败 {{ task.failed_items_count }}</span>
<span class="small text-muted">AI 成功率 {{ ai_percent }}%</span>
</div>
</div>
<div class="row g-3 mb-3">
<div class="col-md-4">
@@ -67,33 +76,40 @@
{% if task.status == "success" and (task.comments_count or 0) < target_comments %}
<div class="alert alert-info">少于理论上限通常是内容本身评论不足或平台返回不足,不直接代表任务失败。若失败内容数大于 0,请结合失败原因判断。</div>
{% endif %}
<div class="mb-2">
<span class="{% if task.analysis_status == 'insufficient' %}text-warning{% else %}text-muted{% endif %}">AI 成功率 {{ ai_percent }}%</span>
{% if task.analysis_status == "insufficient" %}
<span class="badge text-bg-warning ms-1">AI 样本不足</span>
{% endif %}
</div>
{% if task.analysis_status == "insufficient" %}
<div class="alert alert-warning">AI 成功率 {{ ai_percent }}%,当前样本可能不足,报告结论请结合评论明细判断。</div>
{% endif %}
{% if task.error_summary %}<div class="alert alert-danger">{{ task.error_summary }}</div>{% endif %}
</div></section>
</div>
</section>
{% if task.status == "running" and not hotspots %}
<div class="text-center text-muted py-5"><div class="spinner-border text-warning mb-3"></div><p>正在抓取热点数据,请稍候...</p></div>
<div class="empty-state text-muted py-5"><div class="spinner-border text-warning mb-3"></div><p class="mb-0">正在抓取热点数据,请稍候...</p></div>
{% endif %}
<div class="accordion" id="hotspot-list">
{% for hotspot in hotspots %}
<div class="accordion-item">
<div class="accordion-item hotspot-item">
<h2 class="accordion-header">
<button class="accordion-button {% if not loop.first %}collapsed{% endif %}" type="button" data-bs-toggle="collapse" data-bs-target="#hotspot-{{ hotspot.id }}">
热点 {{ hotspot.rank }}{{ hotspot.title }}
<span class="badge text-bg-light border">#{{ hotspot.rank }}</span>
<span>热点 {{ hotspot.rank }}{{ hotspot.title }}</span>
</button>
</h2>
<div id="hotspot-{{ hotspot.id }}" class="accordion-collapse collapse {% if loop.first %}show{% endif %}" data-bs-parent="#hotspot-list">
<div class="accordion-body">
<a class="btn btn-sm btn-outline-primary mb-2" href="/hotspots/{{ hotspot.id }}/report">查看热点级汇总报告</a>
<ul class="list-group">
<div class="d-flex justify-content-between align-items-center gap-3 mb-3">
<span class="text-muted small">内容条目 {{ hotspot.content_items | length }}</span>
<a class="btn btn-sm btn-outline-primary" href="/hotspots/{{ hotspot.id }}/report">查看汇总报告</a>
</div>
<ul class="list-group list-group-flush">
{% for item in hotspot.content_items %}
<li class="list-group-item d-flex justify-content-between">
<span>{{ item.title or item.summary or item.source_item_id }} <small class="text-muted">{{ item.status }}</small></span>
<a class="btn btn-sm btn-outline-secondary" href="/items/{{ item.id }}">查看详情</a>
<li class="list-group-item px-0">
<div class="content-item-row">
<span>
<span class="content-item-title">{{ item.title or item.summary or item.source_item_id }}</span>
<span class="content-item-meta">状态 {{ item.status }} · ID {{ item.source_item_id }}</span>
</span>
<a class="btn btn-sm btn-outline-secondary" href="/items/{{ item.id }}">查看详情</a>
</div>
</li>
{% endfor %}
</ul>
+51 -12
View File
@@ -18,7 +18,10 @@ def test_index_page_renders_task_form_empty_state_and_default_scale():
assert 'name="item_limit_per_hotspot"' in response.text
assert 'name="comment_limit_per_item"' in response.text
assert "1250" in response.text
assert 'onclick="window.location.href=\'/\'"' in response.text
assert "手动刷新" not in response.text
assert 'onclick="window.location.href=\'/\'"' not in response.text
assert 'href="#create-task"' not in response.text
assert 'href="#task-history"' not in response.text
assert "还没有任何任务" in response.text
@@ -104,10 +107,13 @@ def test_index_page_uses_short_task_numbers_compact_fields_and_friendly_error_co
assert "#" not in visible_text
assert first_id not in visible_text
assert second_id not in visible_text
assert "2026-07-03 10:30" in visible_text
assert "2026-07-03 10:35" in visible_text
assert "小红书 · 5热点 × 5内容 × 50评论" in visible_text
assert "抖音 · 1热点 × 1内容 × 10评论" in visible_text
assert "2026-07-03 18:30" in visible_text
assert "2026-07-03 18:35" in visible_text
assert "Demo 数据" not in visible_text
assert "5热点 × 5内容 × 50评论" in visible_text
assert "1热点 × 1内容 × 10评论" in visible_text
assert "小红书 · 5热点" not in visible_text
assert "抖音 · 1热点" not in visible_text
assert "系统重启,任务被中断" in visible_text
assert "system / unexpected_restart" not in visible_text
assert "unexpected_restart" not in visible_text
@@ -167,12 +173,13 @@ def test_running_task_detail_page_auto_polls_current_task():
assert response.status_code == 200
assert 'data-task-id="task-running"' in response.text
assert "pollTaskDetailStatus" in response.text
assert 'onclick="window.location.reload()"' in response.text
assert "手动刷新" not in response.text
assert 'onclick="window.location.reload()"' not in response.text
assert "已处理 1 / 共 2 条内容" in response.text
assert "AI 成功率 100%" in response.text
def test_task_detail_uses_short_number_title_and_keeps_full_uuid_for_diagnostics():
def test_task_detail_uses_short_number_title_and_hides_full_uuid():
task_id = "33333333-3333-4333-8333-333333333333"
with make_test_client() as (client, engine):
from sqlalchemy.orm import Session
@@ -197,11 +204,42 @@ def test_task_detail_uses_short_number_title_and_keeps_full_uuid_for_diagnostics
visible_text = BeautifulSoup(response.text, "html.parser").get_text(" ")
assert "<title>任务 1 - 热榜评论分析工具</title>" in response.text
assert "任务 1" in visible_text
assert "完整 ID" in visible_text
assert task_id in visible_text
assert "完整 ID" not in visible_text
assert task_id not in visible_text
assert "任务 #33333333-3333-4333-8333-333333333333" not in visible_text
assert "#" not in visible_text
assert "创建时间 2026-07-03 10:30" in visible_text
assert "创建时间 2026-07-03 18:30" in visible_text
assert "Demo 数据" not in visible_text
def test_demo_task_flag_is_kept_but_demo_copy_is_hidden_from_pages():
with make_test_client() as (client, engine):
from sqlalchemy.orm import Session
with Session(engine) as session:
session.add(
Task(
id="demo-task-hidden-copy",
platform="xiaohongshu",
status="success",
created_at=datetime(2026, 7, 3, 10, 30, tzinfo=UTC),
hotspot_limit=1,
item_limit_per_hotspot=1,
comment_limit_per_item=10,
)
)
session.commit()
index_response = client.get("/")
detail_response = client.get("/tasks/demo-task-hidden-copy")
api_response = client.get("/api/tasks/demo-task-hidden-copy")
assert index_response.status_code == 200
assert detail_response.status_code == 200
assert api_response.status_code == 200
assert api_response.json()["is_demo"] is True
assert "Demo 数据" not in BeautifulSoup(index_response.text, "html.parser").get_text(" ")
assert "Demo 数据" not in BeautifulSoup(detail_response.text, "html.parser").get_text(" ")
def test_running_task_detail_page_keeps_polling_after_hotspots_exist():
@@ -296,7 +334,7 @@ def test_running_task_detail_page_shows_stage_runtime_and_stale_progress_warning
response = client.get("/tasks/task-stale")
assert response.status_code == 200
assert "阶段AI 分析中" in response.text
assert "阶段 AI 分析中" in response.text
assert "运行时长" in response.text
assert "2小时5分钟" in response.text
assert "最近进度" in response.text
@@ -419,7 +457,8 @@ def test_result_pages_render_seeded_data():
assert task_response.status_code == 200
assert "热点标题" in task_response.text
assert "热点 1:热点标题" in BeautifulSoup(task_response.text, "html.parser").get_text(" ")
assert 'onclick="window.location.reload()"' in task_response.text
assert 'onclick="window.location.reload()"' not in task_response.text
assert "手动刷新" not in task_response.text
assert hotspot_response.status_code == 200
assert "热点总结" in hotspot_response.text
assert "downloadExport(" not in hotspot_response.text
+55
View File
@@ -53,6 +53,61 @@ def test_tikhub_client_raises_structured_error_after_retries(monkeypatch):
assert sleeps == [1, 2, 4]
def test_tikhub_client_retries_transient_api_error(monkeypatch):
sleeps = []
monkeypatch.setattr("app.platforms.base.time.sleep", sleeps.append)
transport = SequenceTransport(
[
httpx.Response(400, json={"message_zh": "临时请求失败"}),
httpx.Response(200, json={"ok": True}),
]
)
http_client = httpx.Client(transport=httpx.MockTransport(transport))
client = TikHubClient(base_url="https://api.test", api_key="secret-token", http_client=http_client)
result = client.get("/demo")
assert result == {"ok": True}
assert sleeps == [1]
assert len(transport.requests) == 2
def test_tikhub_client_includes_response_summary_after_api_error_retries(monkeypatch):
sleeps = []
monkeypatch.setattr("app.platforms.base.time.sleep", sleeps.append)
transport = SequenceTransport(
[httpx.Response(400, json={"message_zh": "笔记评论暂不可用"}) for _ in range(4)]
)
http_client = httpx.Client(transport=httpx.MockTransport(transport))
client = TikHubClient(base_url="https://api.test", api_key="secret-token", http_client=http_client)
with pytest.raises(PlatformAPIError) as exc_info:
client.get("/demo")
assert exc_info.value.error_type == "api_error"
assert exc_info.value.status_code == 400
assert "External API returned HTTP 400" in str(exc_info.value)
assert "笔记评论暂不可用" in str(exc_info.value)
assert "secret-token" not in str(exc_info.value)
assert sleeps == [1, 2, 4]
def test_tikhub_client_includes_text_response_summary_after_api_error_retries(monkeypatch):
sleeps = []
monkeypatch.setattr("app.platforms.base.time.sleep", sleeps.append)
transport = SequenceTransport([httpx.Response(502, text="upstream temporary failure") for _ in range(4)])
http_client = httpx.Client(transport=httpx.MockTransport(transport))
client = TikHubClient(base_url="https://api.test", api_key="secret-token", http_client=http_client)
with pytest.raises(PlatformAPIError) as exc_info:
client.get("/demo")
assert exc_info.value.error_type == "api_error"
assert exc_info.value.status_code == 502
assert str(exc_info.value) == "External API returned HTTP 502: upstream temporary failure"
assert sleeps == [1, 2, 4]
def test_tikhub_client_reports_401_as_auth_error_without_leaking_token():
transport = SequenceTransport([httpx.Response(401, json={"message": "Unauthorized"})])
http_client = httpx.Client(transport=httpx.MockTransport(transport))
+9
View File
@@ -1,4 +1,5 @@
import pytest
from sqlalchemy.pool import NullPool
from app.db import check_database_integrity, checkpoint_sqlite_wal, create_sqlite_engine, ensure_sqlite_schema_compat
@@ -11,6 +12,14 @@ def test_check_database_integrity_returns_ok_for_valid_sqlite_database():
engine.dispose()
def test_file_sqlite_engine_does_not_reuse_connections_after_operational_errors(tmp_path):
engine = create_sqlite_engine(f"sqlite:///{tmp_path / 'app.db'}")
try:
assert isinstance(engine.pool, NullPool)
finally:
engine.dispose()
def test_check_database_integrity_raises_when_sqlite_reports_problem(monkeypatch):
class FakeCursor:
def execute(self, _sql):