diff --git a/app/main.py b/app/main.py index b78d9d1..818663b 100644 --- a/app/main.py +++ b/app/main.py @@ -1,11 +1,9 @@ from collections.abc import AsyncGenerator from contextlib import asynccontextmanager import logging -from urllib.parse import quote from fastapi import Depends, FastAPI, HTTPException, Request, status from fastapi.responses import HTMLResponse, JSONResponse -from fastapi.responses import Response from fastapi.staticfiles import StaticFiles from sqlalchemy.exc import OperationalError, SQLAlchemyError from sqlalchemy import select @@ -14,7 +12,6 @@ from sqlalchemy.orm import Session from app.db import SessionLocal, backup_sqlite_files, get_db_session, init_db from app.models import Comment, ContentItem, Hotspot, Report from app.schemas import CreateTaskRequest, CreateTaskResponse, TaskResponse -from app.services.export_service import export_hotspot_comments_csv, export_item_comments_csv, export_report_markdown from app.services.task_service import ( RUNNING_TASK_MESSAGE, create_task, @@ -146,47 +143,3 @@ def item_detail_page(item_id: str, request: Request, session: Session = Depends( "items/detail.html", {"task": task, "hotspot": hotspot, "item": item, "report": report, "comments": comments}, ) - - -@app.get("/api/export/items/{item_id}/comments.csv") -def export_item_comments(item_id: str, session: Session = Depends(get_db_session)) -> Response: - try: - content, filename = export_item_comments_csv(session, item_id) - except ValueError: - raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="导出数据不存在") - return Response( - content=content, - media_type="text/csv; charset=utf-8", - headers={"Content-Disposition": f"attachment; filename*=UTF-8''{quote(filename)}"}, - ) - - -@app.get("/api/export/hotspots/{hotspot_id}/comments.csv") -def export_hotspot_comments(hotspot_id: str, session: Session = Depends(get_db_session)) -> Response: - try: - content, filename = export_hotspot_comments_csv(session, hotspot_id) - except ValueError: - raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="导出数据不存在") - return Response( - content=content, - media_type="text/csv; charset=utf-8", - headers={"Content-Disposition": f"attachment; filename*=UTF-8''{quote(filename)}"}, - ) - - -@app.get("/api/export/hotspots/{hotspot_id}.md") -def export_hotspot_markdown(hotspot_id: str, session: Session = Depends(get_db_session)) -> Response: - try: - content, filename = export_report_markdown(session, report_type="hotspot", hotspot_id=hotspot_id) - except ValueError: - raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="报告不存在") - return Response(content=content, media_type="text/markdown; charset=utf-8", headers={"Content-Disposition": f"attachment; filename*=UTF-8''{quote(filename)}"}) - - -@app.get("/api/export/items/{item_id}.md") -def export_item_markdown(item_id: str, session: Session = Depends(get_db_session)) -> Response: - try: - content, filename = export_report_markdown(session, report_type="item", item_id=item_id) - except ValueError: - raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="报告不存在") - return Response(content=content, media_type="text/markdown; charset=utf-8", headers={"Content-Disposition": f"attachment; filename*=UTF-8''{quote(filename)}"}) diff --git a/app/services/export_service.py b/app/services/export_service.py deleted file mode 100644 index 59db585..0000000 --- a/app/services/export_service.py +++ /dev/null @@ -1,104 +0,0 @@ -import csv -import io -import json -import re - -from sqlalchemy import select -from sqlalchemy.orm import Session - -from app.models import Comment, ContentItem, Hotspot, Report - - -def labels_to_text(labels_json: str | None) -> str: - try: - labels = json.loads(labels_json or "[]") - except json.JSONDecodeError: - return "" - return "，".join(str(label) for label in labels) if isinstance(labels, list) else "" - - -def safe_csv_field(value) -> str: - text = "" if value is None else str(value) - text = text.replace("\r\n", " ").replace("\n", " ").replace("\r", " ") - if text.startswith(("=", "+", "-", "@")): - return f"'{text}" - return text - - -def safe_filename(platform: str, task_id: str, hotspot_keyword: str, *, extension: str = "csv") -> str: - keyword = hotspot_keyword[:20] + ("..." if len(hotspot_keyword) > 20 else "") - name = f"{platform}_{task_id}_{keyword}" - name = re.sub(r'[/\\:*?"<>|]+', "_", name) - name = re.sub(r"_+", "_", name).strip("_") - return f"{name}.{extension}" - - -def export_item_comments_csv(session: Session, item_id: str) -> tuple[bytes, str]: - item = session.get(ContentItem, item_id) - if item is None: - raise ValueError("content item not found") - hotspot = session.get(Hotspot, item.hotspot_id) - comments = list(session.scalars(select(Comment).where(Comment.content_item_id == item.id))) - output = io.StringIO() - writer = csv.writer(output) - writer.writerow(["平台", "任务 ID", "热点 ID", "热点标题", "内容条目 ID", "内容条目标题", "评论 ID", "评论内容", "情绪倾向", "方向标签", "点赞数", "评论时间"]) - for comment in comments: - writer.writerow( - [ - item.platform, - item.task_id, - hotspot.id if hotspot else "", - hotspot.title if hotspot else "", - item.id, - item.title or "", - comment.source_comment_id or "", - safe_csv_field(comment.content), - comment.sentiment, - labels_to_text(comment.labels), - comment.like_count or 0, - comment.comment_time or "", - ] - ) - filename = safe_filename(item.platform, item.task_id, hotspot.title if hotspot else item.title or "comments") - return output.getvalue().encode("utf-8-sig"), filename - - -def export_hotspot_comments_csv(session: Session, hotspot_id: str) -> tuple[bytes, str]: - hotspot = session.get(Hotspot, hotspot_id) - if hotspot is None: - raise ValueError("hotspot not found") - comments = list(session.scalars(select(Comment).where(Comment.hotspot_id == hotspot.id))) - output = io.StringIO() - writer = csv.writer(output) - writer.writerow(["平台", "任务 ID", "热点 ID", "热点标题", "内容条目 ID", "内容条目标题", "评论 ID", "评论内容", "情绪倾向", "方向标签", "点赞数", "评论时间"]) - for comment in comments: - item = session.get(ContentItem, comment.content_item_id) - writer.writerow( - [ - comment.platform, - comment.task_id, - hotspot.id, - hotspot.title, - item.id if item else "", - item.title if item else "", - comment.source_comment_id or "", - safe_csv_field(comment.content), - comment.sentiment, - labels_to_text(comment.labels), - comment.like_count or 0, - comment.comment_time or "", - ] - ) - return output.getvalue().encode("utf-8-sig"), safe_filename(hotspot.platform, hotspot.task_id, hotspot.title) - - -def export_report_markdown(session: Session, *, report_type: str, hotspot_id: str | None = None, item_id: str | None = None) -> tuple[str, str]: - query = select(Report).where(Report.report_type == report_type) - if hotspot_id: - query = query.where(Report.hotspot_id == hotspot_id) - if item_id: - query = query.where(Report.content_item_id == item_id) - report = session.scalar(query) - if report is None: - raise ValueError("report not found") - return report.markdown_content or report.markdown, safe_filename("report", report.task_id, report.title, extension="md") diff --git a/app/static/app.js b/app/static/app.js index a7cd2af..e29dcd3 100644 --- a/app/static/app.js +++ b/app/static/app.js @@ -111,46 +111,3 @@ function pollTaskListStatus() { }; window.setTimeout(poll, intervalMs); } - -async function downloadExport(url, defaultFilename, event) { - if (event) event.preventDefault(); - const button = event ? event.currentTarget : null; - const originalText = button ? button.textContent : ""; - if (button) { - button.disabled = true; - button.textContent = "下载中..."; - } - try { - const resp = await fetch(url, { cache: "no-store" }); - if (!resp.ok) { - let message = "导出失败，请稍后重试。"; - try { - const data = await resp.json(); - if (data.detail) message = data.detail; - } catch (_error) { - message = resp.status === 503 ? "数据库暂时不可用，请稍后重试。" : message; - } - alert(message); - return; - } - const blob = await resp.blob(); - const disposition = resp.headers.get("Content-Disposition") || ""; - const match = disposition.match(/filename\*=UTF-8''([^;]+)/); - const filename = match ? decodeURIComponent(match[1]) : defaultFilename; - const blobUrl = URL.createObjectURL(blob); - const link = document.createElement("a"); - link.href = blobUrl; - link.download = filename; - document.body.appendChild(link); - link.click(); - document.body.removeChild(link); - URL.revokeObjectURL(blobUrl); - } catch (_error) { - alert("网络异常，导出未完成。"); - } finally { - if (button) { - button.disabled = false; - button.textContent = originalText; - } - } -} diff --git a/app/templates/hotspots/report.html b/app/templates/hotspots/report.html index 9e126eb..876722b 100644 --- a/app/templates/hotspots/report.html +++ b/app/templates/hotspots/report.html @@ -10,19 +10,6 @@ {% block content %}

{{ hotspot.title }} 汇总报告

-
- - -
{% if report %} {% include "partials/report_panel.html" %} @@ -30,7 +17,6 @@

报告生成中，请稍候...

-

Markdown 报告将在分析完成后开放下载；评论 CSV 可先导出已抓取的数据。

{% endif %} {% endblock %} diff --git a/app/templates/items/detail.html b/app/templates/items/detail.html index 1ab1d53..af81949 100644 --- a/app/templates/items/detail.html +++ b/app/templates/items/detail.html @@ -11,19 +11,6 @@ {% block content %}

{{ item.title or item.source_item_id }}

-
- - -
{% if report %} {% include "partials/report_panel.html" %} @@ -31,7 +18,6 @@

报告生成中，请稍候...

-

Markdown 报告将在分析完成后开放下载；评论 CSV 可先导出已抓取的数据。

{% endif %}
评论明细
diff --git a/docs/UserGuide.md b/docs/UserGuide.md index 5830c57..11e7d99 100644 --- a/docs/UserGuide.md +++ b/docs/UserGuide.md @@ -93,16 +93,13 @@ http://localhost:8000 如果报告尚未生成，页面会显示“报告生成中，请稍候...”，不会返回 500。 -## 5. 导出文件 +## 5. 文件导出 -支持导出： +当前版本已关闭 CSV / Markdown 文件下载入口和接口。页面仍可直接查看： -- 热点报告 Markdown -- 内容报告 Markdown -- 热点评论 CSV -- 内容评论 CSV - -CSV 使用 UTF-8-BOM，适合 Windows Excel 打开。评论内容中的换行会被替换为空格，`= + - @` 开头的内容会自动加单引号，避免被 Excel 当作公式执行。 +- 热点级汇总报告 +- 内容条目级报告 +- 评论明细 ## 6. 小规模验收 @@ -119,7 +116,7 @@ CSV 使用 UTF-8-BOM，适合 Windows Excel 打开。评论内容中的换行会 - 至少有热点、内容、评论、报告。 - AI 成功率正常，或页面有明确“AI 样本不足”提示。 - 能打开热点报告、内容详情页。 -- 能导出 Markdown 和 CSV。 +- 页面不展示 CSV / Markdown 下载入口。 ## 7. 默认规模验收 diff --git a/tests/integration/test_routes.py b/tests/integration/test_routes.py index f9a57f3..a10d6fd 100644 --- a/tests/integration/test_routes.py +++ b/tests/integration/test_routes.py @@ -422,8 +422,10 @@ def test_result_pages_render_seeded_data(): assert 'onclick="window.location.reload()"' in task_response.text assert hotspot_response.status_code == 200 assert "热点总结" in hotspot_response.text - assert "downloadExport('/api/export/hotspots/hot-result.md'" in hotspot_response.text - assert "downloadExport('/api/export/hotspots/hot-result/comments.csv'" in hotspot_response.text + assert "downloadExport(" not in hotspot_response.text + assert "/api/export/" not in hotspot_response.text + assert "导出 Markdown" not in hotspot_response.text + assert "导出热点评论 CSV" not in hotspot_response.text assert "评论样本" in hotspot_response.text assert "关联内容" in hotspot_response.text assert "正向" in hotspot_response.text @@ -437,8 +439,10 @@ def test_result_pages_render_seeded_data(): item_visible_text = BeautifulSoup(item_response.text, "html.parser").get_text(" ") assert "热点 1：热点标题" in item_visible_text assert "#" not in item_visible_text - assert "downloadExport('/api/export/items/item-result.md'" in item_response.text - assert "downloadExport('/api/export/items/item-result/comments.csv'" in item_response.text + assert "downloadExport(" not in item_response.text + assert "/api/export/" not in item_response.text + assert "导出 Markdown" not in item_response.text + assert "导出评论 CSV" not in item_response.text assert "评论样本" in item_response.text assert "Top 标签" in item_response.text assert "评论内容" in item_response.text @@ -473,14 +477,16 @@ def test_report_pages_render_empty_state_when_report_missing(): assert hotspot_response.status_code == 200 assert "报告生成中，请稍候" in hotspot_response.text - assert 'title="报告尚未生成"' in hotspot_response.text - assert "Markdown 报告将在分析完成后开放下载" in hotspot_response.text - assert "downloadExport('/api/export/hotspots/hot-no-report/comments.csv'" in hotspot_response.text + assert 'title="报告尚未生成"' not in hotspot_response.text + assert "Markdown 报告将在分析完成后开放下载" not in hotspot_response.text + assert "downloadExport(" not in hotspot_response.text + assert "/api/export/" not in hotspot_response.text assert item_response.status_code == 200 assert "报告生成中，请稍候" in item_response.text - assert 'title="报告尚未生成"' in item_response.text - assert "Markdown 报告将在分析完成后开放下载" in item_response.text - assert "downloadExport('/api/export/items/item-no-report/comments.csv'" in item_response.text + assert 'title="报告尚未生成"' not in item_response.text + assert "Markdown 报告将在分析完成后开放下载" not in item_response.text + assert "downloadExport(" not in item_response.text + assert "/api/export/" not in item_response.text def test_report_pages_warn_when_ai_sample_is_insufficient(): @@ -503,7 +509,7 @@ def test_report_pages_warn_when_ai_sample_is_insufficient(): assert "当前有效评论样本不足" in item_response.text -def test_export_routes_return_csv_and_markdown(): +def test_export_routes_are_removed(): with make_test_client() as (client, engine): seed_result_data(engine) @@ -512,15 +518,10 @@ def test_export_routes_return_csv_and_markdown(): hotspot_md = client.get("/api/export/hotspots/hot-result.md") item_md = client.get("/api/export/items/item-result.md") - assert csv_response.status_code == 200 - assert csv_response.content.startswith(b"\xef\xbb\xbf") - assert "评论内容".encode("utf-8") in csv_response.content - assert hotspot_csv_response.status_code == 200 - assert "评论内容".encode("utf-8") in hotspot_csv_response.content - assert hotspot_md.status_code == 200 - assert "热点总结" in hotspot_md.text - assert item_md.status_code == 200 - assert "内容总结" in item_md.text + assert csv_response.status_code == 404 + assert hotspot_csv_response.status_code == 404 + assert hotspot_md.status_code == 404 + assert item_md.status_code == 404 def test_api_tasks_returns_service_unavailable_when_database_has_io_error(monkeypatch): @@ -616,18 +617,6 @@ def test_item_detail_page_shows_database_error_state_when_database_has_io_error( assert "数据库暂时不可用" in response.text -def test_export_route_returns_service_unavailable_when_database_has_io_error(monkeypatch): - def broken_export(_session, _item_id): - raise OperationalError("SELECT 1", {}, Exception("disk I/O error")) - - monkeypatch.setattr("app.main.export_item_comments_csv", broken_export) - - with make_test_client() as (client, _engine): - response = client.get("/api/export/items/item-io/comments.csv") - - assert response.status_code == 503 - assert response.json()["detail"] == "数据库暂时不可用，请稍后重试或联系维护者恢复数据。" - def test_missing_html_pages_render_friendly_not_found_page(): with make_test_client() as (client, _engine): diff --git a/tests/unit/test_docs.py b/tests/unit/test_docs.py index 4d3b76b..328762a 100644 --- a/tests/unit/test_docs.py +++ b/tests/unit/test_docs.py @@ -4,7 +4,7 @@ from pathlib import Path ROOT = Path(__file__).resolve().parents[2] -def test_user_guide_covers_startup_acceptance_exports_and_troubleshooting(): +def test_user_guide_covers_startup_acceptance_no_exports_and_troubleshooting(): content = (ROOT / "docs" / "UserGuide.md").read_text(encoding="utf-8") for required in [ @@ -12,7 +12,9 @@ def test_user_guide_covers_startup_acceptance_exports_and_troubleshooting(): "http://localhost:8000", "1 × 1 × 10", "5 × 5 × 50", - "导出文件", + "文件导出", + "已关闭 CSV / Markdown 文件下载入口和接口", + "页面不展示 CSV / Markdown 下载入口", "8000 端口被占用", "API Key 缺失", "任务长期 running", diff --git a/tests/unit/test_export.py b/tests/unit/test_export.py deleted file mode 100644 index 6a682c6..0000000 --- a/tests/unit/test_export.py +++ /dev/null @@ -1,24 +0,0 @@ -from app.services.export_service import labels_to_text, safe_csv_field, safe_filename - - -def test_labels_to_text_joins_json_array_with_chinese_comma(): - assert labels_to_text('["认可", "质量好"]') == "认可，质量好" - assert labels_to_text("bad-json") == "" - - -def test_safe_csv_field_prevents_formula_injection_and_newlines(): - assert safe_csv_field("=1+1") == "'=1+1" - assert safe_csv_field("+1+1") == "'+1+1" - assert safe_csv_field("-1+1") == "'-1+1" - assert safe_csv_field("@SUM(1,1)") == "'@SUM(1,1)" - assert safe_csv_field("hello\nworld") == "hello world" - assert safe_csv_field("hello\r\nworld") == "hello world" - assert safe_csv_field("hello\rworld") == "hello world" - - -def test_safe_filename_replaces_illegal_chars_and_truncates_keyword(): - filename = safe_filename("douyin", "task", "a/b:c*d?eg|很长很长很长很长很长") - - assert "/" not in filename - assert "__" not in filename - assert filename.endswith(".csv")