feat: initial MVP - FastAPI backend + Vue3 frontend + docker-compose

- backend: FastAPI + SQLAlchemy 2.0(async) + asyncpg + Alembic
- 7 API routes: auth/me/articles/sources/bookmarks/subscriptions/admin
- models: User/Source/Article/Bookmark/Subscription/ApiToken
- services: RSS fetcher (feedparser) + Tencent TMT translator with quota + cache + local NLLB fallback
- workers: APScheduler + asyncio pipeline (fetch -> dedupe -> insert -> translate)
- seed scripts: create_user, seed_sources (5 RSS: Reuters/BBC/Al Jazeera/NHK/DW)
- frontend: Vue 3 + Vite + Naive UI + Pinia + vue-router
- pages: Login, Feed (24h), ArticleDetail, Sources, Bookmarks, AdminSources
- deploy: docker-compose (postgres/redis/api/worker/frontend/caddy)
- docs: README, DEPLOY, architecture, acceptance

backend/app/services/fetchers/__init__.py

@@ -0,0 +1,12 @@
+"""Fetcher implementations."""
+from app.services.fetchers.base import BaseFetcher, FetchedItem
+from app.services.fetchers.rss import RSSFetcher
+
+__all__ = ["BaseFetcher", "FetchedItem", "RSSFetcher"]
+
+
+def get_fetcher(kind: str, **kwargs) -> BaseFetcher:
+    if kind == "rss":
+        return RSSFetcher(**kwargs)
+    # html_list / tg_channel: Phase 2 实现,这里抛错
+    raise NotImplementedError(f"fetcher not implemented for kind={kind}")

backend/app/services/fetchers/base.py

@@ -0,0 +1,67 @@
+"""Fetcher 抽象基类 + 通用工具。"""
+from __future__ import annotations
+
+import hashlib
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from datetime import datetime
+from typing import Any
+
+import httpx
+
+from app.config import settings
+
+
+def normalize_url(url: str) -> str:
+    """去 utm_*、fragment、尾斜杠,用于 url_hash。"""
+    from urllib.parse import urlsplit, urlunsplit, parse_qsl, urlencode
+
+    sp = urlsplit(url.strip())
+    # 去掉 fragment
+    fragment = ""
+    # 过滤 utm_*
+    qs = [(k, v) for k, v in parse_qsl(sp.query, keep_blank_values=True) if not k.lower().startswith("utm_")]
+    query = urlencode(qs)
+    # 路径末尾 /
+    path = sp.path.rstrip("/") or "/"
+    return urlunsplit((sp.scheme.lower(), sp.netloc.lower(), path, query, fragment))
+
+
+def url_hash(url: str) -> str:
+    return hashlib.sha1(normalize_url(url).encode()).hexdigest()
+
+
+@dataclass
+class FetchedItem:
+    """统一返回结构:一个待入库的条目。"""
+
+    url: str
+    title: str
+    body_html: str | None = None
+    body_text: str = ""
+    published_at: datetime | None = None
+    lang: str | None = None
+    author: str | None = None
+    image_url: str | None = None
+    guid: str | None = None
+    raw: dict[str, Any] = field(default_factory=dict)
+
+
+class BaseFetcher(ABC):
+    def __init__(self, url: str, headers: dict | None = None):
+        self.url = url
+        self.headers = headers or {"User-Agent": "DiaryNews/0.1 (+https://github.com/)"}
+
+    @abstractmethod
+    async def fetch(self) -> list[FetchedItem]:
+        """拉取并解析,返回 FetchedItem 列表。"""
+
+    async def _http_get(self) -> bytes:
+        async with httpx.AsyncClient(
+            timeout=settings.fetch_timeout,
+            follow_redirects=True,
+            headers=self.headers,
+        ) as client:
+            r = await client.get(self.url)
+            r.raise_for_status()
+            return r.content

backend/app/services/fetchers/rss.py

@@ -0,0 +1,100 @@
+"""RSS / Atom fetcher(基于 feedparser)。"""
+from __future__ import annotations
+
+from datetime import datetime, timezone
+from email.utils import parsedate_to_datetime
+
+import feedparser
+from dateutil import parser as dtp
+
+from app.services.fetchers.base import BaseFetcher, FetchedItem
+
+
+class RSSFetcher(BaseFetcher):
+    async def fetch(self) -> list[FetchedItem]:
+        raw = await self._http_get()
+        # feedparser 在不同 Python 下处理 bytes/str
+        try:
+            text = raw.decode("utf-8")
+        except UnicodeDecodeError:
+            text = raw.decode("utf-8", errors="replace")
+        feed = feedparser.parse(text)
+        if feed.bozo and not feed.entries:
+            # 整篇解析失败
+            raise RuntimeError(f"RSS parse failed: {feed.bozo_exception}")
+        items: list[FetchedItem] = []
+        for e in feed.entries:
+            url = e.get("link") or e.get("id")
+            if not url:
+                continue
+            title = (e.get("title") or "").strip()
+            if not title:
+                continue
+
+            body_html = None
+            body_text = ""
+            if e.get("content"):
+                # 选最长 content
+                contents = sorted(e["content"], key=lambda c: -len(c.get("value", "")))
+                body_html = contents[0].get("value")
+            if not body_html:
+                body_html = e.get("summary")
+            if body_html:
+                from bs4 import BeautifulSoup
+
+                soup = BeautifulSoup(body_html, "lxml")
+                # 去 script/style
+                for tag in soup(["script", "style", "noscript"]):
+                    tag.decompose()
+                body_text = soup.get_text(separator="\n", strip=True)
+
+            published_at = _parse_dt(e.get("published") or e.get("updated") or e.get("created"))
+            author = e.get("author")
+            image_url = None
+            if e.get("media_content"):
+                try:
+                    image_url = e["media_content"][0].get("url")
+                except (IndexError, KeyError, TypeError):
+                    pass
+            if not image_url and e.get("media_thumbnail"):
+                try:
+                    image_url = e["media_thumbnail"][0].get("url")
+                except (IndexError, KeyError, TypeError):
+                    pass
+            if not image_url and e.get("enclosures"):
+                for enc in e["enclosures"]:
+                    if enc.get("type", "").startswith("image/"):
+                        image_url = enc.get("href") or enc.get("url")
+                        break
+
+            items.append(
+                FetchedItem(
+                    url=url,
+                    title=title,
+                    body_html=body_html,
+                    body_text=body_text,
+                    published_at=published_at,
+                    lang=e.get("language") or feed.feed.get("language"),
+                    author=author,
+                    image_url=image_url,
+                    guid=e.get("id") or e.get("guid"),
+                )
+            )
+        return items
+
+
+def _parse_dt(s: str | None) -> datetime | None:
+    if not s:
+        return None
+    try:
+        dt = dtp.parse(s)
+    except (ValueError, TypeError, dtp.ParserError):
+        try:
+            dt = parsedate_to_datetime(s)
+        except Exception:
+            return None
+    if dt is None:
+        return None
+    if dt.tzinfo is None:
+        dt = dt.replace(tzinfo=timezone.utc)
+    return dt.astimezone(timezone.utc)