feat: 初始化项目，并且接近完成 ozon 部分

2026-08-15 22:19:27 +08:00
commit 1591d5e35a
46 changed files with 9827 additions and 0 deletions
@@ -0,0 +1,166 @@
+"""采集入库：插件上传文本 + 图片 URL，落库后异步转存。"""
+from __future__ import annotations
+
+import re
+from uuid import UUID
+
+from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from db import get_db, get_session_factory
+from models import (
+    Product, ProductAsset,
+    STATUS_PENDING, STATUS_DOWNLOADING, STATUS_OK, STATUS_FAILED, STAGE_COLLECTED,
+)
+from schemas import MaterialsRequest, MaterialsResponse, TextMaterial
+from services import storage
+
+router = APIRouter(prefix="/api", tags=["collection"])
+
+
+def _parse_number(text: str | None) -> float | None:
+    """'1 290 ₽' / '￥36.80' → 1290.0 / 36.8"""
+    if not text:
+        return None
+    m = re.search(r"(\d+(?:[.,]\d+)?)", text.replace(" ", "").replace(",", "."))
+    return float(m.group(1)) if m else None
+
+
+def _apply_texts(product: Product, texts: list[TextMaterial]) -> None:
+    raw = dict(product.raw or {})
+    raw_texts: list[dict] = list(raw.get("texts") or [])
+    for t in texts:
+        raw_texts.append({"kind": t.kind, "content": t.content, "pairs": t.pairs})
+        if t.kind == "title" and t.content and not product.name:
+            product.name = t.content
+            raw["title"] = t.content
+        elif t.kind == "price":
+            raw["price"] = t.content
+            num = _parse_number(t.content)
+            if num is not None and (product.price is None or product.price == 0):
+                product.price = num
+        elif t.kind == "params" and t.pairs:
+            # 与已有参数按 key 并集合并（跨页追加时同一参数不重复）
+            merged = {p["key"]: p["value"] for p in (raw.get("params") or [])}
+            for p in t.pairs:
+                merged.setdefault(p["key"], p["value"])
+            raw["params"] = [{"key": k, "value": v} for k, v in merged.items()]
+        elif t.kind == "selling_point":
+            raw["sellingPoints"] = t.content
+        elif t.kind == "desc":
+            raw["desc"] = t.content
+            if not product.description:
+                product.description = t.content
+        elif t.kind == "brand":
+            raw["brand"] = t.content
+    raw["texts"] = raw_texts
+    product.raw = raw
+
+
+async def _get_or_create_product(db: AsyncSession, req: MaterialsRequest) -> Product:
+    if req.product_id:
+        product = await db.get(Product, UUID(req.product_id))
+        if product is None:
+            raise HTTPException(status_code=404, detail="商品不存在")
+        return product
+    product = Product(
+        stage=STAGE_COLLECTED,
+        source_platform=req.source.platform,
+        source_item_id=req.source.itemId,
+        source_url=req.source.url,
+    )
+    db.add(product)
+    await db.flush()
+    return product
+
+
+@router.post("/materials", response_model=MaterialsResponse)
+async def create_materials(
+    req: MaterialsRequest,
+    background: BackgroundTasks,
+    db: AsyncSession = Depends(get_db),
+) -> MaterialsResponse:
+    product = await _get_or_create_product(db, req)
+    _apply_texts(product, req.texts)
+
+    if not product.source_url:
+        product.source_url = req.source.url
+    if not product.source_platform:
+        product.source_platform = req.source.platform
+
+    # 去重 + 建素材
+    existing: set[str] = set()
+    if req.images:
+        rows = (await db.execute(
+            select(ProductAsset.dedupe_key).where(
+                ProductAsset.product_id == product.id,
+                ProductAsset.dedupe_key.isnot(None),
+            )
+        )).scalars().all()
+        existing = {k for k in rows if k}
+
+    queued, skipped = 0, 0
+    for img in req.images:
+        if img.dedupeKey and img.dedupeKey in existing:
+            skipped += 1
+            continue
+        db.add(ProductAsset(
+            product_id=product.id,
+            group_key=img.groupKey,
+            variant_name=img.variantName,
+            sort_order=img.index,
+            type=img.type,
+            source_url=img.url,
+            status=STATUS_PENDING,
+            dedupe_key=img.dedupeKey,
+        ))
+        if img.dedupeKey:
+            existing.add(img.dedupeKey)
+        queued += 1
+
+    # 更新分组计数
+    counts: dict = {}
+    for a in await db.scalars(select(ProductAsset).where(ProductAsset.product_id == product.id)):
+        counts[a.group_key] = counts.get(a.group_key, 0) + 1
+    product.asset_counts = counts
+
+    await db.commit()
+    await db.refresh(product)
+
+    if queued:
+        background.add_task(process_product_assets, str(product.id))
+    return MaterialsResponse(product_id=str(product.id), assets_queued=queued, assets_skipped=skipped)
+
+
+async def process_product_assets(product_id: str) -> None:
+    """后台：下载 pending 素材 → 转存本地 media。失败逐张标记，不中断。"""
+    async with get_session_factory()() as db:
+        assets = (await db.scalars(
+            select(ProductAsset).where(
+                ProductAsset.product_id == UUID(product_id),
+                ProductAsset.status == STATUS_PENDING,
+                ProductAsset.type == "img",
+            )
+        )).all()
+        for a in assets:
+            a.status = STATUS_DOWNLOADING
+            await db.commit()
+            try:
+                a.stored_url = await storage.save_from_url(a.source_url, key_prefix="assets")
+                a.status = STATUS_OK
+            except Exception as exc:  # noqa: BLE001
+                a.status = STATUS_FAILED
+                a.error = str(exc)[:500]
+            await db.commit()
+
+
+@router.get("/collected")
+async def is_collected(platform: str, itemId: str, db: AsyncSession = Depends(get_db)):
+    rows = (await db.execute(
+        select(Product.id).where(
+            Product.source_platform == platform,
+            Product.source_item_id == itemId,
+        )
+    )).scalars().all()
+    return {"collected": len(rows) > 0, "count": len(rows)}
@@ -0,0 +1,126 @@
+"""无状态套图生成：请求自带采集数据，不落商品库。"""
+from __future__ import annotations
+
+from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException
+
+from config import get_settings
+from db import get_db
+from models import Suite
+from schemas import (
+    GenerateRequest, PLATFORM_SPECS, SUPPORTED_TYPES, SuiteCreateResponse, TextMaterial,
+    PlanRequest, PlanResponse, PlanItemOut,
+)
+from services.generator import run_suite
+from services.planner import generate_plan
+from services.prompt import type_name
+
+router = APIRouter(prefix="/api", tags=["generate"])
+
+
+def texts_to_raw(texts: list[TextMaterial]) -> dict:
+    """插件上传的文本素材 → prompt 上下文用的 raw dict（后写的覆盖先写的）。"""
+    raw: dict = {}
+    for t in texts:
+        if t.kind == "title" and t.content:
+            raw["title"] = t.content
+        elif t.kind == "price" and t.content:
+            raw["price"] = t.content
+        elif t.kind == "brand" and t.content:
+            raw["brand"] = t.content
+        elif t.kind == "params" and t.pairs:
+            merged = {p["key"]: p["value"] for p in (raw.get("params") or [])}
+            for p in t.pairs:
+                merged.setdefault(p["key"], p["value"])
+            raw["params"] = [{"key": k, "value": v} for k, v in merged.items()]
+        elif t.kind == "selling_point" and t.content:
+            raw["sellingPoints"] = t.content
+        elif t.kind == "desc" and t.content:
+            raw["desc"] = t.content
+    return raw
+
+
+@router.post("/generate", response_model=SuiteCreateResponse)
+async def generate_suite(
+    req: GenerateRequest,
+    background: BackgroundTasks,
+    db=Depends(get_db),
+) -> SuiteCreateResponse:
+    if not req.images:
+        raise HTTPException(status_code=400, detail="未勾选任何图片，无法生成")
+
+    # 生成任务列表：方案优先；无方案时按 types（空则默认四种）
+    if req.plan:
+        jobs: list[dict] = []
+        for item in req.plan:
+            if item.count <= 0:
+                continue
+            if item.kind not in SUPPORTED_TYPES:
+                raise HTTPException(status_code=400, detail=f"方案项「{item.title}」的图类型不支持: {item.kind}")
+            # 同一项多张 → 展开为多任务，第二张起在标题上加序号
+            for n in range(item.count):
+                jobs.append({
+                    "kind": item.kind,
+                    "title": item.title if item.count == 1 else f"{item.title}{n + 1}",
+                    "detail": item.detail,
+                    "prompt_hint": item.prompt_hint,
+                    "variant_name": item.variant_name,
+                })
+        if not jobs:
+            raise HTTPException(status_code=400, detail="方案中所有项的数量都是 0")
+        types = list(dict.fromkeys(j["kind"] for j in jobs))
+    else:
+        types = req.types or ["white_bg", "key_features", "lifestyle", "multi_scene"]
+        bad = [t for t in types if t not in SUPPORTED_TYPES]
+        if bad:
+            raise HTTPException(status_code=400, detail=f"不支持的图类型: {bad}")
+        jobs = [{"kind": t, "title": type_name(t), "detail": "", "prompt_hint": "", "variant_name": None} for t in types]
+
+    if req.platform not in PLATFORM_SPECS:
+        raise HTTPException(status_code=400, detail=f"不支持的目标平台: {req.platform}（ozon | wb | cn）")
+    spec = PLATFORM_SPECS[req.platform]
+
+    settings = get_settings()
+    suite = Suite(
+        product_id=None,
+        style_set=req.style_set,
+        platform=req.platform,
+        lang=spec["lang"],
+        ratio=spec["ratio"],
+        types=types,
+        plan=jobs,
+        provider=req.provider or settings.image_provider,
+        context=texts_to_raw(req.texts),
+        # 参考图池：main 组优先，其余组按序补充（variant 绑定靠 variant_name 匹配）
+        ref_images=[
+            {
+                "url": i.url,
+                "group_key": i.group_key,
+                "variant_name": i.variant_name,
+            }
+            for i in sorted(req.images, key=lambda x: 0 if x.group_key == "main" else 1)
+        ],
+    )
+    db.add(suite)
+    await db.commit()
+    await db.refresh(suite)
+
+    background.add_task(run_suite, str(suite.id))
+    return SuiteCreateResponse(suite_id=str(suite.id))
+
+
+@router.post("/plan", response_model=PlanResponse)
+async def plan_suite(req: PlanRequest) -> PlanResponse:
+    """DeepSeek 根据商品信息生成出图方案。"""
+    product_info = texts_to_raw(req.texts)
+    if not product_info.get("title"):
+        raise HTTPException(status_code=400, detail="缺少商品标题，无法规划")
+    try:
+        result = await generate_plan(product_info, req.sku_variants, req.image_stats, req.platform)
+    except RuntimeError as exc:
+        raise HTTPException(status_code=502, detail=str(exc)) from exc
+    except Exception as exc:  # noqa: BLE001
+        raise HTTPException(status_code=502, detail=f"规划失败: {exc}") from exc
+    return PlanResponse(
+        summary=result["summary"],
+        items=[PlanItemOut(**i) for i in result["items"]],
+    )
@@ -0,0 +1,71 @@
+"""商品查询 API。"""
+from __future__ import annotations
+
+from uuid import UUID
+
+from fastapi import APIRouter, Depends, HTTPException
+from sqlalchemy import func, select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from db import get_db
+from models import Product, ProductAsset
+from schemas import AssetOut, ProductListOut, ProductOut
+from services import storage
+
+router = APIRouter(prefix="/api", tags=["products"])
+
+
+def _asset_out(a: ProductAsset) -> AssetOut:
+    return AssetOut(
+        id=str(a.id),
+        group_key=a.group_key,
+        variant_name=a.variant_name,
+        type=a.type,
+        source_url=a.source_url,
+        url=a.stored_url,
+        status=a.status,
+    )
+
+
+@router.get("/products", response_model=ProductListOut)
+async def list_products(
+    q: str = "",
+    page: int = 1,
+    page_size: int = 20,
+    db: AsyncSession = Depends(get_db),
+):
+    cond = []
+    if q:
+        cond.append(Product.name.contains(q))
+    total = (await db.scalar(select(func.count()).select_from(Product).where(*cond))) or 0
+    rows = (await db.scalars(
+        select(Product).where(*cond).order_by(Product.created_at.desc())
+        .offset((page - 1) * page_size).limit(page_size)
+    )).all()
+    return ProductListOut(total=total, items=[
+        ProductOut(
+            id=str(p.id), stage=p.stage, source_platform=p.source_platform,
+            source_item_id=p.source_item_id, source_url=p.source_url,
+            name=p.name, description=p.description, price=p.price,
+            asset_counts=p.asset_counts,
+            created_at=p.created_at.isoformat() if p.created_at else None,
+        ) for p in rows
+    ])
+
+
+@router.get("/products/{product_id}", response_model=ProductOut)
+async def get_product(product_id: str, db: AsyncSession = Depends(get_db)):
+    p = await db.get(Product, UUID(product_id))
+    if p is None:
+        raise HTTPException(status_code=404, detail="商品不存在")
+    assets = (await db.scalars(
+        select(ProductAsset).where(ProductAsset.product_id == p.id)
+        .order_by(ProductAsset.sort_order)
+    )).all()
+    return ProductOut(
+        id=str(p.id), stage=p.stage, source_platform=p.source_platform,
+        source_item_id=p.source_item_id, source_url=p.source_url,
+        name=p.name, description=p.description, price=p.price,
+        asset_counts=p.asset_counts, assets=[_asset_out(a) for a in assets],
+        created_at=p.created_at.isoformat() if p.created_at else None,
+    )
@@ -0,0 +1,54 @@
+"""图片代理：绕过源站防盗链，供前端 <img> 预览与生图参考使用。
+
+参考 laowang.putumiao.shop 的 /api/proxy-image?url=... 形式。
+"""
+from __future__ import annotations
+
+from urllib.parse import urlparse
+
+from fastapi import APIRouter, HTTPException, Query, Response
+
+from services import storage
+
+router = APIRouter(prefix="/api", tags=["proxy"])
+
+# 域名片段 → 防盗链所需 Referer
+_REFERER_BY_DOMAIN: list[tuple[str, str]] = [
+    ("alicdn.com", "https://www.taobao.com"),
+    ("taobao.com", "https://www.taobao.com"),
+    ("tmall.com", "https://www.tmall.com"),
+    ("1688.com", "https://www.1688.com"),
+    ("ozon.ru", "https://www.ozon.ru"),
+    ("ozon.kz", "https://www.ozon.ru"),
+    ("ozon.by", "https://www.ozon.ru"),
+    ("ozonusercontent.com", "https://www.ozon.ru"),
+]
+
+
+def guess_referer(url: str) -> str | None:
+    host = (urlparse(url).hostname or "").lower()
+    for frag, referer in _REFERER_BY_DOMAIN:
+        if frag in host:
+            return referer
+    return None
+
+
+@router.get("/proxy-image")
+async def proxy_image(url: str = Query(..., description="源站图片 URL")):
+    scheme = urlparse(url).scheme
+    if scheme not in ("http", "https"):
+        raise HTTPException(status_code=400, detail="仅支持 http/https URL")
+    try:
+        data, ctype = await storage.download_bytes(url, referer=guess_referer(url))
+    except Exception as exc:  # noqa: BLE001
+        raise HTTPException(status_code=502, detail=f"图片拉取失败: {exc}") from exc
+    if not ctype.startswith("image/"):
+        ctype = "image/jpeg"
+    return Response(
+        content=data,
+        media_type=ctype,
+        headers={
+            "Cache-Control": "public, max-age=86400",
+            "Access-Control-Allow-Origin": "*",
+        },
+    )
@@ -0,0 +1,141 @@
+"""套图生成 API：创建任务 / 查询状态 / 导出 ZIP。"""
+from __future__ import annotations
+
+import io
+import zipfile
+from uuid import UUID
+
+from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException
+from fastapi.responses import StreamingResponse
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from config import get_settings
+from db import get_db
+from models import Product, ProductAsset, Suite, SuiteImage, STATUS_OK
+from schemas import PLATFORM_SPECS, SUPPORTED_TYPES, SuiteCreateRequest, SuiteCreateResponse, SuiteImageOut, SuiteOut
+from services import storage
+from services.generator import run_suite
+
+router = APIRouter(prefix="/api", tags=["suites"])
+
+
+async def _suite_out(db: AsyncSession, suite: Suite) -> SuiteOut:
+    images = (await db.scalars(
+        select(SuiteImage).where(SuiteImage.suite_id == suite.id)
+        .order_by(SuiteImage.created_at)
+    )).all()
+    return SuiteOut(
+        id=str(suite.id),
+        product_id=str(suite.product_id),
+        status=suite.status,
+        style_set=suite.style_set,
+        platform=suite.platform,
+        lang=suite.lang,
+        ratio=suite.ratio,
+        types=list(suite.types or []),
+        provider=suite.provider,
+        images=[
+            SuiteImageOut(
+                type_id=i.type_id, name=i.name, url=i.stored_url or "",
+                status=i.status, error=i.error,
+            ) for i in images
+        ],
+        error=suite.error,
+    )
+
+
+@router.post("/products/{product_id}/suites", response_model=SuiteCreateResponse)
+async def create_suite(
+    product_id: str,
+    req: SuiteCreateRequest,
+    background: BackgroundTasks,
+    db: AsyncSession = Depends(get_db),
+):
+    product = await db.get(Product, UUID(product_id))
+    if product is None:
+        raise HTTPException(status_code=404, detail="商品不存在")
+
+    # 主图组至少一张图（不要求转存完成：生图可直接用源站 URL 代理解析）
+    ok_assets = (await db.scalars(
+        select(ProductAsset.id).where(
+            ProductAsset.product_id == product.id,
+            ProductAsset.group_key == "main",
+            ProductAsset.type == "img",
+        )
+    )).all()
+    if not ok_assets:
+        raise HTTPException(status_code=400, detail="商品没有主图，无法生成")
+
+    bad = [t for t in req.types if t not in SUPPORTED_TYPES]
+    if bad:
+        raise HTTPException(status_code=400, detail=f"不支持的图类型: {bad}")
+    if req.platform not in PLATFORM_SPECS:
+        raise HTTPException(status_code=400, detail=f"不支持的目标平台: {req.platform}（ozon | wb | cn）")
+    spec = PLATFORM_SPECS[req.platform]
+
+    settings = get_settings()
+    suite = Suite(
+        product_id=product.id,
+        style_set=req.style_set,
+        platform=req.platform,
+        lang=spec["lang"],
+        ratio=spec["ratio"],
+        types=req.types,
+        provider=req.provider or settings.image_provider,
+    )
+    db.add(suite)
+    await db.commit()
+    await db.refresh(suite)
+
+    background.add_task(run_suite, str(suite.id))
+    return SuiteCreateResponse(suite_id=str(suite.id))
+
+
+@router.get("/suites/{suite_id}", response_model=SuiteOut)
+async def get_suite(suite_id: str, db: AsyncSession = Depends(get_db)):
+    suite = await db.get(Suite, UUID(suite_id))
+    if suite is None:
+        raise HTTPException(status_code=404, detail="任务不存在")
+    return await _suite_out(db, suite)
+
+
+@router.get("/products/{product_id}/suites")
+async def list_suites(product_id: str, db: AsyncSession = Depends(get_db)):
+    suites = (await db.scalars(
+        select(Suite).where(Suite.product_id == UUID(product_id))
+        .order_by(Suite.created_at.desc())
+    )).all()
+    return [await _suite_out(db, s) for s in suites]
+
+
+@router.get("/suites/{suite_id}/zip")
+async def download_suite_zip(suite_id: str, db: AsyncSession = Depends(get_db)):
+    """把任务内所有成功图打包成 ZIP（中文文件名）。"""
+    suite = await db.get(Suite, UUID(suite_id))
+    if suite is None:
+        raise HTTPException(status_code=404, detail="任务不存在")
+    images = (await db.scalars(
+        select(SuiteImage).where(
+            SuiteImage.suite_id == suite.id, SuiteImage.status == STATUS_OK,
+        ).order_by(SuiteImage.created_at)
+    )).all()
+
+    buf = io.BytesIO()
+    with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as zf:
+        seen: set[str] = set()
+        for i, img in enumerate(images):
+            path = storage.local_path(img.stored_url or "")
+            if path is None:
+                continue
+            filename = img.name or img.type_id
+            if filename in seen:  # 同类型多张时加序号防覆盖
+                filename = f"{filename}-{i + 1}"
+            seen.add(filename)
+            zf.write(path, f"{filename}{path.suffix or '.jpg'}")
+    buf.seek(0)
+    return StreamingResponse(
+        buf,
+        media_type="application/zip",
+        headers={"Content-Disposition": f'attachment; filename="suite-{suite_id}.zip"'},
+    )