3218485270
b7f429db89
1) 模板导出：识别「基码表-胸围」填 sku.bust（多个胸围列都填）；申报价格模糊匹配多列统一按加价后价格填写；详情图文不再拼接 img_url_2；SPU 款式来源统一填「现货款」；商品产地国家简称映射（沙特→沙特阿拉伯） 2) 模特性别分组：model_features 按男女分组，按模板类目含男/女固定取对应性别模特（含 Pinterest 模式 pipeline） 3) 三合一提示词：去掉 DESIGN CONTENT 四要素描述（设计已由设计稿提供） 4) 生图尺寸：全部改为读 config 不再硬编码（设计图 compose.design_size / 合成图 compose.size / 种草图 seed_shot.size）
340 lines
13 KiB
Python
340 lines
13 KiB
Python
"""Pinterest 参考模式共享辅助：种子词加载、已用搜索词持久化、搜索词全局过滤、设计图全局 MD5 去重。
|
||
|
||
独立于 Google Trends 采集链路，供 pinterest_search / scrape / analyze 节点复用。
|
||
"""
|
||
import hashlib
|
||
import json
|
||
import random
|
||
import re
|
||
import threading
|
||
import time
|
||
from pathlib import Path
|
||
from typing import Any, Dict, List
|
||
|
||
from graph.paths import project_root, runtime_root
|
||
|
||
# 不适合 T 恤印花的类目关键词（复用 product_batch 的兜底清单）
|
||
_UNSUITABLE = re.compile(
|
||
r"\b(nails?|manicure|pedicure|recipes?|cooking|lottery|jackpot|results?|score|scores?|"
|
||
r"fixtures?|forecast|weather|temperature|map|directions?|parking|opening hours?|"
|
||
r"prices?|price|reviews?|jobs?|salary|mortgage|council tax|election|referendum|"
|
||
r"stock market|exchange rate|gas prices?)\b",
|
||
re.IGNORECASE,
|
||
)
|
||
|
||
|
||
def pinterest_seed_path(country: str) -> Path:
|
||
for root in (runtime_root(), project_root()):
|
||
p = root / "configs" / "pinterest" / f"{country}.yaml"
|
||
if p.exists():
|
||
return p
|
||
return Path("configs") / "pinterest" / f"{country}.yaml"
|
||
|
||
|
||
def load_pinterest_seeds(country: str) -> List[str]:
|
||
"""读国家 Pinterest 种子词池（configs/pinterest/<CC>.yaml 的 seeds）。"""
|
||
try:
|
||
import yaml
|
||
p = pinterest_seed_path(country)
|
||
if not p.exists():
|
||
print(f"[pinterest] 未找到种子词配置: {p}")
|
||
return []
|
||
data = yaml.safe_load(p.read_text(encoding="utf-8")) or {}
|
||
seeds = [str(s).strip() for s in (data.get("seeds") or []) if str(s).strip()]
|
||
return seeds
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 种子词加载失败: {e}")
|
||
return []
|
||
|
||
|
||
def sample_seeds(country: str, n: int) -> List[str]:
|
||
"""从国家种子池随机抽取 n 个种子词（不足则全取）。"""
|
||
seeds = load_pinterest_seeds(country)
|
||
if not seeds:
|
||
return []
|
||
if len(seeds) <= n:
|
||
return list(seeds)
|
||
return random.sample(seeds, n)
|
||
|
||
|
||
def used_terms_path(output_dir: str, country: str) -> Path:
|
||
return Path(output_dir) / "pinterest_ref" / country / "used_search_terms.json"
|
||
|
||
|
||
def load_used_terms(output_dir: str, country: str) -> List[str]:
|
||
"""读已用搜索词（跨多次运行持久化，供动态注入防重复）。"""
|
||
try:
|
||
p = used_terms_path(output_dir, country)
|
||
if p.exists():
|
||
data = json.loads(p.read_text(encoding="utf-8"))
|
||
return [str(t).strip() for t in (data.get("terms") or []) if str(t).strip()]
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 已用搜索词读取失败: {e}")
|
||
return []
|
||
|
||
|
||
def save_used_terms(output_dir: str, country: str, terms: List[str]) -> None:
|
||
"""持久化已用搜索词（去重保序）。"""
|
||
try:
|
||
p = used_terms_path(output_dir, country)
|
||
p.parent.mkdir(parents=True, exist_ok=True)
|
||
seen, out = set(), []
|
||
for t in terms:
|
||
k = t.strip().lower()
|
||
if k and k not in seen:
|
||
seen.add(k)
|
||
out.append(t.strip())
|
||
p.write_text(json.dumps({"terms": out}, ensure_ascii=False, indent=2), encoding="utf-8")
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 已用搜索词保存失败: {e}")
|
||
|
||
|
||
def filter_search_terms(terms: List[str], used: List[str], blacklist: List[str]) -> List[str]:
|
||
"""全局搜索词过滤：剔除已用、黑名单、不适合 T 恤类目、去重（大小写不敏感）。"""
|
||
used_set = {str(u).strip().lower() for u in used if str(u).strip()}
|
||
black = [str(b).strip().lower() for b in (blacklist or []) if str(b).strip()]
|
||
seen, out = set(), []
|
||
for t in terms:
|
||
s = str(t).strip()
|
||
low = s.lower()
|
||
if not s or low in seen or low in used_set:
|
||
continue
|
||
if any(b and b in low for b in black):
|
||
continue
|
||
if _UNSUITABLE.search(low):
|
||
continue
|
||
seen.add(low)
|
||
out.append(s)
|
||
return out
|
||
|
||
|
||
def merge_used(existing: List[str], new_terms: List[str]) -> List[str]:
|
||
"""合并已用搜索词（新词追加到末尾，去重保序）。"""
|
||
seen, out = set(), []
|
||
for t in list(existing) + list(new_terms):
|
||
k = str(t).strip().lower()
|
||
if k and k not in seen:
|
||
seen.add(k)
|
||
out.append(str(t).strip())
|
||
return out
|
||
|
||
|
||
# —— 设计图全局 MD5 去重（跨国家、跨运行；对所有国家生效）——
|
||
_MD5_LOCK = threading.Lock()
|
||
|
||
|
||
def global_md5_path() -> Path:
|
||
"""全局设计图 MD5 过滤文件（.cache 随打包同步，跨版本保留）。"""
|
||
return runtime_root() / ".cache" / "global_design_md5.json"
|
||
|
||
|
||
def load_global_md5() -> set:
|
||
"""读全局设计图 MD5 集合。"""
|
||
try:
|
||
p = global_md5_path()
|
||
if p.exists():
|
||
data = json.loads(p.read_text(encoding="utf-8"))
|
||
return {str(m).strip().lower() for m in (data.get("md5s") or []) if str(m).strip()}
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 全局 MD5 过滤读取失败: {e}")
|
||
return set()
|
||
|
||
|
||
def add_global_md5(md5: str) -> bool:
|
||
"""把设计图 MD5 加入全局过滤；返回 True=新增可用，False=已存在（全局重复，应跳过）。"""
|
||
md5 = str(md5 or "").strip().lower()
|
||
if not md5:
|
||
return False
|
||
with _MD5_LOCK:
|
||
try:
|
||
p = global_md5_path()
|
||
p.parent.mkdir(parents=True, exist_ok=True)
|
||
md5s = load_global_md5()
|
||
if md5 in md5s:
|
||
return False
|
||
md5s.add(md5)
|
||
p.write_text(json.dumps(
|
||
{"updated_at": time.strftime("%Y-%m-%dT%H:%M:%S"), "md5s": sorted(md5s)},
|
||
ensure_ascii=False, indent=2), encoding="utf-8")
|
||
return True
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 全局 MD5 过滤写入失败: {e}")
|
||
return True # 写入失败不阻塞：按新增处理，避免误跳过
|
||
|
||
|
||
def design_md5_ok(image_path: str) -> bool:
|
||
"""计算设计图 MD5 并加入全局过滤；返回 True=新增可用，False=全局重复（应跳过）。"""
|
||
try:
|
||
md5 = hashlib.md5(Path(image_path).read_bytes()).hexdigest()
|
||
return add_global_md5(md5)
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 设计图 MD5 计算失败: {e}")
|
||
return True
|
||
|
||
|
||
# —— 图池（Image Pool）：跨轮次/跨运行持久化的爬取图片池 + 已消费图片 MD5 拉黑 ——
|
||
# 图池 = 所有已爬取图片的注册表（path + md5 + term）；已消费（分析过）的图片 MD5 记入
|
||
# used_images，不再复用。分析从图池取未消费图片，池不足时由路由触发新一轮搜索。
|
||
|
||
_IMG_EXTS = (".jpg", ".jpeg", ".png", ".webp", ".gif", ".bmp")
|
||
|
||
|
||
def image_pool_path(output_dir: str, country: str) -> Path:
|
||
return Path(output_dir) / "pinterest_ref" / country / "image_pool.json"
|
||
|
||
|
||
def used_images_path(output_dir: str, country: str) -> Path:
|
||
return Path(output_dir) / "pinterest_ref" / country / "used_images.json"
|
||
|
||
|
||
def load_image_pool(output_dir: str, country: str) -> Dict[str, Any]:
|
||
"""读图池注册表；无文件时回退扫描文件系统重建。"""
|
||
try:
|
||
p = image_pool_path(output_dir, country)
|
||
if p.exists():
|
||
data = json.loads(p.read_text(encoding="utf-8")) or {}
|
||
imgs = data.get("images") or []
|
||
if imgs:
|
||
return {"updated_at": data.get("updated_at", ""), "images": imgs}
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 图池读取失败: {e}")
|
||
return {"updated_at": "", "images": scan_scraped_images(output_dir, country)}
|
||
|
||
|
||
def save_image_pool(output_dir: str, country: str, pool: Dict[str, Any]) -> None:
|
||
"""持久化图池注册表。"""
|
||
try:
|
||
p = image_pool_path(output_dir, country)
|
||
p.parent.mkdir(parents=True, exist_ok=True)
|
||
p.write_text(json.dumps(
|
||
{"updated_at": time.strftime("%Y-%m-%dT%H:%M:%S"), "images": pool.get("images") or []},
|
||
ensure_ascii=False, indent=2), encoding="utf-8")
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 图池保存失败: {e}")
|
||
|
||
|
||
def scan_scraped_images(output_dir: str, country: str) -> List[Dict[str, Any]]:
|
||
"""扫描 pinterest_ref/<country>/*/ 下所有图片，重建图池注册表（含 md5）。"""
|
||
base = Path(output_dir) / "pinterest_ref" / country
|
||
out: List[Dict[str, Any]] = []
|
||
if not base.exists():
|
||
return out
|
||
for term_dir in sorted(base.iterdir()):
|
||
if not term_dir.is_dir():
|
||
continue
|
||
term = term_dir.name
|
||
for f in sorted(term_dir.iterdir()):
|
||
if not f.is_file() or f.suffix.lower() not in _IMG_EXTS:
|
||
continue
|
||
out.append({"path": str(f), "md5": image_md5(str(f)), "term": term})
|
||
return out
|
||
|
||
|
||
def image_md5(path: str) -> str:
|
||
"""计算图片文件 MD5（失败返回空串）。"""
|
||
try:
|
||
return hashlib.md5(Path(path).read_bytes()).hexdigest()
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 图片 MD5 计算失败 {path}: {e}")
|
||
return ""
|
||
|
||
|
||
def load_used_images(output_dir: str, country: str) -> set:
|
||
"""读已消费图片 MD5 集合（拉黑，不再复用）。"""
|
||
try:
|
||
p = used_images_path(output_dir, country)
|
||
if p.exists():
|
||
data = json.loads(p.read_text(encoding="utf-8")) or {}
|
||
return {str(m).strip().lower() for m in (data.get("md5s") or []) if str(m).strip()}
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 已消费图片读取失败: {e}")
|
||
return set()
|
||
|
||
|
||
def save_used_images(output_dir: str, country: str, md5s: set) -> None:
|
||
"""持久化已消费图片 MD5 集合。"""
|
||
try:
|
||
p = used_images_path(output_dir, country)
|
||
p.parent.mkdir(parents=True, exist_ok=True)
|
||
p.write_text(json.dumps(
|
||
{"updated_at": time.strftime("%Y-%m-%dT%H:%M:%S"), "md5s": sorted(md5s)},
|
||
ensure_ascii=False, indent=2), encoding="utf-8")
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 已消费图片保存失败: {e}")
|
||
|
||
|
||
def pool_unused_images(pool: Dict[str, Any], used: set) -> List[Dict[str, Any]]:
|
||
"""从图池取未消费图片（md5 不在 used 集合），保序。"""
|
||
out = []
|
||
for img in pool.get("images") or []:
|
||
if not isinstance(img, dict):
|
||
continue
|
||
m = str(img.get("md5") or "").strip().lower()
|
||
if not m or m in used:
|
||
continue
|
||
if not Path(str(img.get("path") or "")).exists():
|
||
continue
|
||
out.append(img)
|
||
return out
|
||
|
||
|
||
def compress_image(path: str, max_dim: int = 1024, max_bytes: int = 1_500_000,
|
||
out_dir: str = "") -> str:
|
||
"""压缩大图：超过 max_dim 边长或 max_bytes 体积时缩放/重编码，返回压缩后路径。
|
||
|
||
- 内存占用过大（分辨率过高）→ 等比缩放到 max_dim 内；
|
||
- 文件过大 → 转 JPEG 重编码（质量自适应）；
|
||
- 无需压缩 → 返回原路径。压缩产物存 out_dir（默认图片同目录 .compressed/）。
|
||
"""
|
||
try:
|
||
from PIL import Image
|
||
p = Path(path)
|
||
if not p.exists():
|
||
return path
|
||
size = p.stat().st_size
|
||
try:
|
||
with Image.open(p) as im:
|
||
w, h = im.size
|
||
except Exception: # noqa: BLE001 无法解析的图片（损坏/非标准）直接返回原路径
|
||
return path
|
||
if w <= max_dim and h <= max_dim and size <= max_bytes:
|
||
return path
|
||
out_root = Path(out_dir) if out_dir else (p.parent / ".compressed")
|
||
out_root.mkdir(parents=True, exist_ok=True)
|
||
out = out_root / f"{p.stem}_c.jpg"
|
||
with Image.open(p) as im:
|
||
im = im.convert("RGB")
|
||
im.thumbnail((max_dim, max_dim), Image.LANCZOS)
|
||
quality = 85
|
||
while quality >= 40:
|
||
im.save(out, "JPEG", quality=quality, optimize=True)
|
||
if out.stat().st_size <= max_bytes:
|
||
break
|
||
quality -= 15
|
||
print(f"[pinterest] 图片压缩 {p.name} ({w}x{h}, {size // 1024}KB) → "
|
||
f"{out.name} ({out.stat().st_size // 1024}KB)")
|
||
return str(out)
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[pinterest] 图片压缩失败 {path}: {e}")
|
||
return path
|
||
|
||
|
||
def is_400_content_image(exc) -> bool:
|
||
"""HTTP 400 且错误信息模糊匹配到「内容」或「图片」才算（用户要求）。
|
||
|
||
生图后端抛 RuntimeError("图像 API 400: {body}")，body 在消息里；
|
||
多模态后端抛 requests.HTTPError，响应体在 exc.response.text。
|
||
"""
|
||
msg = str(exc or "")
|
||
resp = getattr(exc, "response", None)
|
||
if resp is not None:
|
||
try:
|
||
body = resp.text or ""
|
||
except Exception: # noqa: BLE001
|
||
body = ""
|
||
if body:
|
||
msg = f"{msg} {body}"
|
||
if "400" not in msg:
|
||
return False
|
||
return ("内容" in msg or "图片" in msg)
|