|
|
@@ -42,7 +42,7 @@ def read_post(cid: str, extractor: GeminiExtractor):
|
|
|
if ec.from_image:
|
|
|
parts.append("【图片要点】\n" + ec.from_image)
|
|
|
parts += [f"【卡片{c.index}】{c.content}" for c in ec.cards if c.content]
|
|
|
- return post, "\n\n".join(p for p in parts if p)
|
|
|
+ return post, "\n\n".join(p for p in parts if p), bool(ec.is_empty)
|
|
|
|
|
|
|
|
|
# ---------- ② 判颗+成形+轻标签 ----------
|
|
|
@@ -163,7 +163,14 @@ def main() -> None:
|
|
|
posts_out, payloads = [], []
|
|
|
for cid in CIDS:
|
|
|
print(f"\n=== {cid[:8]} ===")
|
|
|
- post, read = read_post(cid, extractor)
|
|
|
+ post, read, is_empty = read_post(cid, extractor)
|
|
|
+ meta = {"post_id": cid, "title": post.title or "", "platform": post.platform,
|
|
|
+ "url": post.url, "img_base": f"/data/demo/xiaohongshu/xhs_{cid}",
|
|
|
+ "img_count": len(post.image_urls)}
|
|
|
+ if is_empty: # ① 总闸：判无知识 → 不走 ②③⑤
|
|
|
+ print(f" ① 读懂 {len(read)} 字 → 判定无可提取的创作知识，跳过拆颗")
|
|
|
+ posts_out.append({**meta, "no_knowledge": True, "knowledges": []})
|
|
|
+ continue
|
|
|
print(f" ① 读懂 {len(read)} 字")
|
|
|
knowledges = shape(post, read)
|
|
|
# 守卫：组件颗 parent 必须指向同帖一个 how，否则降级为 orphan 主颗
|
|
|
@@ -176,9 +183,7 @@ def main() -> None:
|
|
|
print(f" ② {len(knowledges)} 颗：" + ", ".join(f"{k.get('type')}/{k.get('role')}" for k in knowledges))
|
|
|
apply_scopes(knowledges, scope_candidates(knowledges), linker)
|
|
|
print(" ③⑤ 作用域回扣 + 组装")
|
|
|
- posts_out.append({"post_id": cid, "title": post.title or "", "platform": post.platform,
|
|
|
- "url": post.url, "img_base": f"/data/demo/xiaohongshu/xhs_{cid}",
|
|
|
- "img_count": len(post.image_urls), "knowledges": knowledges})
|
|
|
+ posts_out.append({**meta, "knowledges": knowledges})
|
|
|
payloads += [build_payload(post, k, how_titles) for k in knowledges]
|
|
|
(ROOT / "web/frameworks.json").write_text(
|
|
|
json.dumps({"count": len(posts_out), "posts": posts_out}, ensure_ascii=False, indent=1), encoding="utf-8")
|
SamLee