wait4xandGLM-5.3
aea21c8694
- 正文源=线上渲染页（Halo 快照层 patch 残迹：泥潭/赎罪仅 2 字符），
pandoc html→gfm + tags API 显示名换算后分类：5 书评（五档情绪色）+1 技术
- 图库 21 张：长边 2400/q86 压缩入仓（原图 196M→9.5M——公开仓历史膨胀
与 nginx 100M 推送上限双杀；原图在 Phase 0 备份 tar 中永久留档）
- 瞬间 1 条；URL 1:1（6 slug 全等，零 301）
- 本提交由 7 个本地提交重写而成（清除已进历史的 196M blob，未推送过）；
因 reset --soft 暂存竞态，一并包含 spec 归档文件
（.spec/specs/archive/2026-10-24_migrate-blog-content/）
验证: check_urls.py 6==6；astro build 11 页 exit 0（8.67s）；
EXIF 管线跑通；staging 更新；halo healthy+200 全程未动
Co-authored-by: GLM-5.3
53 lines
1.7 KiB
Python
53 lines
1.7 KiB
Python
#!/usr/bin/env python3
|
||
"""瞬间迁移（Phase 2 T4）：Halo moments → content/moments/*.md
|
||
|
||
Halo moment.content.html 为富文本（内联样式很脏），经 pandoc 提纯为
|
||
纯文本 md；medium（配图）当前库存为空，字段留待将来有图时扩展。
|
||
"""
|
||
import json
|
||
import subprocess
|
||
from datetime import datetime, timezone
|
||
from pathlib import Path
|
||
|
||
OUT = Path("content/moments")
|
||
|
||
|
||
def main() -> int:
|
||
moments = json.load(open(".migration/moments.json", encoding="utf-8"))
|
||
n = 0
|
||
for m in moments:
|
||
spec = m["spec"]
|
||
if spec.get("visible") == "PRIVATE":
|
||
continue
|
||
html = (spec.get("content") or {}).get("html", "")
|
||
text = subprocess.run(
|
||
["/home/wait4x/.local/bin/pandoc", "-f", "html", "-t", "plain", "--wrap=none"],
|
||
input=html.encode(), capture_output=True, check=True,
|
||
).stdout.decode("utf-8").strip()
|
||
if not text:
|
||
continue
|
||
ts = spec.get("releaseTime") or m["metadata"].get("creationTimestamp", "")
|
||
day = datetime.fromisoformat(ts.replace("Z", "+00:00")).astimezone(timezone.utc).strftime("%Y-%m-%d")
|
||
out = OUT / f"{day}.md"
|
||
i = 2
|
||
while out.exists():
|
||
out = OUT / f"{day}-{i}.md"
|
||
i += 1
|
||
tags = spec.get("tags") or []
|
||
# schema 约束 text/image 在 frontmatter（body 不参与校验），一句话即 text 字段
|
||
out.write_text(
|
||
"---\n"
|
||
f"pubDate: {day}\n"
|
||
f"tags: [{', '.join(tags)}]\n"
|
||
f'text: "{text.replace(chr(34), chr(39))}"\n'
|
||
"---\n",
|
||
encoding="utf-8",
|
||
)
|
||
n += 1
|
||
print(f"migrated {n} moments")
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(main())
|