270 lines
9.6 KiB
Python
270 lines
9.6 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
《卡若的IP财富旅程》PART1-5 重新上传：正文以本地 MD 为准，已入库的图片块按顺序保留（不重新上传）。
|
||
|
||
- 从 chapters.content 提取现有 <p><img .../></p>（或裸 <img>）块，顺序与 MD 中独立图片行一一对应。
|
||
- 无图片的章节：与 batch_upload_ip_book.py 相同（纯文本清洗）。
|
||
- 同步 sort_order（与 fix_ip_book_sort_and_images 一致）。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import html
|
||
import importlib.util
|
||
import re
|
||
import sys
|
||
from pathlib import Path
|
||
|
||
ROOT = Path(__file__).resolve().parent.parent
|
||
BOOK_DIR = Path("/Users/karuo/Documents/个人/2、我写的书/《卡若的IP财富旅程》")
|
||
|
||
PART_ID = "part-new-17755513182"
|
||
PART_TITLE = "卡若的IP财富旅程"
|
||
|
||
CHAPTERS = {
|
||
1: ("chapter-ip-1", "PART1 | 我少年时期的互联网启蒙"),
|
||
2: ("chapter-ip-2", "PART2 | 从0-1的过程"),
|
||
3: ("chapter-ip-3", "PART3 | 我的创业旅程"),
|
||
4: ("chapter-ip-4", "PART4 | 私域流量到AI时代的商业进化"),
|
||
5: ("chapter-ip-5", "PART5 | 未来的一些思考"),
|
||
}
|
||
|
||
FILENAME_RE = re.compile(
|
||
r"^[✅⬜]?\s*(\d+)\.(\d+)[- ]+(.+?)(?:\.md)?$",
|
||
re.UNICODE,
|
||
)
|
||
|
||
LINE_IMAGE_ONLY = re.compile(r"^\s*!\[([^\]]*)\]\(([^)]+)\)\s*$")
|
||
|
||
|
||
def load_db():
|
||
mig = ROOT / "scripts" / "migrate_2026_sections.py"
|
||
spec = importlib.util.spec_from_file_location("_mig_db", mig)
|
||
mod = importlib.util.module_from_spec(spec)
|
||
assert spec.loader is not None
|
||
spec.loader.exec_module(mod)
|
||
return mod.DB_CONFIG
|
||
|
||
|
||
def strip_md_title_line(text: str) -> str:
|
||
lines = text.splitlines()
|
||
if lines and lines[0].lstrip().startswith("#"):
|
||
return "\n".join(lines[1:]).lstrip("\n")
|
||
return text
|
||
|
||
|
||
def for_miniprogram_body_plain(text: str) -> str:
|
||
out_lines: list[str] = []
|
||
for line in text.splitlines():
|
||
if line.strip() == "---":
|
||
out_lines.append("")
|
||
else:
|
||
out_lines.append(line)
|
||
body = "\n".join(out_lines)
|
||
body = body.replace("**", "")
|
||
body = re.sub(r"\n{3,}", "\n\n", body)
|
||
return body.strip() + "\n"
|
||
|
||
|
||
def extract_img_blocks_from_db(old_content: str) -> list[str]:
|
||
"""从已入库正文中按文档顺序提取图片块（供复用 URL）。"""
|
||
if not old_content or "<img" not in old_content.lower():
|
||
return []
|
||
s = old_content.strip()
|
||
blocks: list[str] = []
|
||
for m in re.finditer(r"<p[^>]*>\s*(<img\b[^>]+/?>)\s*</p>", s, re.IGNORECASE | re.DOTALL):
|
||
blocks.append(m.group(0).strip())
|
||
if blocks:
|
||
return blocks
|
||
for m in re.finditer(r"<img\b[^>]+/?>", s, re.IGNORECASE):
|
||
blocks.append(f"<p>{m.group(0).strip()}</p>")
|
||
return blocks
|
||
|
||
|
||
def body_html_preserve_images(md_path: Path, old_content: str) -> tuple[str, list[str]]:
|
||
"""
|
||
按 fix_ip_book 的 HTML 段落规则生成正文，图片行使用旧库中的块。
|
||
返回 (body, warnings)
|
||
"""
|
||
warnings: list[str] = []
|
||
old_imgs = extract_img_blocks_from_db(old_content)
|
||
raw = md_path.read_text(encoding="utf-8")
|
||
lines = strip_md_title_line(raw).splitlines()
|
||
|
||
img_idx = 0
|
||
md_img_lines = sum(1 for ln in lines if LINE_IMAGE_ONLY.match(ln))
|
||
|
||
chunks: list[str] = []
|
||
for line in lines:
|
||
if line.strip() == "---":
|
||
chunks.append("")
|
||
continue
|
||
m = LINE_IMAGE_ONLY.match(line)
|
||
if m:
|
||
if img_idx < len(old_imgs):
|
||
chunks.append(old_imgs[img_idx])
|
||
img_idx += 1
|
||
else:
|
||
warnings.append(f"MD 图片行多于库中已存图片 ({md_path.name})，已跳过该行图片")
|
||
chunks.append("<p>（图片：库中无对应已上传块，请检查）</p>")
|
||
continue
|
||
stripped = line.replace("**", "").strip()
|
||
if stripped:
|
||
chunks.append(f"<p>{html.escape(stripped)}</p>")
|
||
else:
|
||
chunks.append("")
|
||
|
||
html_parts: list[str] = []
|
||
for c in chunks:
|
||
if c == "":
|
||
if html_parts and html_parts[-1] != "":
|
||
html_parts.append("")
|
||
else:
|
||
html_parts.append(c)
|
||
body = "\n".join(html_parts).strip() + "\n"
|
||
|
||
rest = len(old_imgs) - img_idx
|
||
if rest > 0:
|
||
warnings.append(f"{md_path.name}: 库中多 {rest} 张图片未在 MD 中引用，已从新正文移除（按 MD 为准）")
|
||
if md_img_lines and not old_imgs:
|
||
warnings.append(f"{md_path.name}: MD 含图片行但库中正文无 <img>，请先跑 fix_ip_book_sort_and_images 上传图片，或使用纯文本上传")
|
||
|
||
return body, warnings
|
||
|
||
|
||
def collect_files(part_num: int) -> list[tuple[str, str, Path]]:
|
||
part_dir = BOOK_DIR / f"PART{part_num}"
|
||
if not part_dir.exists():
|
||
print(f" ⚠ 目录不存在: {part_dir}", file=sys.stderr)
|
||
return []
|
||
|
||
seen_sections: dict[str, tuple[str, str, Path]] = {}
|
||
for f in part_dir.iterdir():
|
||
name = f.name
|
||
clean_name = re.sub(r"\.md(\.md)*$", "", name, flags=re.IGNORECASE)
|
||
m = FILENAME_RE.match(clean_name)
|
||
if not m:
|
||
print(f" ⚠ 跳过无法解析的文件: {name}")
|
||
continue
|
||
p_num, s_num, title_raw = m.group(1), m.group(2), m.group(3).strip()
|
||
if int(p_num) != part_num:
|
||
print(f" ⚠ PART号不匹配，跳过: {name}")
|
||
continue
|
||
ip_id = f"ip{part_num}.{s_num}"
|
||
section_key = f"{part_num}.{s_num}"
|
||
title = title_raw
|
||
if section_key in seen_sections:
|
||
existing_path = seen_sections[section_key][2]
|
||
if str(f).lower().endswith(".md") and not str(existing_path).lower().endswith(".md"):
|
||
seen_sections[section_key] = (ip_id, title, f)
|
||
else:
|
||
seen_sections[section_key] = (ip_id, title, f)
|
||
|
||
result = list(seen_sections.values())
|
||
result.sort(key=lambda x: float(re.sub(r"ip\d+\.", "", x[0])))
|
||
return result
|
||
|
||
|
||
def md_has_image_only_lines(md_path: Path) -> bool:
|
||
raw = md_path.read_text(encoding="utf-8")
|
||
text = strip_md_title_line(raw)
|
||
return any(LINE_IMAGE_ONLY.match(ln) for ln in text.splitlines())
|
||
|
||
|
||
def upsert_chapter(cur, chapter_id: str, chapter_title: str, ip_id: str, title: str, body: str, price: float, sort_order: int):
|
||
cur.execute("SELECT id FROM chapters WHERE id = %s", (ip_id,))
|
||
if cur.fetchone():
|
||
cur.execute(
|
||
"UPDATE chapters SET section_title=%s, content=%s, part_id=%s, part_title=%s, "
|
||
"chapter_id=%s, chapter_title=%s, price=%s, sort_order=%s WHERE id=%s",
|
||
(title, body, PART_ID, PART_TITLE, chapter_id, chapter_title, price, sort_order, ip_id),
|
||
)
|
||
return "updated"
|
||
cur.execute(
|
||
"INSERT INTO chapters (id, section_title, content, part_id, part_title, chapter_id, chapter_title, price, sort_order) "
|
||
"VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)",
|
||
(ip_id, title, body, PART_ID, PART_TITLE, chapter_id, chapter_title, price, sort_order),
|
||
)
|
||
return "created"
|
||
|
||
|
||
def main():
|
||
try:
|
||
import pymysql
|
||
except ImportError:
|
||
print("需要: pip install pymysql", file=sys.stderr)
|
||
sys.exit(1)
|
||
|
||
dry_run = "--dry-run" in sys.argv
|
||
price = 1.0
|
||
|
||
cfg = load_db()
|
||
conn = pymysql.connect(**cfg)
|
||
cur = conn.cursor()
|
||
|
||
total_ok = 0
|
||
total_err = 0
|
||
all_warnings: list[str] = []
|
||
|
||
for part_num, (chapter_id, chapter_title) in CHAPTERS.items():
|
||
print(f"\n{'='*60}")
|
||
print(f"PART{part_num} → {chapter_id} | {chapter_title}")
|
||
print(f"{'='*60}")
|
||
files = collect_files(part_num)
|
||
if not files:
|
||
print(" 无文件，跳过")
|
||
continue
|
||
|
||
for sort_order, (ip_id, title, path) in enumerate(files, start=1):
|
||
try:
|
||
has_imgs = md_has_image_only_lines(path)
|
||
if has_imgs:
|
||
cur.execute("SELECT content FROM chapters WHERE id = %s", (ip_id,))
|
||
row = cur.fetchone()
|
||
old_content = row[0] if row and row[0] else ""
|
||
body, warns = body_html_preserve_images(path, old_content)
|
||
for w in warns:
|
||
all_warnings.append(f"{ip_id}: {w}")
|
||
else:
|
||
raw = path.read_text(encoding="utf-8")
|
||
body = for_miniprogram_body_plain(strip_md_title_line(raw))
|
||
except Exception as e:
|
||
print(f" ✗ 处理失败 {ip_id} ({path.name}): {e}")
|
||
total_err += 1
|
||
continue
|
||
|
||
if dry_run:
|
||
mode = "html+保留图" if has_imgs else "plain"
|
||
print(f" [dry] {ip_id} sort={sort_order} [{mode}] {title[:36]} ({path.name})")
|
||
total_ok += 1
|
||
continue
|
||
|
||
try:
|
||
action = upsert_chapter(
|
||
cur, chapter_id, chapter_title, ip_id, title, body, price, sort_order
|
||
)
|
||
conn.commit()
|
||
mode = "html" if has_imgs else "plain"
|
||
print(f" ✓ [{action}] {ip_id} sort={sort_order} [{mode}] {title[:40]}")
|
||
total_ok += 1
|
||
except Exception as e:
|
||
conn.rollback()
|
||
print(f" ✗ 上传失败 {ip_id} ({path.name}): {e}")
|
||
total_err += 1
|
||
|
||
conn.close()
|
||
print(f"\n{'='*60}")
|
||
print(f"完成：成功 {total_ok} | 失败 {total_err}")
|
||
if all_warnings:
|
||
print("\n⚠ 提示：")
|
||
for w in all_warnings[:50]:
|
||
print(f" - {w}")
|
||
if len(all_warnings) > 50:
|
||
print(f" ... 另有 {len(all_warnings) - 50} 条")
|
||
if dry_run:
|
||
print("（dry-run 模式，未实际写库）")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|