kai
0801f7c7df
1. UI 层： - 抛弃网格卡片结构，改版为沉浸式的“图书墙”(1:1.43 原比例包含模式)。 - 新增悬浮深色遮罩系统(hover-details)，解绑评分点击阻塞。 - 过滤系统默认进入“在读”状态页，彻底移除冗余无效的全选按钮。 2. 抓取与刮削层 (scrape.py)： - 抛弃对 ISBN 查询 Google Books 的严重强依赖。 - 重构抓取链路，首选 Goodreads 与特供的 Books.com.tw(博客来) 高精爬取港台原版资料。 - 建立 Amazon/Goodreads 图片去码净化正则，告别低分辨率与畸形图片。 - 修复 bs4 (.select_first) 解析选择器在旧版环境的兼容性异常。 3. Agent AI 数据管线设计 (bookshelf.py)： - 开放基于 --json 与 --cover 的强力直接注入功能。 - 升级 add 命令作为最优先级的录入手段，免去繁琐的 enrich 阶段，直接连带高清图和满载元数据强插。 - 建立入库反重名智能拦截 (title + author 交叉校验)，形成完美的防呆与自动化壁垒。
210 lines
7.6 KiB
Python
210 lines
7.6 KiB
Python
"""网页生成器 — 读取数据库，生成静态 HTML 展示页面。"""
|
|
|
|
import os
|
|
import json
|
|
import db
|
|
|
|
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
TEMPLATE_PATH = os.path.join(BASE_DIR, "templates", "index.html")
|
|
STYLE_PATH = os.path.join(BASE_DIR, "static", "style.css")
|
|
OUTPUT_DIR = os.path.join(BASE_DIR, "output")
|
|
OUTPUT_PATH = os.path.join(OUTPUT_DIR, "index.html")
|
|
|
|
|
|
def _escape(text):
|
|
"""简单的 HTML 转义。"""
|
|
if not text:
|
|
return ""
|
|
return (str(text)
|
|
.replace("&", "&")
|
|
.replace("<", "<")
|
|
.replace(">", ">")
|
|
.replace('"', """))
|
|
|
|
|
|
def _render_book_card(book):
|
|
"""渲染单本书的 HTML 卡片。"""
|
|
# 封面：优先本地 BLOB 提取后的相对路径，其次远程 URL
|
|
cover = book.get("cover_url") or ""
|
|
if book.get("cover_blob"):
|
|
cover = f"covers/{book['id']}.jpg"
|
|
|
|
cover_html = (f'<img class="card-cover" src="{_escape(cover)}" alt="封面" loading="lazy">'
|
|
if cover
|
|
else '<div class="card-cover card-cover--placeholder">📖</div>')
|
|
|
|
rating_html = ""
|
|
if book.get("rating"):
|
|
stars = "★" * book["rating"] + "☆" * (5 - book["rating"])
|
|
rating_html = f'<div class="card-rating personal">{stars}</div>'
|
|
|
|
scores = []
|
|
if book.get("douban_score"):
|
|
ds = f'D {book["douban_score"]}'
|
|
if book.get("douban_url"):
|
|
scores.append(f'<a href="{_escape(book["douban_url"])}" target="_blank" class="score douban" title="在豆瓣查看">{ds}</a>')
|
|
else:
|
|
scores.append(f'<span class="score douban">{ds}</span>')
|
|
|
|
if book.get("goodreads_score"):
|
|
gs = f'G {book["goodreads_score"]}'
|
|
if book.get("goodreads_url"):
|
|
scores.append(f'<a href="{_escape(book["goodreads_url"])}" target="_blank" class="score goodreads" title="在 Goodreads 查看">{gs}</a>')
|
|
else:
|
|
scores.append(f'<span class="score goodreads">{gs}</span>')
|
|
|
|
scores_html = f'<div class="card-scores-container">{"".join(scores)}</div>' if scores else ""
|
|
|
|
tags_html = ""
|
|
if book.get("tags"):
|
|
tag_spans = "".join(
|
|
f'<span class="tag" data-tag="{_escape(t.strip())}">{_escape(t.strip())}</span>'
|
|
for t in book["tags"].split(",") if t.strip()
|
|
)
|
|
tags_html = f'<div class="card-tags">{tag_spans}</div>'
|
|
|
|
meta_parts = []
|
|
if book.get("author"):
|
|
a_text = _escape(book["author"])
|
|
if book.get("author_en"):
|
|
a_text += f' <span style="opacity: 0.7;">[{_escape(book["author_en"])}]</span>'
|
|
meta_parts.append(a_text)
|
|
if book.get("translator"):
|
|
meta_parts.append(f'译: {_escape(book["translator"])}')
|
|
if book.get("publisher"):
|
|
meta_parts.append(f'{_escape(book["publisher"])}')
|
|
if book.get("pub_date"):
|
|
meta_parts.append(f'{_escape(book["pub_date"])}')
|
|
meta_html = f'<div class="card-meta">{" · ".join(meta_parts)}</div>' if meta_parts else ""
|
|
|
|
notes_html = ""
|
|
if book.get("notes"):
|
|
notes_html = f'<div class="card-notes">{_escape(book["notes"])}</div>'
|
|
|
|
dates = []
|
|
if book.get("start_date"):
|
|
dates.append(f'开始: {_escape(book["start_date"])}')
|
|
if book.get("finish_date"):
|
|
dates.append(f'完成: {_escape(book["finish_date"])}')
|
|
dates_html = f'<div class="card-dates">{" · ".join(dates)}</div>' if dates else ""
|
|
|
|
format_badge = "📱 电子书" if book.get("format") == "ebook" else "📕 纸质书"
|
|
group_html = f'<div class="card-group">{_escape(book.get("group", ""))}</div>' if book.get("group") else ""
|
|
priority = book.get("priority", "")
|
|
priority_html = f'<span class="card-priority">{priority}</span>' if priority else ""
|
|
|
|
# 默认加上在读状态的类（如果在读）
|
|
is_reading = ' is-reading' if book.get('status') == 'reading' else ''
|
|
|
|
return f"""
|
|
<div class="book-card{is_reading}" data-status="{_escape(book.get('status', ''))}"
|
|
data-format="{_escape(book.get('format', ''))}"
|
|
data-tags="{_escape(book.get('tags', ''))}"
|
|
data-group="{_escape(book.get('group', ''))}">
|
|
|
|
<div class="card-cover-wrapper">
|
|
{cover_html}
|
|
<div class="card-hover-details">
|
|
{group_html}
|
|
<h3 class="card-title">{_escape(book.get('title', ''))} {priority_html}</h3>
|
|
{f'<div class="card-title-en">{_escape(book["title_en"])}</div>' if book.get("title_en") else ""}
|
|
<div class="meta-section">
|
|
{meta_html}
|
|
</div>
|
|
{rating_html}
|
|
<div class="meta-dates">
|
|
{dates_html}
|
|
</div>
|
|
{notes_html}
|
|
{tags_html}
|
|
<div class="card-format">{format_badge}</div>
|
|
</div>
|
|
</div>
|
|
|
|
{scores_html}
|
|
</div>"""
|
|
|
|
|
|
def build():
|
|
"""生成静态 HTML 页面，返回输出路径。"""
|
|
os.makedirs(OUTPUT_DIR, exist_ok=True)
|
|
|
|
books = db.list_books()
|
|
stats = db.get_stats()
|
|
all_tags = db.get_all_tags()
|
|
|
|
cards_html = "\n".join(_render_book_card(b) for b in books)
|
|
|
|
# 读取 CSS
|
|
with open(STYLE_PATH, "r", encoding="utf-8") as f:
|
|
css = f.read()
|
|
|
|
# 读取模板并填充
|
|
with open(TEMPLATE_PATH, "r", encoding="utf-8") as f:
|
|
template = f.read()
|
|
|
|
# 统计数据
|
|
total = stats["total"]
|
|
reading = stats["by_status"].get("reading", 0)
|
|
read = stats["by_status"].get("read", 0)
|
|
to_read = stats["by_status"].get("to-read", 0)
|
|
paper = stats["by_format"].get("paper", 0)
|
|
ebook = stats["by_format"].get("ebook", 0)
|
|
|
|
# 领域/分组概览
|
|
|
|
from collections import defaultdict
|
|
group_books = defaultdict(list)
|
|
for b in books:
|
|
grp = b.get("group") or "未分类"
|
|
group_books[grp].append(b)
|
|
|
|
group_sections = []
|
|
for grp, gbooks in sorted(group_books.items()):
|
|
covers_html = []
|
|
for b in gbooks:
|
|
cid = str(b["id"])
|
|
if b.get("cover_blob") or b.get("cover_local"):
|
|
src = f"./covers/{cid}.jpg"
|
|
else:
|
|
src = b.get("cover_url", "https://via.placeholder.com/150?text=No+Cover")
|
|
cv = f'<img src="{src}" class="tiny-cover" title="{_escape(b.get("title",""))}">'
|
|
covers_html.append(cv)
|
|
|
|
section = f'''
|
|
<div class="group-section">
|
|
<h2 class="group-section-title">{_escape(grp)} <span class="group-count">({len(gbooks)})</span></h2>
|
|
<div class="group-covers">
|
|
{"".join(covers_html)}
|
|
</div>
|
|
</div>
|
|
'''
|
|
group_sections.append(section)
|
|
|
|
group_overview_html = "".join(group_sections)
|
|
|
|
html = (template
|
|
.replace("{{CSS}}", css)
|
|
.replace("{{TOTAL}}", str(total))
|
|
.replace("{{READING}}", str(reading))
|
|
.replace("{{READ}}", str(read))
|
|
.replace("{{TO_READ}}", str(to_read))
|
|
.replace("{{PAPER}}", str(paper))
|
|
.replace("{{EBOOK}}", str(ebook))
|
|
.replace("{{GROUP_OVERVIEW_HTML}}", group_overview_html)
|
|
.replace("{{BOOK_CARDS}}", cards_html))
|
|
|
|
with open(OUTPUT_PATH, "w", encoding="utf-8") as f:
|
|
f.write(html)
|
|
|
|
# 提取 BLOB 封面到 output/covers/
|
|
covers_dir = os.path.join(OUTPUT_DIR, "covers")
|
|
os.makedirs(covers_dir, exist_ok=True)
|
|
for b in books:
|
|
if b.get("cover_blob"):
|
|
cover_path = os.path.join(covers_dir, f"{b['id']}.jpg")
|
|
with open(cover_path, "wb") as f:
|
|
f.write(b["cover_blob"])
|
|
|
|
return OUTPUT_PATH
|