Group02-notes/note_organizer.py

738 lines
28 KiB
Python
Raw Normal View History

import streamlit as st
from datetime import datetime
import json
import os
import re
from collections import Counter
# 1. 页面配置
st.set_page_config(page_title="学习笔记整理器", page_icon="📚", layout="wide")
# 添加自定义CSS样式
st.markdown("""
<style>
/* 全局样式优化 */
.main {
padding-top: 2rem;
}
/* 标题样式 */
h1 {
color: #1a1a1a;
font-weight: 700;
margin-bottom: 1.5rem;
}
/* 侧边栏样式 */
[data-testid="stSidebar"] {
background-color: #f8f9fa;
border-right: 2px solid #e9ecef;
}
/* 笔记卡片样式 */
.stExpander {
border: 1px solid #dee2e6;
border-radius: 8px;
margin-bottom: 1rem;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
transition: all 0.3s ease;
}
.stExpander:hover {
box-shadow: 0 4px 8px rgba(0,0,0,0.15);
}
/* 按钮样式优化 */
.stButton > button {
border-radius: 6px;
font-weight: 500;
transition: all 0.2s ease;
}
.stButton > button:hover {
transform: translateY(-2px);
box-shadow: 0 4px 8px rgba(0,0,0,0.2);
}
/* 输入框样式 */
.stTextInput > div > div > input,
.stTextArea > div > div > textarea,
.stSelectbox > div > div > select {
border-radius: 6px;
border: 1px solid #ced4da;
transition: border-color 0.2s ease;
}
.stTextInput > div > div > input:focus,
.stTextArea > div > div > textarea:focus,
.stSelectbox > div > div > select:focus {
border-color: #007bff;
box-shadow: 0 0 0 0.2rem rgba(0, 123, 255, 0.25);
}
/* 标签样式 */
.tag {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
padding: 4px 12px;
border-radius: 20px;
font-size: 12px;
font-weight: 500;
margin: 3px;
display: inline-block;
box-shadow: 0 2px 4px rgba(102, 126, 234, 0.3);
}
/* 关键词标签样式 */
.keyword {
background: linear-gradient(135deg, #f093fb 0%, #f5576c 100%);
color: white;
padding: 4px 12px;
border-radius: 20px;
font-size: 12px;
font-weight: 500;
margin: 3px;
display: inline-block;
box-shadow: 0 2px 4px rgba(240, 147, 251, 0.3);
}
/* 分隔线样式 */
hr {
border: none;
height: 2px;
background: linear-gradient(90deg, transparent, #007bff, transparent);
margin: 2rem 0;
}
/* 统计卡片样式 */
[data-testid="stMetricValue"] {
font-size: 2rem;
font-weight: 700;
color: #007bff;
}
/* 信息框样式 */
.stAlert {
border-radius: 8px;
border-left: 4px solid;
}
/* 成功提示 */
.stAlert[role="alert"] {
background-color: #d4edda;
border-color: #28a745;
}
/* 警告提示 */
.stAlert[role="alertwarning"] {
background-color: #fff3cd;
border-color: #ffc107;
}
/* 错误提示 */
.stAlert[role="alerterror"] {
background-color: #f8d7da;
border-color: #dc3545;
}
/* 响应式设计 */
@media (max-width: 768px) {
.main {
padding: 1rem;
}
.stButton > button {
width: 100%;
margin: 5px 0;
}
}
</style>
""", unsafe_allow_html=True)
st.title("📚 学习笔记整理器")
# 文本提炼函数
def extract_key_content(content, max_sentences=3, max_keywords=5):
"""提炼笔记的关键内容"""
if not content or len(content.strip()) < 10:
return {"summary": "内容太短,无法提炼", "keywords": []}
# 分句
sentences = re.split(r'[。!?\n]', content)
sentences = [s.strip() for s in sentences if s.strip()]
# 提取关键句子(基于句子长度和关键词密度)
sentence_scores = []
for sentence in sentences:
score = len(sentence)
# 检查是否包含常见关键词
keywords = ['重要', '关键', '核心', '主要', '注意', '必须', '应该', '需要', '总结', '结论']
for kw in keywords:
if kw in sentence:
score += 20
sentence_scores.append((sentence, score))
# 按分数排序,取前几句
sentence_scores.sort(key=lambda x: x[1], reverse=True)
top_sentences = [s[0] for s in sentence_scores[:max_sentences]]
# 提取关键词
words = re.findall(r'[\u4e00-\u9fa5]{2,}', content)
word_freq = Counter(words)
# 过滤常见词
stop_words = ['', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '我们', '你们', '他们']
keywords = [w for w, c in word_freq.most_common(max_keywords * 2) if w not in stop_words][:max_keywords]
return {
"summary": "".join(top_sentences) + "" if top_sentences else "无法提取摘要",
"keywords": keywords
}
# 2. 数据持久化函数
def save_notes():
"""保存笔记到 JSON 文件"""
data = {
"notes": st.session_state.notes,
"categories": st.session_state.categories
}
with open('notes_data.json', 'w', encoding='utf-8') as f:
json.dump(data, f, ensure_ascii=False, indent=2)
def load_notes():
"""从 JSON 文件加载笔记"""
if os.path.exists('notes_data.json'):
with open('notes_data.json', 'r', encoding='utf-8') as f:
data = json.load(f)
st.session_state.notes = data.get("notes", [])
st.session_state.categories = data.get("categories", ["编程", "数学", "英语", "其他"])
# 3. 初始化数据
if "notes" not in st.session_state:
st.session_state.notes = []
load_notes()
if "categories" not in st.session_state:
st.session_state.categories = ["编程", "数学", "英语", "其他"]
load_notes()
# 初始化编辑状态
if "editing_note" not in st.session_state:
st.session_state.editing_note = None
# 4. 左侧侧边栏 - 添加笔记和管理类型
with st.sidebar:
st.header("📝 添加笔记")
# 笔记标题
title = st.text_input("标题", placeholder="输入笔记标题")
# 分类选择(支持自定义)
category = st.selectbox(
"选择分类",
st.session_state.categories,
help="选择笔记的分类"
)
# 自定义分类输入
new_category = st.text_input(
"或创建新分类",
placeholder="输入新分类名称,按回车添加",
key="new_category_input"
)
# 添加新分类按钮
if st.button(" 添加新分类"):
if new_category and new_category not in st.session_state.categories:
st.session_state.categories.append(new_category)
save_notes()
st.success(f"已添加新分类:{new_category}")
st.rerun()
elif new_category in st.session_state.categories:
st.warning("该分类已存在")
# 笔记内容
content = st.text_area(
"笔记内容",
placeholder="输入笔记内容...",
height=200
)
# 标签输入
tags_input = st.text_input(
"标签",
placeholder="输入标签,用逗号分隔 (例如: 重要, 复习, 考试)",
help="为笔记添加多个标签,便于分类和搜索"
)
tags = [tag.strip() for tag in tags_input.split(",") if tag.strip()]
# 实时预览提炼结果
if content and len(content.strip()) > 10:
with st.expander("🔍 预览提炼结果", expanded=False):
extracted = extract_key_content(content)
st.markdown("**摘要预览:**")
st.info(extracted['summary'])
st.markdown("**关键词预览:**")
if extracted['keywords']:
keywords_html = " ".join([f'<span style="background-color: #fff3e0; color: #e65100; padding: 2px 8px; border-radius: 4px; margin-right: 5px; font-size: 12px;">{kw}</span>' for kw in extracted['keywords']])
st.markdown(keywords_html, unsafe_allow_html=True)
# 添加按钮
if st.button("添加笔记", type="primary"):
if title and content:
note = {
"id": len(st.session_state.notes) + 1,
"title": title,
"category": category,
"content": content,
"tags": tags,
"created_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
"updated_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
}
st.session_state.notes.append(note)
save_notes()
st.success("笔记添加成功!")
else:
st.warning("请填写标题和内容")
st.divider()
# 显示所有分类
st.subheader("📂 所有分类")
for cat in st.session_state.categories:
st.markdown(f"- {cat}")
# 5. 主界面 - 笔记展示和搜索
st.header("📖 我的笔记")
# 搜索和排序区域
col1, col2, col3, col4, col5 = st.columns([2, 1, 1, 1, 1])
with col1:
# 搜索关键词
search_query = st.text_input(
"🔍 搜索关键词",
placeholder="输入关键词...",
help="支持模糊搜索"
)
with col2:
# 搜索范围选择
search_scope = st.selectbox(
"搜索范围",
["全部", "仅标题", "仅内容", "仅类型", "仅标签"],
help="选择搜索的范围"
)
with col3:
# 分类筛选
filter_category = st.selectbox(
"筛选分类",
["全部"] + st.session_state.categories,
help="按分类筛选笔记"
)
with col4:
# 标签筛选
all_tags = list(set(tag for note in st.session_state.notes for tag in note.get("tags", [])))
filter_tag = st.selectbox(
"筛选标签",
["全部"] + sorted(all_tags),
help="按标签筛选笔记"
)
with col5:
# 排序方式
sort_by = st.selectbox(
"排序方式",
["最新", "最旧", "标题A-Z", "标题Z-A", "类型A-Z", "类型Z-A"],
help="选择笔记的排序方式"
)
# 批量提炼功能
st.divider()
col_batch1, col_batch2 = st.columns([3, 1])
with col_batch1:
st.markdown("### ✨ 批量提炼")
with col_batch2:
if st.button("🔄 提炼所有笔记", key="batch_extract"):
for note in st.session_state.notes:
if len(note['content'].strip()) > 10:
extracted = extract_key_content(note['content'])
st.session_state[f'extracted_{note["id"]}'] = extracted
st.success(f"已提炼 {len(st.session_state.notes)} 条笔记的关键内容!")
st.rerun()
# 6. 显示笔记
if st.session_state.notes:
# 筛选和搜索逻辑
filtered_notes = []
for note in st.session_state.notes:
# 分类筛选
category_match = filter_category == "全部" or note["category"] == filter_category
# 标签筛选
tag_match = filter_tag == "全部" or filter_tag in note.get("tags", [])
# 关键词搜索(根据选择范围)
search_match = True
if search_query:
query = search_query.lower()
if search_scope == "全部":
search_match = (
query in note["title"].lower() or
query in note["content"].lower() or
query in note["category"].lower() or
any(query in tag.lower() for tag in note.get("tags", []))
)
elif search_scope == "仅标题":
search_match = query in note["title"].lower()
elif search_scope == "仅内容":
search_match = query in note["content"].lower()
elif search_scope == "仅类型":
search_match = query in note["category"].lower()
elif search_scope == "仅标签":
search_match = any(query in tag.lower() for tag in note.get("tags", []))
if category_match and tag_match and search_match:
filtered_notes.append(note)
# 排序逻辑
if sort_by == "最新":
filtered_notes.sort(key=lambda x: x["created_at"], reverse=True)
elif sort_by == "最旧":
filtered_notes.sort(key=lambda x: x["created_at"])
elif sort_by == "标题A-Z":
filtered_notes.sort(key=lambda x: x["title"].lower())
elif sort_by == "标题Z-A":
filtered_notes.sort(key=lambda x: x["title"].lower(), reverse=True)
elif sort_by == "类型A-Z":
filtered_notes.sort(key=lambda x: x["category"].lower())
elif sort_by == "类型Z-A":
filtered_notes.sort(key=lambda x: x["category"].lower(), reverse=True)
# 显示筛选结果
if filtered_notes:
st.info(f"找到 {len(filtered_notes)} 条笔记")
# 使用两列布局展示笔记
cols = st.columns(2)
for i, note in enumerate(filtered_notes):
with cols[i % 2]:
# 检查是否正在编辑此笔记
if st.session_state.editing_note == note['id']:
with st.expander(f"✏️ 编辑: {note['title']}", expanded=True):
# 编辑表单
edit_title = st.text_input("标题", value=note['title'], key=f"edit_title_{note['id']}")
edit_category = st.selectbox(
"分类",
st.session_state.categories,
index=st.session_state.categories.index(note['category']) if note['category'] in st.session_state.categories else 0,
key=f"edit_category_{note['id']}"
)
edit_content = st.text_area("内容", value=note['content'], height=200, key=f"edit_content_{note['id']}")
# 编辑标签
current_tags = ", ".join(note.get("tags", []))
edit_tags = st.text_input(
"标签",
value=current_tags,
key=f"edit_tags_{note['id']}",
help="输入标签,用逗号分隔"
)
edit_tags_list = [tag.strip() for tag in edit_tags.split(",") if tag.strip()]
# 保存和取消按钮
col_save, col_cancel = st.columns(2)
with col_save:
if st.button("💾 保存修改", key=f"save_{note['id']}", type="primary"):
note['title'] = edit_title
note['category'] = edit_category
note['content'] = edit_content
note['tags'] = edit_tags_list
note['updated_at'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
st.session_state.editing_note = None
save_notes()
st.success("笔记已更新!")
st.rerun()
with col_cancel:
if st.button("❌ 取消", key=f"cancel_{note['id']}"):
st.session_state.editing_note = None
st.rerun()
else:
# 正常显示笔记
with st.expander(f"📌 {note['title']}", expanded=False):
# 显示笔记元信息
st.markdown(f"**分类:** {note['category']}")
# 显示标签
if note.get("tags"):
tags_html = " ".join([f'<span style="background-color: #e1f5fe; color: #01579b; padding: 2px 8px; border-radius: 4px; margin-right: 5px; font-size: 12px;">{tag}</span>' for tag in note["tags"]])
st.markdown(f"**标签:** {tags_html}", unsafe_allow_html=True)
st.markdown(f"**创建时间:** {note['created_at']}")
if 'updated_at' in note:
st.markdown(f"**更新时间:** {note['updated_at']}")
st.markdown("---")
# 提炼内容按钮
if st.button("✨ 提炼内容", key=f"extract_{note['id']}"):
extracted = extract_key_content(note['content'])
st.session_state[f'extracted_{note["id"]}'] = extracted
# 显示提炼结果
if f'extracted_{note["id"]}' in st.session_state:
extracted = st.session_state[f'extracted_{note["id"]}']
with st.expander("📝 提炼结果", expanded=True):
st.markdown("**摘要:**")
st.info(extracted['summary'])
st.markdown("**关键词:**")
if extracted['keywords']:
keywords_html = " ".join([f'<span style="background-color: #fff3e0; color: #e65100; padding: 2px 8px; border-radius: 4px; margin-right: 5px; font-size: 12px;">{kw}</span>' for kw in extracted['keywords']])
st.markdown(keywords_html, unsafe_allow_html=True)
else:
st.warning("未找到关键词")
# 显示笔记内容
st.markdown(note['content'])
# 操作按钮
col_edit, col_delete = st.columns(2)
with col_edit:
if st.button("✏️ 编辑", key=f"edit_{note['id']}"):
st.session_state.editing_note = note['id']
st.rerun()
with col_delete:
if st.button("🗑️ 删除", key=f"delete_{note['id']}"):
st.session_state.notes.remove(note)
st.session_state.editing_note = None
save_notes()
st.rerun()
else:
st.warning("没有找到匹配的笔记")
else:
st.info("还没有笔记,请在左侧添加您的第一条笔记!")
# 7. 统计信息
st.divider()
st.subheader("📊 统计信息")
# 笔记和分类统计
col_stats1, col_stats2 = st.columns(2)
with col_stats1:
st.metric("总笔记数", len(st.session_state.notes))
with col_stats2:
all_tags = list(set(tag for note in st.session_state.notes for tag in note.get("tags", [])))
st.metric("总标签数", len(all_tags))
# 分类统计
st.markdown("### 分类统计")
cat_stat_cols = st.columns(min(5, len(st.session_state.categories)))
for i, cat in enumerate(st.session_state.categories):
if i < len(cat_stat_cols):
with cat_stat_cols[i]:
count = len([n for n in st.session_state.notes if n["category"] == cat])
st.metric(cat, count)
# 标签统计
if all_tags:
st.markdown("### 标签统计")
tag_stat_cols = st.columns(min(5, len(all_tags)))
for i, tag in enumerate(sorted(all_tags)):
if i < len(tag_stat_cols):
with tag_stat_cols[i]:
count = len([n for n in st.session_state.notes if tag in n.get("tags", [])])
st.metric(tag, count)
# 8. 数据管理
st.divider()
st.subheader("💾 数据管理")
# 导入JSON文件
st.markdown("### 📥 导入笔记")
tab_json, tab_txt = st.tabs(["JSON文件", "文本文件"])
with tab_json:
uploaded_file = st.file_uploader("选择JSON文件", type=['json'], help="选择之前导出的JSON文件", key="json_uploader")
if uploaded_file is not None:
try:
# 读取并解析JSON文件
import_data = json.load(uploaded_file)
# 显示导入预览
st.info(f"文件包含 {len(import_data.get('notes', []))} 条笔记")
# 显示笔记列表预览
with st.expander("📋 查看文件内容", expanded=False):
for i, note in enumerate(import_data.get('notes', [])[:5]):
st.markdown(f"**{i+1}. {note.get('title', '无标题')}**")
st.markdown(f" 分类: {note.get('category', '未知')}")
st.markdown(f" 时间: {note.get('created_at', '未知')}")
st.markdown("---")
if len(import_data.get('notes', [])) > 5:
st.info(f"还有 {len(import_data.get('notes', [])) - 5} 条笔记...")
# 导入选项
col_merge, col_replace = st.columns(2)
with col_merge:
if st.button("🔄 合并导入", type="primary", key="merge_json"):
# 合并导入:保留现有笔记,添加新笔记
new_notes = import_data.get('notes', [])
for note in new_notes:
note['id'] = len(st.session_state.notes) + 1
st.session_state.notes.append(note)
# 合并分类
new_categories = import_data.get('categories', [])
for cat in new_categories:
if cat not in st.session_state.categories:
st.session_state.categories.append(cat)
save_notes()
st.success(f"成功导入 {len(new_notes)} 条笔记!")
st.rerun()
with col_replace:
if st.button("⚠️ 替换导入", key="replace_json"):
# 替换导入:清空现有笔记,导入新笔记
st.session_state.notes = import_data.get('notes', [])
st.session_state.categories = import_data.get('categories', ["编程", "数学", "英语", "其他"])
st.session_state.editing_note = None
save_notes()
st.success(f"成功替换为 {len(st.session_state.notes)} 条笔记!")
st.rerun()
except Exception as e:
st.error(f"文件解析失败: {str(e)}")
with tab_txt:
# 导入文本文件
txt_file = st.file_uploader("选择文本文件", type=['txt'], help="选择要导入的文本文件", key="txt_uploader")
if txt_file is not None:
try:
# 读取文本文件内容
content = txt_file.read().decode('utf-8')
# 显示文件内容预览
st.info(f"文件大小: {len(content)} 字符")
with st.expander("📋 查看文件内容", expanded=False):
st.text(content[:1000])
if len(content) > 1000:
st.info(f"还有 {len(content) - 1000} 个字符...")
# 设置导入参数
col_title, col_cat = st.columns(2)
with col_title:
import_title = st.text_input("笔记标题", value=txt_file.name.replace('.txt', ''), help="为导入的笔记设置标题")
with col_cat:
import_category = st.selectbox("笔记分类", st.session_state.categories)
# 导入按钮
if st.button("📥 导入文本文件", type="primary"):
note = {
"id": len(st.session_state.notes) + 1,
"title": import_title,
"category": import_category,
"content": content,
"created_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
"updated_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
}
st.session_state.notes.append(note)
save_notes()
st.success(f"成功导入笔记:{import_title}")
st.rerun()
except Exception as e:
st.error(f"文件读取失败: {str(e)}")
st.divider()
# 导出功能
st.markdown("### 📤 导出笔记")
export_tab_json, export_tab_txt = st.tabs(["JSON格式", "文本格式"])
with export_tab_json:
if st.button("📤 导出为JSON", key="export_json"):
st.download_button(
label="下载 JSON 文件",
data=json.dumps({"notes": st.session_state.notes, "categories": st.session_state.categories}, ensure_ascii=False, indent=2),
file_name=f"notes_backup_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
mime="application/json"
)
with export_tab_txt:
# 导出选项
export_option = st.radio("导出选项", ["导出所有笔记", "导出单个笔记"])
if export_option == "导出所有笔记":
if st.button("📤 导出所有笔记为文本", type="primary", key="export_all_txt"):
# 合并所有笔记为一个文本文件
all_content = "=" * 50 + "\n"
all_content += f"学习笔记备份 - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n"
all_content += "=" * 50 + "\n\n"
for note in st.session_state.notes:
all_content += "-" * 40 + "\n"
all_content += f"标题: {note['title']}\n"
all_content += f"分类: {note['category']}\n"
all_content += f"创建时间: {note['created_at']}\n"
all_content += "-" * 40 + "\n\n"
all_content += note['content'] + "\n\n"
st.download_button(
label="下载文本文件",
data=all_content,
file_name=f"notes_all_{datetime.now().strftime('%Y%m%d_%H%M%S')}.txt",
mime="text/plain"
)
else:
# 导出单个笔记
if st.session_state.notes:
note_titles = [f"{note['id']}. {note['title']}" for note in st.session_state.notes]
selected_note = st.selectbox("选择要导出的笔记", note_titles)
if st.button("📤 导出选中笔记", type="primary", key="export_single_txt"):
# 找到选中的笔记
note_id = int(selected_note.split('.')[0])
note = next((n for n in st.session_state.notes if n['id'] == note_id), None)
if note:
# 格式化笔记内容
note_content = "=" * 50 + "\n"
note_content += f"标题: {note['title']}\n"
note_content += f"分类: {note['category']}\n"
note_content += f"创建时间: {note['created_at']}\n"
if 'updated_at' in note:
note_content += f"更新时间: {note['updated_at']}\n"
note_content += "=" * 50 + "\n\n"
note_content += note['content']
st.download_button(
label="下载文本文件",
data=note_content,
file_name=f"note_{note['id']}_{note['title']}.txt",
mime="text/plain"
)
else:
st.info("没有笔记可导出")
st.divider()
# 清空功能
col_clear = st.columns(1)[0]
with col_clear:
if st.button("🗑️ 清空所有笔记"):
if st.session_state.notes:
st.warning("⚠️ 此操作不可恢复!")
if st.button("确认清空"):
st.session_state.notes = []
st.session_state.editing_note = None
save_notes()
st.success("所有笔记已清空!")
st.rerun()
else:
st.info("没有笔记可清空")