hahaju/aiagents-stock
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

1.修复docker运行无法打开页面问题 (#6)

Browse Source 
2.支持下载DM文件
3.支持硅基流动，阿里百炼模型
This commit is contained in:
wsx180808
2025-10-30 08:10:15 +08:00
committed by GitHub
parent 2cf43884e0
commit dbc6b5b359
9 changed files with 1224 additions and 741 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app.py
+410 -407
View File
File diff suppressed because it is too large Load Diff
docker-compose.yml
+2 -2
View File
@@ -7,7 +7,7 @@ services:
dockerfile: Dockerfile
container_name: agentsstock1
ports:
- "8503:8501"
- "8503:8503"
volumes:
# 数据和数据库持久化 - 使用目录挂载而不是文件挂载
- ./data:/app/data
@@ -20,7 +20,7 @@ services:
networks:
- agentsstock-network
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8501/_stcore/health"]
test: ["CMD", "curl", "-f", "http://localhost:8503/_stcore/health"]
interval: 30s
timeout: 10s
retries: 3
longhubang_ui.py
+155 -4
View File
@@ -136,9 +136,12 @@ def display_analysis_tab():
)
with col3:
# 导入model_config.py中定义的model_options
from model_config import model_options as app_model_options
selected_model = st.selectbox(
"AI模型",
["deepseek-chat", "deepseek-reasoner"],
list(app_model_options.keys()),
format_func=lambda x: app_model_options[x],
help="Reasoner模型提供更强的推理能力"
)
@@ -721,12 +724,12 @@ def display_visualizations(result):
def display_pdf_export_section(result):
"""显示PDF导出功能"""
st.markdown("### 📄 导出PDF报告")
st.markdown("### 📄 导出报告")
col1, col2 = st.columns([3, 1])
col1, col2, col3 = st.columns([2, 1, 1])
with col1:
st.info("💡 点击按钮生成并下载专业的PDF分析报告")
st.info("💡 点击按钮生成并下载专业分析报告")
with col2:
if st.button("📥 生成PDF", type="primary", width='stretch'):
@@ -752,6 +755,154 @@ def display_pdf_export_section(result):
except Exception as e:
st.error(f"❌ PDF生成失败: {str(e)}")
with col3:
if st.button("📝 生成Markdown", type="secondary", width='stretch'):
with st.spinner("正在生成Markdown报告..."):
try:
# 生成Markdown内容
markdown_content = generate_markdown_report(result)
# 提供下载
st.download_button(
label="📥 下载Markdown报告",
data=markdown_content,
file_name=f"智瞰龙虎报告_{datetime.now().strftime('%Y%m%d_%H%M%S')}.md",
mime="text/markdown",
width='stretch'
)
st.success("✅ Markdown报告生成成功！")
except Exception as e:
st.error(f"❌ Markdown生成失败: {str(e)}")
def generate_markdown_report(result_data: dict) -> str:
"""生成龙虎榜分析Markdown报告"""
# 获取当前时间
current_time = datetime.now().strftime("%Y年%m月%d日 %H:%M:%S")
# 标题页
markdown_content = f"""# 智瞰龙虎榜分析报告
**AI驱动的龙虎榜多维度分析系统**
---
## 📊 报告概览
- **生成时间**: {current_time}
- **数据记录**: {result_data.get('data_info', {}).get('total_records', 0)} 条
- **涉及股票**: {result_data.get('data_info', {}).get('total_stocks', 0)} 只
- **涉及游资**: {result_data.get('data_info', {}).get('total_youzi', 0)} 个
- **AI分析师**: 5位专业分析师团队
- **分析模型**: DeepSeek AI Multi-Agent System
> ⚠️ 本报告由AI系统基于龙虎榜公开数据自动生成，仅供参考，不构成投资建议。市场有风险，投资需谨慎。
---
## 📈 数据概况
本次分析共涵盖 **{result_data.get('data_info', {}).get('total_records', 0)}** 条龙虎榜记录，
涉及 **{result_data.get('data_info', {}).get('total_stocks', 0)}** 只股票和
**{result_data.get('data_info', {}).get('total_youzi', 0)}** 个游资席位。
"""
# 资金概况
summary = result_data.get('data_info', {}).get('summary', {})
markdown_content += f"""
### 💰 资金概况
- **总买入金额**: {summary.get('total_buy_amount', 0):,.2f} 元
- **总卖出金额**: {summary.get('total_sell_amount', 0):,.2f} 元
- **净流入金额**: {summary.get('total_net_inflow', 0):,.2f} 元
"""
# TOP游资
if summary.get('top_youzi'):
markdown_content += "### 🏆 活跃游资 TOP10\n\n| 排名 | 游资名称 | 净流入金额(元) |\n|------|----------|---------------|\n"
for idx, (name, amount) in enumerate(list(summary['top_youzi'].items())[:10], 1):
markdown_content += f"| {idx} | {name} | {amount:,.2f} |\n"
markdown_content += "\n"
# TOP股票
if summary.get('top_stocks'):
markdown_content += "### 📈 资金净流入 TOP20 股票\n\n| 排名 | 股票代码 | 股票名称 | 净流入金额(元) |\n|------|----------|----------|---------------|\n"
for idx, stock in enumerate(summary['top_stocks'][:20], 1):
markdown_content += f"| {idx} | {stock['code']} | {stock['name']} | {stock['net_inflow']:,.2f} |\n"
markdown_content += "\n"
# 热门概念
if summary.get('hot_concepts'):
markdown_content += "### 🔥 热门概念 TOP15\n\n"
for idx, (concept, count) in enumerate(list(summary['hot_concepts'].items())[:15], 1):
markdown_content += f"{idx}. {concept} ({count}次) \n"
markdown_content += "\n"
# 推荐股票
recommended = result_data.get('recommended_stocks', [])
if recommended:
markdown_content += f"""
## 🎯 AI推荐股票
基于5位AI分析师的综合分析，系统识别出以下 **{len(recommended)}** 只潜力股票，
这些股票在资金流向、游资关注度、题材热度等多个维度表现突出。
### 推荐股票清单
| 排名 | 股票代码 | 股票名称 | 净流入金额 | 确定性 | 持有周期 |
|------|----------|----------|------------|--------|----------|
"""
for stock in recommended[:10]:
markdown_content += f"| {stock.get('rank', '-')} | {stock.get('code', '-')} | {stock.get('name', '-')} | {stock.get('net_inflow', 0):,.0f} | {stock.get('confidence', '-')} | {stock.get('hold_period', '-')} |\n"
markdown_content += "\n### 推荐理由详解\n\n"
for stock in recommended[:5]: # 只详细展示前5只
markdown_content += f"**{stock.get('rank', '-')}. {stock.get('name', '-')} ({stock.get('code', '-')})**\n\n"
markdown_content += f"- 推荐理由: {stock.get('reason', '暂无')}\n"
markdown_content += f"- 确定性: {stock.get('confidence', '-')}\n"
markdown_content += f"- 持有周期: {stock.get('hold_period', '-')}\n\n"
# AI分析师报告
agents_analysis = result_data.get('agents_analysis', {})
if agents_analysis:
markdown_content += "## 🤖 AI分析师报告\n\n"
markdown_content += "本报告由5位AI专业分析师从不同维度进行分析，综合形成投资建议：\n\n"
markdown_content += "- **游资行为分析师** - 分析游资操作特征和意图\n"
markdown_content += "- **个股潜力分析师** - 挖掘次日大概率上涨的股票\n"
markdown_content += "- **题材追踪分析师** - 识别热点题材和轮动机会\n"
markdown_content += "- **风险控制专家** - 识别高风险股票和市场陷阱\n"
markdown_content += "- **首席策略师** - 综合研判并给出最终建议\n\n"
agent_titles = {
'youzi': '游资行为分析师',
'stock': '个股潜力分析师',
'theme': '题材追踪分析师',
'risk': '风险控制专家',
'chief': '首席策略师综合研判'
}
for agent_key, agent_title in agent_titles.items():
agent_data = agents_analysis.get(agent_key, {})
if agent_data:
markdown_content += f"### {agent_title}\n\n"
analysis_text = agent_data.get('analysis', '暂无分析')
# 处理文本中的换行
analysis_text = analysis_text.replace('\n', '\n\n')
markdown_content += f"{analysis_text}\n\n"
markdown_content += """
---
*报告由智瞰龙虎AI系统自动生成*
"""
return markdown_content
def display_history_tab():
main_force_ui.py
+176 -173
View File
@@ -13,17 +13,17 @@ import pandas as pd
def display_main_force_selector():
"""显示主力选股界面"""
# 检查是否触发批量分析（不立即删除标志）
if st.session_state.get('main_force_batch_trigger'):
run_main_force_batch_analysis()
return
# 检查是否查看历史记录
if st.session_state.get('main_force_view_history'):
display_batch_history()
return
# 页面标题和历史记录按钮
col_title, col_history = st.columns([4, 1])
with col_title:
@@ -33,9 +33,9 @@ def display_main_force_selector():
if st.button("📚 批量分析历史", width='content'):
st.session_state.main_force_view_history = True
st.rerun()
st.markdown("---")
st.markdown("""
### 功能说明
@@ -53,18 +53,18 @@ def display_main_force_selector():
- ✅ 行业前景明朗
- ✅ 综合素质优秀
""")
st.markdown("---")
# 参数设置
col1, col2, col3 = st.columns(3)
with col1:
date_option = st.selectbox(
"选择时间区间",
["最近3个月", "最近6个月", "最近1年", "自定义日期"]
)
if date_option == "最近3个月":
days_ago = 90
start_date = None
@@ -81,7 +81,7 @@ def display_main_force_selector():
)
start_date = f"{custom_date.year}年{custom_date.month}月{custom_date.day}日"
days_ago = None
with col2:
final_n = st.slider(
"最终精选数量",
@@ -91,14 +91,14 @@ def display_main_force_selector():
step=1,
help="最终推荐的股票数量"
)
with col3:
st.info("💡 系统将获取前100名股票，进行整体分析后精选优质标的")
# 高级选项
with st.expander("⚙️ 高级筛选参数"):
col1, col2, col3 = st.columns(3)
with col1:
max_change = st.number_input(
"最大涨跌幅(%)",
@@ -108,7 +108,7 @@ def display_main_force_selector():
step=5.0,
help="过滤掉涨幅过高的股票，避免追高"
)
with col2:
min_cap = st.number_input(
"最小市值(亿)",
@@ -117,7 +117,7 @@ def display_main_force_selector():
value=50.0,
step=10.0
)
with col3:
max_cap = st.number_input(
"最大市值(亿)",
@@ -126,24 +126,27 @@ def display_main_force_selector():
value=5000.0,
step=100.0
)
# 模型选择
# 导入model_config.py中定义的model_options
from model_config import model_options as app_model_options
model = st.selectbox(
"选择AI模型",
["deepseek-chat", "deepseek-reasoner"],
list(app_model_options.keys()),
format_func=lambda x: app_model_options[x],
help="deepseek-chat速度快，deepseek-reasoner推理能力强"
)
st.markdown("---")
# 开始分析按钮
if st.button("🚀 开始主力选股", type="primary", width='content'):
with st.spinner("正在获取数据并分析，这可能需要几分钟..."):
# 创建分析器
analyzer = MainForceAnalyzer(model=model)
# 运行分析
result = analyzer.run_full_analysis(
start_date=start_date,
@@ -153,83 +156,83 @@ def display_main_force_selector():
min_market_cap=min_cap,
max_market_cap=max_cap
)
# 保存结果到session_state
st.session_state.main_force_result = result
st.session_state.main_force_analyzer = analyzer
# 显示结果
if result['success']:
st.success(f"✅ 分析完成！共筛选出 {len(result['final_recommendations'])} 只优质标的")
st.rerun()
else:
st.error(f"❌ 分析失败: {result.get('error', '未知错误')}")
# 显示分析结果
if 'main_force_result' in st.session_state:
result = st.session_state.main_force_result
if result['success']:
display_analysis_results(result, st.session_state.get('main_force_analyzer'))
def display_analysis_results(result: dict, analyzer):
"""显示分析结果"""
st.markdown("---")
st.markdown("## 📊 分析结果")
# 统计信息
col1, col2, col3 = st.columns(3)
with col1:
st.metric("获取股票数", result['total_stocks'])
with col2:
st.metric("筛选后", result['filtered_stocks'])
with col3:
st.metric("最终推荐", len(result['final_recommendations']))
st.markdown("---")
# 显示AI分析师完整报告
if analyzer and hasattr(analyzer, 'fund_flow_analysis'):
display_analyst_reports(analyzer)
st.markdown("---")
# 显示推荐股票
if result['final_recommendations']:
st.markdown("### ⭐ 精选推荐")
for rec in result['final_recommendations']:
with st.expander(
f"【第{rec['rank']}名】{rec['symbol']} - {rec['name']}",
f"【第{rec['rank']}名】{rec['symbol']} - {rec['name']}",
expanded=(rec['rank'] <= 3)
):
display_recommendation_detail(rec)
# 显示候选股票列表
if analyzer and analyzer.raw_stocks is not None and not analyzer.raw_stocks.empty:
st.markdown("---")
st.markdown("### 📋 候选股票列表（筛选后）")
# 选择关键列显示
display_cols = ['股票代码', '股票简称']
# 添加行业列
industry_cols = [col for col in analyzer.raw_stocks.columns if '行业' in col]
if industry_cols:
display_cols.append(industry_cols[0])
# 添加区间主力资金净流入（智能匹配）
main_fund_col = None
main_fund_patterns = [
'区间主力资金流向', # 实际列名
'区间主力资金净流入',
'区间主力资金净流入',
'主力资金流向',
'主力资金净流入',
'主力净流入',
'主力资金净流入',
'主力净流入',
'主力资金'
]
for pattern in main_fund_patterns:
@@ -239,11 +242,11 @@ def display_analysis_results(result: dict, analyzer):
break
if main_fund_col:
display_cols.append(main_fund_col)
# 添加区间涨跌幅（前复权）（智能匹配）
interval_pct_col = None
interval_pct_patterns = [
'区间涨跌幅:前复权', '区间涨跌幅:前复权(%)', '区间涨跌幅(%)',
'区间涨跌幅:前复权', '区间涨跌幅:前复权(%)', '区间涨跌幅(%)',
'区间涨跌幅', '涨跌幅:前复权', '涨跌幅:前复权(%)', '涨跌幅(%)', '涨跌幅'
]
for pattern in interval_pct_patterns:
@@ -253,16 +256,16 @@ def display_analysis_results(result: dict, analyzer):
break
if interval_pct_col:
display_cols.append(interval_pct_col)
# 添加市值、市盈率、市净率
for col_name in ['总市值', '市盈率', '市净率']:
matching_cols = [col for col in analyzer.raw_stocks.columns if col_name in col]
if matching_cols:
display_cols.append(matching_cols[0])
# 选择存在的列
final_cols = [col for col in display_cols if col in analyzer.raw_stocks.columns]
# 调试信息：显示找到的列名
with st.expander("🔍 调试信息 - 查看数据列", expanded=False):
st.caption("所有可用列:")
@@ -277,14 +280,14 @@ def display_analysis_results(result: dict, analyzer):
st.success(f"✅ 找到涨跌幅列: {interval_pct_col}")
else:
st.warning("⚠️ 未找到涨跌幅列")
# 显示DataFrame
display_df = analyzer.raw_stocks[final_cols].copy()
st.dataframe(display_df, width='content', height=400)
# 显示统计
st.caption(f"共 {len(display_df)} 只候选股票，显示 {len(final_cols)} 个字段")
# 下载按钮
csv = display_df.to_csv(index=False, encoding='utf-8-sig')
st.download_button(
@@ -293,15 +296,15 @@ def display_analysis_results(result: dict, analyzer):
file_name=f"main_force_stocks_{datetime.now().strftime('%Y%m%d')}.csv",
mime="text/csv"
)
# 批量分析功能区
st.markdown("---")
col_batch1, col_batch2, col_batch3 = st.columns([2, 1, 1])
with col_batch1:
st.markdown("#### 🚀 批量深度分析")
st.caption("对主力资金净流入TOP股票进行完整的AI团队分析，获取投资评级和关键价位")
with col_batch2:
batch_count = st.selectbox(
"分析数量",
@@ -309,18 +312,18 @@ def display_analysis_results(result: dict, analyzer):
index=1, # 默认20只
help="选择分析主力资金净流入前N只股票"
)
with col_batch3:
st.write("") # 占位
if st.button("🚀 开始批量分析", type="primary", width='content'):
# 准备数据：按主力资金净流入排序
df_sorted = analyzer.raw_stocks.copy()
# 确保主力资金列是数值类型并排序
if main_fund_col:
df_sorted[main_fund_col] = pd.to_numeric(df_sorted[main_fund_col], errors='coerce')
df_sorted = df_sorted.sort_values(by=main_fund_col, ascending=False)
# 提取股票代码并去掉市场后缀（.SH, .SZ等）
raw_codes = df_sorted.head(batch_count)['股票代码'].tolist()
stock_codes = []
@@ -332,55 +335,55 @@ def display_analysis_results(result: dict, analyzer):
stock_codes.append(clean_code)
else:
stock_codes.append(str(code))
# 存储到session_state，触发批量分析
st.session_state.main_force_batch_codes = stock_codes
st.session_state.main_force_batch_trigger = True
st.rerun()
# 显示PDF报告下载区域
if analyzer and result:
display_report_download_section(analyzer, result)
def display_recommendation_detail(rec: dict):
"""显示单个推荐股票的详细信息"""
col1, col2 = st.columns([1, 1])
with col1:
st.markdown("#### 📌 推荐理由")
for reason in rec.get('reasons', []):
st.markdown(f"- {reason}")
st.markdown("#### 💡 投资亮点")
st.info(rec.get('highlights', 'N/A'))
with col2:
st.markdown("#### 📊 投资建议")
st.markdown(f"**建议仓位**: {rec.get('position', 'N/A')}")
st.markdown(f"**投资周期**: {rec.get('investment_period', 'N/A')}")
st.markdown("#### ⚠️ 风险提示")
st.warning(rec.get('risks', 'N/A'))
# 显示股票详细数据
if 'stock_data' in rec:
st.markdown("---")
st.markdown("#### 📊 股票详细数据")
stock_data = rec['stock_data']
# 创建数据展示
col1, col2, col3 = st.columns(3)
with col1:
st.metric("股票代码", stock_data.get('股票代码', 'N/A'))
# 显示行业
industry_keys = [k for k in stock_data.keys() if '行业' in k]
if industry_keys:
st.metric("所属行业", stock_data.get(industry_keys[0], 'N/A'))
with col2:
# 显示主力资金
fund_keys = [k for k in stock_data.keys() if '主力' in k and '净流入' in k]
@@ -390,7 +393,7 @@ def display_recommendation_detail(rec: dict):
st.metric("主力资金净流入", f"{fund_value/100000000:.2f}亿")
else:
st.metric("主力资金净流入", str(fund_value))
with col3:
# 显示涨跌幅
change_keys = [k for k in stock_data.keys() if '涨跌幅' in k]
@@ -400,23 +403,23 @@ def display_recommendation_detail(rec: dict):
st.metric("区间涨跌幅", f"{change_value:.2f}%")
else:
st.metric("区间涨跌幅", str(change_value))
# 显示其他关键指标
st.markdown("**其他关键指标：**")
metrics_col1, metrics_col2, metrics_col3 = st.columns(3)
with metrics_col1:
if '市盈率' in stock_data or any('市盈率' in k for k in stock_data.keys()):
pe_keys = [k for k in stock_data.keys() if '市盈率' in k]
if pe_keys:
st.caption(f"市盈率: {stock_data.get(pe_keys[0], 'N/A')}")
with metrics_col2:
if '市净率' in stock_data or any('市净率' in k for k in stock_data.keys()):
pb_keys = [k for k in stock_data.keys() if '市净率' in k]
if pb_keys:
st.caption(f"市净率: {stock_data.get(pb_keys[0], 'N/A')}")
with metrics_col3:
if '总市值' in stock_data or any('总市值' in k for k in stock_data.keys()):
cap_keys = [k for k in stock_data.keys() if '总市值' in k]
@@ -425,12 +428,12 @@ def display_recommendation_detail(rec: dict):
def display_analyst_reports(analyzer):
"""显示AI分析师完整报告"""
st.markdown("### 🤖 AI分析师团队完整报告")
# 创建三个标签页
tab1, tab2, tab3 = st.tabs(["💰 资金流向分析", "📊 行业板块分析", "📈 财务基本面分析"])
with tab1:
st.markdown("#### 💰 资金流向分析师报告")
st.markdown("---")
@@ -438,7 +441,7 @@ def display_analyst_reports(analyzer):
st.markdown(analyzer.fund_flow_analysis)
else:
st.info("暂无资金流向分析报告")
with tab2:
st.markdown("#### 📊 行业板块及市场热点分析师报告")
st.markdown("---")
@@ -446,7 +449,7 @@ def display_analyst_reports(analyzer):
st.markdown(analyzer.industry_analysis)
else:
st.info("暂无行业板块分析报告")
with tab3:
st.markdown("#### 📈 财务基本面分析师报告")
st.markdown("---")
@@ -459,10 +462,10 @@ def format_number(value, unit='', suffix=''):
"""格式化数字显示"""
if value is None or value == 'N/A':
return 'N/A'
try:
num = float(value)
# 如果单位是亿，需要转换
if unit == '亿':
if abs(num) >= 100000000: # 大于1亿（以元为单位）
@@ -471,7 +474,7 @@ def format_number(value, unit='', suffix=''):
pass
else: # 100-100000000之间，可能是万
num = num / 10000
# 格式化显示
if abs(num) >= 1000:
formatted = f"{num:,.2f}"
@@ -479,7 +482,7 @@ def format_number(value, unit='', suffix=''):
formatted = f"{num:.2f}"
else:
formatted = f"{num:.4f}"
return f"{formatted}{suffix}"
except (ValueError, TypeError):
return str(value)
@@ -489,14 +492,14 @@ def run_main_force_batch_analysis():
"""执行主力选股TOP股票批量分析（遵循统一调用规范）"""
import time
import re
st.markdown("## 🚀 主力选股TOP股票批量分析")
st.markdown("---")
# 检查是否已有分析结果
if st.session_state.get('main_force_batch_results'):
display_main_force_batch_results(st.session_state.main_force_batch_results)
# 返回按钮
col_back, col_clear = st.columns(2)
with col_back:
@@ -509,28 +512,28 @@ def run_main_force_batch_analysis():
if 'main_force_batch_results' in st.session_state:
del st.session_state.main_force_batch_results
st.rerun()
with col_clear:
if st.button("🔄 重新分析", width='content'):
# 清除结果，保留触发标志和代码
if 'main_force_batch_results' in st.session_state:
del st.session_state.main_force_batch_results
st.rerun()
return
# 获取股票代码列表
stock_codes = st.session_state.get('main_force_batch_codes', [])
if not stock_codes:
st.error("未找到股票代码列表")
# 清除触发标志
if 'main_force_batch_trigger' in st.session_state:
del st.session_state.main_force_batch_trigger
return
st.info(f"即将分析 {len(stock_codes)} 只股票：{', '.join(stock_codes[:10])}{'...' if len(stock_codes) > 10 else ''}")
# 返回按钮
if st.button("🔙 取消返回", type="secondary"):
# 清除所有批量分析相关状态
@@ -539,12 +542,12 @@ def run_main_force_batch_analysis():
if 'main_force_batch_codes' in st.session_state:
del st.session_state.main_force_batch_codes
st.rerun()
st.markdown("---")
# 分析选项
col1, col2 = st.columns(2)
with col1:
analysis_mode = st.selectbox(
"分析模式",
@@ -552,7 +555,7 @@ def run_main_force_batch_analysis():
format_func=lambda x: "顺序分析（稳定）" if x == "sequential" else "并行分析（快速）",
help="顺序分析较慢但稳定，并行分析更快但消耗更多资源"
)
with col2:
if analysis_mode == "parallel":
max_workers = st.number_input(
@@ -564,17 +567,17 @@ def run_main_force_batch_analysis():
)
else:
max_workers = 1
st.markdown("---")
# 开始分析按钮
col_confirm, col_cancel = st.columns(2)
start_analysis = False
with col_confirm:
if st.button("🚀 确认开始分析", type="primary", width='content'):
start_analysis = True
with col_cancel:
if st.button("❌ 取消", type="secondary", width='content'):
# 清除所有批量分析相关状态
@@ -583,16 +586,16 @@ def run_main_force_batch_analysis():
if 'main_force_batch_codes' in st.session_state:
del st.session_state.main_force_batch_codes
st.rerun()
if start_analysis:
# 导入统一分析函数（遵循统一规范）
from app import analyze_single_stock_for_batch
import concurrent.futures
import time
st.markdown("---")
st.info("⏳ 正在执行批量分析，请稍候...")
# 显示即将分析的股票代码（调试用）
with st.expander("🔍 调试信息", expanded=True):
st.write(f"**股票代码数量**: {len(stock_codes)} 只")
@@ -600,7 +603,7 @@ def run_main_force_batch_analysis():
st.write(f"**代码格式检查**: {'✅ 无后缀，格式正确' if all('.' not in str(c) for c in stock_codes) else '❌ 包含后缀，可能有问题'}")
st.write(f"**分析模式**: {analysis_mode}")
st.write(f"**线程数**: {max_workers if analysis_mode == 'parallel' else 1}")
# 配置分析师参数
enabled_analysts_config = {
'technical': True,
@@ -612,23 +615,23 @@ def run_main_force_batch_analysis():
}
selected_model = 'deepseek-chat'
period = '1y'
# 创建进度显示
progress_bar = st.progress(0)
status_text = st.empty()
# 存储结果
results = []
# 记录开始时间
start_time = time.time()
if analysis_mode == "sequential":
# 顺序分析
for i, code in enumerate(stock_codes):
status_text.text(f"正在分析 {code} ({i+1}/{len(stock_codes)})")
progress_bar.progress((i + 1) / len(stock_codes))
try:
# 调用统一分析函数
result = analyze_single_stock_for_batch(
@@ -637,23 +640,23 @@ def run_main_force_batch_analysis():
enabled_analysts_config=enabled_analysts_config,
selected_model=selected_model
)
results.append(result)
except Exception as e:
results.append({
"symbol": code,
"success": False,
"error": str(e)
})
else:
# 并行分析
status_text.text(f"并行分析 {len(stock_codes)} 只股票（{max_workers}线程）...")
print(f"\n{'='*60}")
print(f"🚀 开始并行分析 {len(stock_codes)} 只股票")
print(f"{'='*60}")
def analyze_one(code):
try:
print(f" 开始分析: {code}")
@@ -668,10 +671,10 @@ def run_main_force_batch_analysis():
except Exception as e:
print(f" 分析失败: {code} - {str(e)}")
return {"symbol": code, "success": False, "error": str(e)}
with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = {executor.submit(analyze_one, code): code for code in stock_codes}
completed = 0
for future in concurrent.futures.as_completed(futures):
code = futures[future] # 获取对应的股票代码
@@ -679,48 +682,48 @@ def run_main_force_batch_analysis():
progress = completed / len(stock_codes)
progress_bar.progress(progress)
status_text.text(f"已完成 {completed}/{len(stock_codes)} ({code})")
print(f" 进度更新: {completed}/{len(stock_codes)} ({progress*100:.1f}%) - {code}")
try:
result = future.result()
results.append(result)
except Exception as e:
print(f" 获取结果失败: {code} - {str(e)}")
results.append({"symbol": code, "success": False, "error": str(e)})
print(f"\n✅ 所有并行任务已完成")
print(f" 完成数: {completed}")
print(f" 结果数: {len(results)}")
print(f"{'='*60}\n")
# 清除进度
progress_bar.empty()
status_text.empty()
# 计算统计
elapsed_time = time.time() - start_time
success_count = sum(1 for r in results if r.get("success", False))
failed_count = len(results) - success_count
# 显示完成信息
if success_count > 0:
st.success(f"✅ 批量分析完成！成功 {success_count} 只，失败 {failed_count} 只，耗时 {elapsed_time/60:.1f} 分钟")
else:
st.error(f"❌ 批量分析完成，但所有 {failed_count} 只股票都分析失败！")
# 显示失败原因（调试用）
with st.expander("❌ 查看失败原因", expanded=True):
for r in results:
if not r.get("success", False):
st.error(f"**{r.get('symbol', 'N/A')}**: {r.get('error', '未知错误')}")
# 先保存到数据库历史记录（在 rerun 之前完成）
save_success = False
save_error = None
try:
from main_force_batch_db import batch_db
# 调试信息
print(f"\n{'='*60}")
print(f"📝 准备保存批量分析结果到历史记录")
@@ -731,17 +734,17 @@ def run_main_force_batch_analysis():
print(f"失败数: {failed_count}")
print(f"总耗时: {elapsed_time:.2f}秒")
print(f"结果数: {len(results)}")
# 检查结果数据类型
print(f"\n检查结果数据类型:")
for i, result in enumerate(results[:3]): # 只检查前3个
print(f" 结果 {i+1}:")
for key, value in list(result.items())[:5]: # 只检查前5个字段
print(f" - {key}: {type(value).__name__}")
print(f"\n开始保存到数据库...")
save_start = time.time()
# 保存到数据库
record_id = batch_db.save_batch_analysis(
batch_count=len(stock_codes),
@@ -751,14 +754,14 @@ def run_main_force_batch_analysis():
total_time=elapsed_time,
results=results
)
save_elapsed = time.time() - save_start
print(f"✅ 批量分析结果已保存到历史记录")
print(f" 记录ID: {record_id}")
print(f" 保存耗时: {save_elapsed:.2f}秒")
print(f"{'='*60}\n")
save_success = True
except Exception as e:
import traceback
save_error = str(e)
@@ -769,7 +772,7 @@ def run_main_force_batch_analysis():
print(f"详细错误:")
print(traceback.format_exc())
print(f"{'='*60}\n")
# 保存结果到session_state
st.session_state.main_force_batch_results = {
"results": results,
@@ -781,9 +784,9 @@ def run_main_force_batch_analysis():
"saved_to_history": save_success,
"save_error": save_error
}
time.sleep(0.5)
# 重新渲染以显示结果
st.rerun()
@@ -791,7 +794,7 @@ def run_main_force_batch_analysis():
def display_main_force_batch_results(batch_results):
"""显示主力选股批量分析结果"""
import re
results = batch_results['results']
total = batch_results['total']
success = batch_results['success']
@@ -799,46 +802,46 @@ def display_main_force_batch_results(batch_results):
elapsed_time = batch_results['elapsed_time']
saved_to_history = batch_results.get('saved_to_history', False)
save_error = batch_results.get('save_error')
st.markdown("## 📊 批量分析结果")
# 显示保存状态
if saved_to_history:
st.success("✅ 分析结果已自动保存到历史记录，可点击右上角'📚 批量分析历史'查看")
elif save_error:
st.warning(f"⚠️ 历史记录保存失败: {save_error}，但结果仍可查看")
st.markdown("---")
# 统计信息
col1, col2, col3, col4 = st.columns(4)
with col1:
st.metric("总计分析", f"{total} 只")
with col2:
st.metric("成功分析", f"{success} 只", delta=f"{success/total*100:.1f}%")
with col3:
st.metric("失败分析", f"{failed} 只")
with col4:
st.metric("总耗时", f"{elapsed_time/60:.1f} 分钟")
st.markdown("---")
# 成功分析的股票
successful_results = [r for r in results if r['success']]
if successful_results:
st.markdown(f"### ✅ 成功分析的股票 ({len(successful_results)}只)")
# 创建DataFrame展示
display_data = []
for result in successful_results:
stock_info = result.get('stock_info', {})
final_decision = result.get('final_decision', {})
# 提取评级emoji
rating = final_decision.get('rating', '未知')
rating_emoji = {
@@ -848,7 +851,7 @@ def display_main_force_batch_results(batch_results):
'卖出': '⚠️',
'强烈卖出': '🚫'
}.get(rating, '❓')
display_data.append({
'股票代码': stock_info.get('symbol', ''),
'股票名称': stock_info.get('name', ''),
@@ -859,9 +862,9 @@ def display_main_force_batch_results(batch_results):
'止损位': final_decision.get('stop_loss', 'N/A'),
'目标价': final_decision.get('target_price', 'N/A')
})
df_display = pd.DataFrame(display_data)
# 类型统一，避免Arrow序列化错误
numeric_cols = ['信心度', '止盈位', '止损位', '目标价']
for col in numeric_cols:
@@ -872,17 +875,17 @@ def display_main_force_batch_results(batch_results):
for col in text_cols:
if col in df_display.columns:
df_display[col] = df_display[col].astype(str)
st.dataframe(df_display, width='content', height=400)
# 详细分析结果（可展开）
st.markdown("---")
st.markdown("### 📋 详细分析报告")
for result in successful_results:
stock_info = result.get('stock_info', {})
final_decision = result.get('final_decision', {})
symbol = stock_info.get('symbol', '')
name = stock_info.get('name', '')
rating = final_decision.get('rating', '未知')
@@ -893,34 +896,34 @@ def display_main_force_batch_results(batch_results):
'卖出': '⚠️',
'强烈卖出': '🚫'
}.get(rating, '❓')
with st.expander(f"{rating_emoji} {symbol} - {name} | {rating}"):
# 关键信息
col1, col2, col3 = st.columns(3)
with col1:
st.metric("信心度", final_decision.get('confidence_level', 'N/A'))
with col2:
st.metric("进场区间", final_decision.get('entry_range', 'N/A'))
with col3:
st.metric("目标价", final_decision.get('target_price', 'N/A'))
# 止盈止损
col1, col2 = st.columns(2)
with col1:
st.metric("止盈位", final_decision.get('take_profit', 'N/A'))
with col2:
st.metric("止损位", final_decision.get('stop_loss', 'N/A'))
# 投资建议
st.markdown("#### 💡 投资建议")
advice = final_decision.get('operation_advice', final_decision.get('advice', '暂无建议'))
st.info(advice)
# 加入监测按钮
if st.button(f"➕ 加入监测列表", key=f"monitor_{symbol}"):
# 解析进场区间
@@ -933,7 +936,7 @@ def display_main_force_batch_results(batch_results):
entry_max = float(parts[1].strip())
except:
pass
# 解析止盈止损
take_profit_str = final_decision.get('take_profit', '')
take_profit = None
@@ -944,7 +947,7 @@ def display_main_force_batch_results(batch_results):
take_profit = float(numbers[0])
except:
pass
stop_loss_str = final_decision.get('stop_loss', '')
stop_loss = None
if stop_loss_str:
@@ -954,16 +957,16 @@ def display_main_force_batch_results(batch_results):
stop_loss = float(numbers[0])
except:
pass
# 调用监测管理器添加
from monitor_db import monitor_db
try:
# 准备进场区间数据
entry_range_dict = {}
if entry_min and entry_max:
entry_range_dict = {"min": entry_min, "max": entry_max}
# 添加到监测列表
monitor_db.add_monitored_stock(
symbol=symbol,
@@ -976,21 +979,21 @@ def display_main_force_batch_results(batch_results):
st.success(f"✅ {symbol} - {name} 已加入监测列表")
except Exception as e:
st.error(f"❌ 添加失败: {str(e)}")
# 失败的股票
failed_results = [r for r in results if not r['success']]
if failed_results:
st.markdown("---")
st.markdown(f"### ❌ 分析失败的股票 ({len(failed_results)}只)")
failed_data = []
for result in failed_results:
failed_data.append({
'股票代码': result.get('symbol', ''),
'失败原因': result.get('error', '未知错误')
})
df_failed = pd.DataFrame(failed_data)
st.dataframe(df_failed, width='content')
model_config.py
+24
View File
@@ -0,0 +1,24 @@
"""
模型配置文件
包含所有可用的AI模型选项
"""
model_options = {
"deepseek-chat": "DeepSeek Chat (默认)",
"deepseek-reasoner": "DeepSeek Reasoner (推理增强)",
"qwen-plus": "qwen-plus (阿里百炼)",
"qwen-plus-latest": "qwen-plus-latest (阿里百炼)",
"qwen-flash": "qwen-flash (阿里百炼)",
"qwen-turbo": "qwen-turbo (阿里百炼)",
"qwen3-max": "qwen-max (阿里百炼)",
"qwen-long": "qwen-long (阿里百炼)",
"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B": "DeepSeek-R1 免费(硅基流动)",
"Qwen/Qwen2.5-7B-Instruct": "Qwen 免费(硅基流动)",
"Pro/deepseek-ai/DeepSeek-V3.1-Terminus": "DeepSeek-V3.1-Terminus (硅基流动)",
"deepseek-ai/DeepSeek-R1": "DeepSeek-R1 (硅基流动)",
"Qwen/Qwen3-235B-A22B-Thinking-2507": "Qwen3-235B (硅基流动)",
"zai-org/GLM-4.6": "智谱(硅基流动)",
"moonshotai/Kimi-K2-Instruct-0905": "Kimi (硅基流动)",
"Ring-1T": "蚂蚁百灵 (硅基流动)",
"step3": "阶跃星辰(硅基流动)"
}
pdf_generator.py
+160 -2
View File
@@ -259,6 +259,128 @@ def create_download_link(pdf_content, filename):
href = f'<a href="data:application/pdf;base64,{b64}" download="{filename}" style="display: inline-block; padding: 15px 30px; background-color: #e74c3c; color: white; text-decoration: none; border-radius: 8px; font-weight: bold; font-size: 16px; margin: 10px;">📄 下载PDF报告</a>'
return href
def generate_markdown_report(stock_info, agents_results, discussion_result, final_decision):
"""生成Markdown格式的分析报告"""
# 获取当前时间
current_time = datetime.now().strftime("%Y年%m月%d日 %H:%M:%S")
markdown_content = f"""
# AI股票分析报告
**生成时间**: {current_time}
---
## 📊 股票基本信息
| 项目 | 值 |
|------|-----|
| **股票代码** | {stock_info.get('symbol', 'N/A')} |
| **股票名称** | {stock_info.get('name', 'N/A')} |
| **当前价格** | {stock_info.get('current_price', 'N/A')} |
| **涨跌幅** | {stock_info.get('change_percent', 'N/A')}% |
| **市盈率(PE)** | {stock_info.get('pe_ratio', 'N/A')} |
| **市净率(PB)** | {stock_info.get('pb_ratio', 'N/A')} |
| **市值** | {stock_info.get('market_cap', 'N/A')} |
| **市场** | {stock_info.get('market', 'N/A')} |
| **交易所** | {stock_info.get('exchange', 'N/A')} |
---
## 🔍 各分析师详细分析
"""
# 添加各分析师的分析结果
agent_names = {
'technical': '📈 技术分析师',
'fundamental': '📊 基本面分析师',
'fund_flow': '💰 资金面分析师',
'risk_management': '⚠️ 风险管理师',
'market_sentiment': '📈 市场情绪分析师'
}
for agent_key, agent_name in agent_names.items():
if agent_key in agents_results:
agent_result = agents_results[agent_key]
if isinstance(agent_result, dict):
analysis_text = agent_result.get('analysis', '暂无分析')
else:
analysis_text = str(agent_result)
markdown_content += f"""
### {agent_name}
{analysis_text}
---
"""
# 添加团队讨论结果
markdown_content += f"""
## 🤝 团队综合讨论
{discussion_result}
---
## 📋 最终投资决策
"""
# 处理最终决策的显示
if isinstance(final_decision, dict) and "decision_text" not in final_decision:
# JSON格式的决策
markdown_content += f"""
**投资评级**: {final_decision.get('rating', '未知')}
**目标价位**: {final_decision.get('target_price', 'N/A')}
**操作建议**: {final_decision.get('operation_advice', '暂无建议')}
**进场区间**: {final_decision.get('entry_range', 'N/A')}
**止盈位**: {final_decision.get('take_profit', 'N/A')}
**止损位**: {final_decision.get('stop_loss', 'N/A')}
**持有周期**: {final_decision.get('holding_period', 'N/A')}
**仓位建议**: {final_decision.get('position_size', 'N/A')}
**信心度**: {final_decision.get('confidence_level', 'N/A')}/10
**风险提示**: {final_decision.get('risk_warning', '无')}
"""
else:
# 文本格式的决策
decision_text = final_decision.get('decision_text', str(final_decision))
markdown_content += decision_text
markdown_content += """
---
## 📝 免责声明
本报告由AI系统生成，仅供参考，不构成投资建议。投资有风险，入市需谨慎。请在做出投资决策前咨询专业的投资顾问。
---
*报告生成时间: {current_time}*
*AI股票分析系统 v1.0*
"""
return markdown_content
def create_markdown_download_link(markdown_content, filename):
"""创建Markdown下载链接"""
b64 = base64.b64encode(markdown_content.encode()).decode()
href = f'<a href="data:text/markdown;base64,{b64}" download="{filename}" style="display: inline-block; padding: 15px 30px; background-color: #9b59b6; color: white; text-decoration: none; border-radius: 8px; font-weight: bold; font-size: 16px; margin: 10px;">📝 下载Markdown报告</a>'
return href
def display_pdf_export_section(stock_info, agents_results, discussion_result, final_decision):
"""显示PDF导出区域"""
@@ -269,8 +391,11 @@ def display_pdf_export_section(stock_info, agents_results, discussion_result, fi
with col2:
# 生成PDF报告按钮（使用股票代码作为key的一部分，确保唯一性）
button_key = f"pdf_btn_{stock_info.get('symbol', 'unknown')}"
if st.button("📄 生成并下载PDF报告", type="primary", width='content', key=button_key):
pdf_button_key = f"pdf_btn_{stock_info.get('symbol', 'unknown')}"
markdown_button_key = f"markdown_btn_{stock_info.get('symbol', 'unknown')}"
# 生成PDF报告按钮
if st.button("📄 生成并下载PDF报告", type="primary", width='content', key=pdf_button_key):
with st.spinner("正在生成PDF报告..."):
try:
# 生成PDF内容
@@ -300,3 +425,36 @@ def display_pdf_export_section(stock_info, agents_results, discussion_result, fi
st.error(f"❌ 生成PDF报告时出错: {str(e)}")
import traceback
st.error(f"详细错误信息: {traceback.format_exc()}")
# 生成Markdown报告按钮
if st.button("📝 生成并下载Markdown报告", type="secondary", width='content', key=markdown_button_key):
with st.spinner("正在生成Markdown报告..."):
try:
# 生成Markdown内容
markdown_content = generate_markdown_report(stock_info, agents_results, discussion_result, final_decision)
# 生成文件名
stock_symbol = stock_info.get('symbol', 'unknown')
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"股票分析报告_{stock_symbol}_{timestamp}.md"
st.success("✅ Markdown报告生成成功！")
st.balloons()
# 显示下载链接
st.markdown("### 📄 报告下载")
download_link = create_markdown_download_link(markdown_content, filename)
st.markdown(f"""
<div style="text-align: center; margin: 20px 0;">
{download_link}
</div>
""", unsafe_allow_html=True)
st.info("💡 提示：点击上方按钮即可下载Markdown格式的完整分析报告")
except Exception as e:
st.error(f"❌ 生成Markdown报告时出错: {str(e)}")
import traceback
st.error(f"详细错误信息: {traceback.format_exc()}")
pdf_generator_fixed.py
+46 -148
View File
@@ -133,151 +133,6 @@ def create_html_download_link(content, filename, link_text):
href = f'<a href="data:text/html;base64,{b64}" download="{filename}" style="display: inline-block; padding: 10px 20px; background-color: #2196F3; color: white; text-decoration: none; border-radius: 5px; margin: 5px;">{link_text}</a>'
return href
def generate_html_content(markdown_content):
"""将Markdown转换为HTML"""
html_content = f"""
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>AI股票分析报告</title>
<style>
body {{
font-family: 'Microsoft YaHei', Arial, sans-serif;
line-height: 1.6;
max-width: 800px;
margin: 0 auto;
padding: 20px;
background-color: #f5f5f5;
}}
.container {{
background-color: white;
padding: 30px;
border-radius: 10px;
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
}}
h1 {{
color: #2c3e50;
border-bottom: 3px solid #3498db;
padding-bottom: 10px;
}}
h2 {{
color: #34495e;
border-left: 4px solid #3498db;
padding-left: 15px;
margin-top: 30px;
}}
h3 {{
color: #2980b9;
margin-top: 25px;
}}
table {{
width: 100%;
border-collapse: collapse;
margin: 20px 0;
}}
th, td {{
border: 1px solid #ddd;
padding: 12px;
text-align: left;
}}
th {{
background-color: #3498db;
color: white;
}}
tr:nth-child(even) {{
background-color: #f9f9f9;
}}
.disclaimer {{
background-color: #fff3cd;
border: 1px solid #ffeaa7;
border-radius: 5px;
padding: 15px;
margin-top: 30px;
}}
.footer {{
text-align: center;
margin-top: 30px;
color: #7f8c8d;
font-style: italic;
}}
hr {{
border: none;
height: 2px;
background-color: #ecf0f1;
margin: 20px 0;
}}
strong {{
color: #2c3e50;
}}
</style>
</head>
<body>
<div class="container">
"""
# 简单的Markdown到HTML转换
html_body = markdown_content
html_body = html_body.replace('\n# ', '\n<h1>').replace('\n## ', '\n<h2>').replace('\n### ', '\n<h3>')
html_body = html_body.replace('# ', '<h1>').replace('## ', '<h2>').replace('### ', '<h3>')
html_body = html_body.replace('\n---\n', '\n<hr>\n')
# 处理粗体文本
html_body = re.sub(r'\*\*(.*?)\*\*', r'<strong>\1</strong>', html_body)
# 处理表格
lines = html_body.split('\n')
in_table = False
processed_lines = []
for line in lines:
if '|' in line and not in_table and line.strip().startswith('|'):
processed_lines.append('<table>')
in_table = True
cells = [cell.strip() for cell in line.split('|')[1:-1]]
processed_lines.append('<tr>')
for cell in cells:
processed_lines.append(f'<th>{cell}</th>')
processed_lines.append('</tr>')
elif '|' in line and in_table:
if '---' not in line:
cells = [cell.strip() for cell in line.split('|')[1:-1]]
processed_lines.append('<tr>')
for cell in cells:
processed_lines.append(f'<td>{cell}</td>')
processed_lines.append('</tr>')
elif in_table and '|' not in line:
processed_lines.append('</table>')
processed_lines.append(line)
in_table = False
else:
processed_lines.append(line)
if in_table:
processed_lines.append('</table>')
html_body = '\n'.join(processed_lines)
# 处理段落
paragraphs = html_body.split('\n\n')
processed_paragraphs = []
for para in paragraphs:
para = para.strip()
if para and not para.startswith('<') and not para.startswith('---'):
processed_paragraphs.append(f'<p>{para}</p>')
else:
processed_paragraphs.append(para)
html_body = '\n'.join(processed_paragraphs)
html_content += html_body + """
</div>
</body>
</html>
"""
return html_content
def display_pdf_export_section(stock_info, agents_results, discussion_result, final_decision):
"""显示PDF导出区域 - 修复报告生成问题"""
@@ -290,8 +145,11 @@ def display_pdf_export_section(stock_info, agents_results, discussion_result, fi
# 生成报告按钮
import uuid
import time
button_key = f"generate_report_btn_{int(time.time())}_{uuid.uuid4().hex[:8]}"
if st.button("📊 生成并下载报告", type="primary", width='content', key=button_key):
pdf_button_key = f"generate_report_btn_{int(time.time())}_{uuid.uuid4().hex[:8]}"
markdown_button_key = f"generate_markdown_btn_{int(time.time())}_{uuid.uuid4().hex[:8]}"
# 生成PDF和HTML报告按钮
if st.button("📊 生成并下载报告(PDF/HTML)", type="primary", width='content', key=pdf_button_key):
with st.spinner("正在生成报告..."):
try:
# 生成Markdown内容
@@ -337,4 +195,44 @@ def display_pdf_export_section(stock_info, agents_results, discussion_result, fi
except Exception as e:
st.error(f"❌ 生成报告时出错: {str(e)}")
import traceback
st.error(f"详细错误信息: {traceback.format_exc()}")
st.error(f"详细错误信息: {traceback.format_exc()}")
# 单独生成Markdown报告按钮
if st.button("📝 生成并下载Markdown报告", type="secondary", width='content', key=markdown_button_key):
with st.spinner("正在生成Markdown报告..."):
try:
# 生成Markdown内容
markdown_content = generate_markdown_report(stock_info, agents_results, discussion_result, final_decision)
# 生成文件名
stock_symbol = stock_info.get('symbol', 'unknown')
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"股票分析报告_{stock_symbol}_{timestamp}.md"
st.success("✅ Markdown报告生成成功！")
st.balloons()
# 显示下载链接
st.markdown("### 📄 报告下载")
# 创建下载链接
md_link = create_download_link(
markdown_content,
filename,
"📝 下载Markdown报告"
)
# 显示下载链接
st.markdown(f"""
<div style="text-align: center; margin: 20px 0;">
{md_link}
</div>
""", unsafe_allow_html=True)
st.info("💡 提示：点击上方按钮即可下载Markdown格式的报告文件")
except Exception as e:
st.error(f"❌ 生成Markdown报告时出错: {str(e)}")
import traceback
st.error(f"详细错误信息: {traceback.format_exc()}")
pdf_generator_pandoc.py
+36 -1
View File
@@ -267,12 +267,47 @@ def display_pdf_export_section(stock_info, agents_results, discussion_result, fi
col1, col2, col3 = st.columns([1, 2, 1])
with col2:
if st.button("📊 生成并下载报告", type="primary", width='content', key="generate_report_btn"):
pdf_button_key = "generate_report_btn"
markdown_button_key = "generate_markdown_btn"
# 生成PDF报告按钮
if st.button("📊 生成并下载报告(PDF/HTML)", type="primary", width='content', key=pdf_button_key):
st.session_state.show_download_links = True
with st.spinner("正在生成报告..."):
success = generate_pdf_report(stock_info, agents_results, discussion_result, final_decision)
if success:
st.balloons()
# 生成Markdown报告按钮
if st.button("📝 生成并下载Markdown报告", type="secondary", width='content', key=markdown_button_key):
with st.spinner("正在生成Markdown报告..."):
try:
# 生成Markdown内容
markdown_content = generate_markdown_report(stock_info, agents_results, discussion_result, final_decision)
# 生成文件名
stock_symbol = stock_info.get('symbol', 'unknown')
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"股票分析报告_{stock_symbol}_{timestamp}.md"
st.success("✅ Markdown报告生成成功！")
st.balloons()
# 显示下载链接
st.markdown("### 📄 报告下载")
# Markdown下载链接
md_download_link = create_download_link(
markdown_content,
filename,
"📝 下载Markdown报告"
)
st.markdown(md_download_link, unsafe_allow_html=True)
st.info("💡 提示：点击上方按钮即可下载Markdown格式的报告文件")
except Exception as e:
st.error(f"❌ 生成Markdown报告时出错: {str(e)}")
# 如果已经生成了报告，显示下载链接
if st.session_state.show_download_links:
sector_strategy_ui.py
+215 -4
View File
@@ -116,9 +116,12 @@ def display_analysis_tab():
col1, col2, col3 = st.columns([2, 2, 2])
with col1:
# 导入model_config.py中定义的model_options
from model_config import model_options as app_model_options
selected_model = st.selectbox(
"选择AI模型",
["deepseek-chat", "deepseek-reasoner"],
"AI模型",
list(app_model_options.keys()),
format_func=lambda x: app_model_options[x],
help="Reasoner模型提供更强的推理能力"
)
@@ -774,10 +777,10 @@ def display_pdf_export_section(result):
"""显示PDF导出部分"""
st.subheader("📄 导出报告")
col1, col2, col3 = st.columns([2, 1, 1])
col1, col2, col3, col4 = st.columns([2, 1, 1, 1])
with col1:
st.write("将分析报告导出为PDF文件，方便保存和分享")
st.write("将分析报告导出为PDF或Markdown文件，方便保存和分享")
with col2:
if st.button("📥 生成PDF报告", type="primary", width='content'):
@@ -802,6 +805,23 @@ def display_pdf_export_section(result):
st.error(f"❌ PDF生成失败: {str(e)}")
with col3:
if st.button("📝 生成Markdown", type="secondary", width='content'):
with st.spinner("正在生成Markdown报告..."):
try:
# 生成Markdown内容
markdown_content = generate_sector_markdown_report(result)
# 保存到session_state
st.session_state.sector_markdown_data = markdown_content
st.session_state.sector_markdown_filename = f"智策报告_{result.get('timestamp', datetime.now().strftime('%Y%m%d_%H%M%S')).replace(':', '').replace(' ', '_')}.md"
st.success("✅ Markdown报告生成成功！")
st.rerun()
except Exception as e:
st.error(f"❌ Markdown生成失败: {str(e)}")
with col4:
# 如果已经生成了PDF，显示下载按钮
if 'sector_pdf_data' in st.session_state:
st.download_button(
@@ -811,6 +831,197 @@ def display_pdf_export_section(result):
mime="application/pdf",
width='content'
)
# 如果已经生成了Markdown，显示下载按钮
if 'sector_markdown_data' in st.session_state:
st.download_button(
label="💾 下载Markdown",
data=st.session_state.sector_markdown_data,
file_name=st.session_state.sector_markdown_filename,
mime="text/markdown",
width='content'
)
def generate_sector_markdown_report(result_data: dict) -> str:
"""生成智策分析Markdown报告"""
# 获取当前时间
current_time = datetime.now().strftime("%Y年%m月%d日 %H:%M:%S")
# 标题页
markdown_content = f"""# 智策板块策略分析报告
**AI驱动的多维度板块投资决策支持系统**
---
## 📊 报告信息
- **生成时间**: {current_time}
- **分析周期**: 当日市场数据
- **AI模型**: DeepSeek Multi-Agent System
- **分析维度**: 宏观·板块·资金·情绪
> ⚠️ 本报告由AI系统自动生成，仅供参考，不构成投资建议。投资有风险，决策需谨慎。
---
## 📈 市场概况
本报告基于{result_data.get('timestamp', 'N/A')}的实时市场数据，
通过四位AI智能体的多维度分析，为您提供板块投资策略建议。
### 分析师团队:
- **宏观策略师** - 分析宏观经济、政策导向、新闻事件
- **板块诊断师** - 分析板块走势、估值水平、轮动特征
- **资金流向分析师** - 分析主力资金、北向资金流向
- **市场情绪解码员** - 分析市场情绪、热度、赚钱效应
"""
# 核心预测
predictions = result_data.get('final_predictions', {})
if predictions.get('prediction_text'):
# 文本格式预测
markdown_content += f"""
## 🎯 核心预测
{predictions.get('prediction_text', '')}
"""
else:
# JSON格式预测
markdown_content += "## 🎯 核心预测\n\n"
# 1. 板块多空预测
long_short = predictions.get('long_short', {})
bullish = long_short.get('bullish', [])
bearish = long_short.get('bearish', [])
markdown_content += "### 📊 板块多空预测\n\n"
if bullish:
markdown_content += "#### 🟢 看多板块\n\n"
for idx, item in enumerate(bullish, 1):
markdown_content += f"{idx}. **{item.get('sector', 'N/A')}** (信心度: {item.get('confidence', 0)}/10)\n"
markdown_content += f" - 理由: {item.get('reason', 'N/A')}\n"
markdown_content += f" - 风险: {item.get('risk', 'N/A')}\n\n"
if bearish:
markdown_content += "#### 🔴 看空板块\n\n"
for idx, item in enumerate(bearish, 1):
markdown_content += f"{idx}. **{item.get('sector', 'N/A')}** (信心度: {item.get('confidence', 0)}/10)\n"
markdown_content += f" - 理由: {item.get('reason', 'N/A')}\n"
markdown_content += f" - 风险: {item.get('risk', 'N/A')}\n\n"
# 2. 板块轮动预测
rotation = predictions.get('rotation', {})
current_strong = rotation.get('current_strong', [])
potential = rotation.get('potential', [])
declining = rotation.get('declining', [])
markdown_content += "### 🔄 板块轮动预测\n\n"
if current_strong:
markdown_content += "#### 💪 当前强势板块\n\n"
for item in current_strong:
markdown_content += f"- **{item.get('sector', 'N/A')}**\n"
markdown_content += f" - 轮动逻辑: {item.get('logic', 'N/A')}\n"
markdown_content += f" - 时间窗口: {item.get('time_window', 'N/A')}\n"
markdown_content += f" - 操作建议: {item.get('advice', 'N/A')}\n\n"
if potential:
markdown_content += "#### 🌱 潜力接力板块\n\n"
for item in potential:
markdown_content += f"- **{item.get('sector', 'N/A')}**\n"
markdown_content += f" - 轮动逻辑: {item.get('logic', 'N/A')}\n"
markdown_content += f" - 时间窗口: {item.get('time_window', 'N/A')}\n"
markdown_content += f" - 操作建议: {item.get('advice', 'N/A')}\n\n"
if declining:
markdown_content += "#### 📉 衰退板块\n\n"
for item in declining:
markdown_content += f"- **{item.get('sector', 'N/A')}**\n"
markdown_content += f" - 轮动逻辑: {item.get('logic', 'N/A')}\n"
markdown_content += f" - 时间窗口: {item.get('time_window', 'N/A')}\n"
markdown_content += f" - 操作建议: {item.get('advice', 'N/A')}\n\n"
# 3. 板块热度排行
heat = predictions.get('heat', {})
hottest = heat.get('hottest', [])
heating = heat.get('heating', [])
cooling = heat.get('cooling', [])
markdown_content += "### 🔥 板块热度排行\n\n"
if hottest:
markdown_content += "#### 最热板块\n\n| 排名 | 板块 | 热度评分 | 趋势 | 持续性 |\n|------|------|----------|------|--------|\n"
for idx, item in enumerate(hottest[:10], 1):
markdown_content += f"| {idx} | {item.get('sector', 'N/A')} | {item.get('score', 0)} | {item.get('trend', 'N/A')} | {item.get('sustainability', 'N/A')} |\n"
markdown_content += "\n"
if heating:
markdown_content += "#### 升温板块\n\n"
for idx, item in enumerate(heating[:5], 1):
markdown_content += f"{idx}. {item.get('sector', 'N/A')} (评分: {item.get('score', 0)})\n"
markdown_content += "\n"
if cooling:
markdown_content += "#### 降温板块\n\n"
for idx, item in enumerate(cooling[:5], 1):
markdown_content += f"{idx}. {item.get('sector', 'N/A')} (评分: {item.get('score', 0)})\n"
markdown_content += "\n"
# 4. 策略总结
summary = predictions.get('summary', {})
if summary:
markdown_content += "### 📝 策略总结\n\n"
if summary.get('market_view'):
markdown_content += f"**市场观点:** {summary.get('market_view', '')}\n\n"
if summary.get('key_opportunity'):
markdown_content += f"**核心机会:** {summary.get('key_opportunity', '')}\n\n"
if summary.get('major_risk'):
markdown_content += f"**主要风险:** {summary.get('major_risk', '')}\n\n"
if summary.get('strategy'):
markdown_content += f"**整体策略:** {summary.get('strategy', '')}\n\n"
# AI智能体分析
agents_analysis = result_data.get('agents_analysis', {})
if agents_analysis:
markdown_content += "## 🤖 AI智能体分析\n\n"
for key, agent_data in agents_analysis.items():
agent_name = agent_data.get('agent_name', '未知分析师')
agent_role = agent_data.get('agent_role', '')
focus_areas = ', '.join(agent_data.get('focus_areas', []))
analysis = agent_data.get('analysis', '')
markdown_content += f"### {agent_name}\n\n"
markdown_content += f"- **职责**: {agent_role}\n"
markdown_content += f"- **关注领域**: {focus_areas}\n\n"
markdown_content += f"{analysis}\n\n"
markdown_content += "---\n\n"
# 综合研判
comprehensive_report = result_data.get('comprehensive_report', '')
if comprehensive_report:
markdown_content += "## 📊 综合研判\n\n"
markdown_content += f"{comprehensive_report}\n\n"
markdown_content += """
---
*报告由智策AI系统自动生成*
"""
return markdown_content
def display_scheduler_settings():