feat: 钉钉群聊飞书文档收集与知识图谱系统初始提交

- 通过悟空(dws CLI)拉取dc战略问题研究院+创新组两个群的消息(377条) - 提取190个飞书链接、18个文件附件 - 下载HTML/MD/XLSX等报告文件到output/downloaded-files/ - 构建知识图谱(JSON+HTML可视化) - 生成Obsidian知识库(28个页面,7大主题) - 生成花园世界全量汇总报告 - 所有脚本路径改为相对路径,便于迁移
2026-06-02 20:24:25 +08:00
commit fe5505343e
77 changed files with 20155 additions and 0 deletions
@@ -0,0 +1,115 @@
+#!/usr/bin/env python3
+"""读取所有飞书链接并生成汇总报告"""
+
+import json
+import requests
+from bs4 import BeautifulSoup
+import time
+from datetime import datetime
+
+def extract_content(url):
+    """从飞书链接提取内容"""
+    try:
+        resp = requests.get(url, timeout=10, headers={'User-Agent': 'Mozilla/5.0'})
+        soup = BeautifulSoup(resp.text, 'html.parser')
+        
+        # 获取标题
+        title = soup.find('title')
+        title_text = title.text.strip() if title else ''
+        
+        # 移除脚本和样式
+        for script in soup(['script', 'style']):
+            script.decompose()
+        
+        # 获取文本内容
+        text = soup.get_text(strip=True)
+        
+        # 提取关键信息
+        # 查找日报内容（通常在特定区域）
+        content_start = text.find('日报')
+        if content_start == -1:
+            content_start = text.find('工作')
+        if content_start == -1:
+            content_start = 0
+        
+        content = text[content_start:content_start + 800]
+        
+        return {
+            'title': title_text,
+            'content': content,
+            'success': True
+        }
+    except Exception as e:
+        return {
+            'title': '',
+            'content': str(e),
+            'success': False
+        }
+
+def main():
+    # 读取链接
+    with open('D:/desktop/feishu_docs_summary/all_feishu_links.json', 'r', encoding='utf-8') as f:
+        data = json.load(f)
+    
+    links = data.get('links', [])
+    print(f'共 {len(links)} 个链接')
+    
+    # 按组分类
+    groups = {}
+    for link in links:
+        group = link['group']
+        if group not in groups:
+            groups[group] = []
+        groups[group].append(link)
+    
+    # 读取每个组的文档
+    all_docs = []
+    for group_name, group_links in groups.items():
+        print(f'\n=== {group_name} ({len(group_links)} 个链接) ===')
+        
+        for i, link in enumerate(group_links[:5], 1):  # 每个组读取前5个
+            print(f'  [{i}/5] {link["sender"]} - {link["url"][:50]}...')
+            result = extract_content(link['url'])
+            result['sender'] = link['sender']
+            result['time'] = link['time']
+            result['group'] = group_name
+            result['url'] = link['url']
+            all_docs.append(result)
+            time.sleep(0.3)
+    
+    # 保存结果
+    output = {
+        'date': datetime.now().strftime('%Y-%m-%d'),
+        'total_links': len(links),
+        'docs_read': len(all_docs),
+        'documents': all_docs
+    }
+    
+    with open('D:/desktop/feishu_docs_summary/feishu_docs_content.json', 'w', encoding='utf-8') as f:
+        json.dump(output, f, ensure_ascii=False, indent=2)
+    
+    # 生成 Markdown 报告
+    report = f'# 飞书文档汇总报告\n\n'
+    report += f'**日期**: {datetime.now().strftime("%Y-%m-%d")}\n'
+    report += f'**链接总数**: {len(links)}\n'
+    report += f'**已读取**: {len(all_docs)}\n\n'
+    
+    for group_name in groups.keys():
+        group_docs = [d for d in all_docs if d['group'] == group_name]
+        if group_docs:
+            report += f'## {group_name}\n\n'
+            for doc in group_docs:
+                report += f'### {doc["sender"]} ({doc["time"]})\n'
+                report += f'**链接**: {doc["url"]}\n\n'
+                report += f'{doc["content"][:300]}\n\n'
+                report += '---\n\n'
+    
+    with open('D:/desktop/feishu_docs_summary/feishu_summary_report.md', 'w', encoding='utf-8') as f:
+        f.write(report)
+    
+    print(f'\n已保存到:')
+    print(f'  - feishu_docs_content.json')
+    print(f'  - feishu_summary_report.md')
+
+if __name__ == '__main__':
+    main()