Initial commit: 微信联系人祝福管理系统

batch_ocr_full.py

@@ -0,0 +1,144 @@
+# -*- coding: utf-8 -*-
+"""
+对完整截图进行OCR识别
+"""
+import os
+import requests
+import base64
+from PIL import Image
+import glob
+import json
+
+
+def ocr_image(image_path):
+    """OCR识别单张图片"""
+    with open(image_path, 'rb') as f:
+        image_base64 = base64.b64encode(f.read()).decode('utf-8')
+    
+    url = "http://localhost:11434/api/chat"
+    payload = {
+        "model": "glm-ocr",
+        "messages": [{
+            "role": "user",
+            "content": """识别图片中的所有联系人名称。要求：
+1. 只输出联系人名称，每行一个
+2. 忽略分组标题（如星号、字母A-Z等）
+3. 忽略数字统计
+4. 不要添加任何其他内容""",
+            "images": [image_base64]
+        }],
+        "stream": False
+    }
+    
+    try:
+        response = requests.post(url, json=payload, timeout=60)
+        return response.json().get('message', {}).get('content', '')
+    except Exception as e:
+        print(f"OCR失败: {e}")
+        return ""
+
+
+def is_valid_contact(line):
+    """判断是否是有效的联系人"""
+    line = line.strip()
+    if not line or len(line) < 2:
+        return False
+    
+    invalid = ["公众号", "服务号", "企业微信联系人", "我的企业", "联系人",
+               "星标朋友", "新的朋友", "群聊", "标签", "仅聊天", "设备"]
+    
+    if line in invalid:
+        return False
+    if len(line) == 1 and line.isalpha():
+        return False
+    if line.startswith(">") or line.startswith("!"):
+        return False
+    if line.startswith('"') or line.startswith('{') or line.startswith('[') or line.startswith('```'):
+        return False
+    if line.startswith('"') and ':' in line:
+        return False
+    
+    return True
+
+
+def clean_contact_name(name):
+    """清理联系人名称"""
+    name = name.strip('"\'')
+    name = name.rstrip(',，。：:')
+    return name.strip()
+
+
+def main():
+    print("=" * 60)
+    print("批量OCR识别完整截图")
+    print("=" * 60)
+    
+    # 获取截图目录
+    scroll_dir = r"D:\夏骥\微信研究\scroll_full"
+    
+    if not os.path.exists(scroll_dir):
+        print(f"目录不存在: {scroll_dir}")
+        print("请先运行 scroll_full_contacts.py 进行截图")
+        return
+    
+    screenshots = sorted(glob.glob(os.path.join(scroll_dir, "*.png")))
+    
+    if not screenshots:
+        print("未找到截图文件！")
+        return
+    
+    print(f"找到 {len(screenshots)} 张截图")
+    
+    all_contacts = set()
+    
+    for i, path in enumerate(screenshots):
+        print(f"\n[{i+1}/{len(screenshots)}] {os.path.basename(path)}")
+        result = ocr_image(path)
+        
+        new_count = 0
+        for line in result.strip().split('\n'):
+            line = line.strip()
+            if is_valid_contact(line):
+                cleaned = clean_contact_name(line)
+                if cleaned and len(cleaned) >= 2 and cleaned not in all_contacts:
+                    new_count += 1
+                    print(f"  + {cleaned}")
+                all_contacts.add(cleaned)
+        
+        print(f"  本轮新增 {new_count}，累计 {len(all_contacts)}")
+    
+    # 生成JSON数据
+    contacts_json = []
+    for idx, name in enumerate(sorted(all_contacts, key=lambda x: (not x[0].isalpha() if x else True, x.lower() if x and x[0].isalpha() else x))):
+        if name and len(name) >= 2:
+            contacts_json.append({
+                "id": idx + 1,
+                "name": name,
+                "category": "",
+                "blessing": "马年新春快乐！愿您在新的一年里，事业腾飞，马到成功！",
+                "selected": False
+            })
+    
+    # 保存JSON文件
+    json_file = r"D:\夏骥\微信研究\contacts_data.json"
+    with open(json_file, 'w', encoding='utf-8') as f:
+        json.dump(contacts_json, f, ensure_ascii=False, indent=2)
+    
+    print(f"\nJSON数据已保存: {json_file}")
+    
+    # 保存纯文本结果
+    result_file = r"D:\夏骥\微信研究\ocr_result_full.txt"
+    with open(result_file, 'w', encoding='utf-8') as f:
+        f.write(f"微信通讯录OCR识别结果（完整）\n")
+        f.write(f"共截图 {len(screenshots)} 张\n")
+        f.write(f"共识别 {len(contacts_json)} 个联系人\n")
+        f.write("=" * 60 + "\n\n")
+        for c in contacts_json:
+            f.write(f"{c['name']}\n")
+    
+    print(f"结果已保存: {result_file}")
+    print(f"\n共识别到 {len(contacts_json)} 个不重复联系人")
+
+
+if __name__ == '__main__':
+    main()