145 lines
4.4 KiB
Python
145 lines
4.4 KiB
Python
# -*- 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()
|