157 lines
4.5 KiB
Python
157 lines
4.5 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""
|
||
完整截取微信通讯录 - 小步滚动确保不遗漏
|
||
"""
|
||
import uiautomation as auto
|
||
import time
|
||
import os
|
||
from PIL import Image
|
||
|
||
|
||
def find_wechat_window():
|
||
"""查找微信窗口"""
|
||
wechat_window = auto.WindowControl(searchDepth=1, Name='微信')
|
||
if wechat_window.Exists(3, 1):
|
||
return wechat_window
|
||
return None
|
||
|
||
|
||
def capture_contact_region(wechat_window, index, save_dir):
|
||
"""截取通讯录区域"""
|
||
rect = wechat_window.BoundingRectangle
|
||
|
||
# 通讯录列表区域
|
||
x_offset = 70
|
||
y_offset = 130
|
||
width = 280
|
||
height = rect.height() - 160
|
||
|
||
screenshot_path = os.path.join(save_dir, f"region_{index:04d}.png")
|
||
|
||
try:
|
||
bitmap = wechat_window.ToBitmap(x=x_offset, y=y_offset, width=width, height=height)
|
||
bitmap.ToFile(screenshot_path)
|
||
return screenshot_path
|
||
except Exception as e:
|
||
print(f"截图失败: {e}")
|
||
return None
|
||
|
||
|
||
def get_image_hash(image_path):
|
||
"""计算图片感知哈希"""
|
||
try:
|
||
img = Image.open(image_path)
|
||
img = img.resize((32, 32), Image.Resampling.LANCZOS)
|
||
img = img.convert('L')
|
||
pixels = list(img.getdata())
|
||
avg = sum(pixels) / len(pixels)
|
||
return ''.join(['1' if p > avg else '0' for p in pixels])
|
||
except Exception as e:
|
||
print(f"哈希计算失败: {e}")
|
||
return None
|
||
|
||
|
||
def images_similarity(hash1, hash2):
|
||
"""计算图片相似度"""
|
||
if not hash1 or not hash2:
|
||
return 0
|
||
diff = sum(c1 != c2 for c1, c2 in zip(hash1, hash2))
|
||
return 1 - diff / len(hash1)
|
||
|
||
|
||
def scroll_down(wechat_window, wheel_times=1):
|
||
"""向下滚动 - 小幅度滚动"""
|
||
try:
|
||
rect = wechat_window.BoundingRectangle
|
||
center_x = rect.left + 200
|
||
center_y = rect.top + 400
|
||
|
||
auto.SetCursorPos(center_x, center_y)
|
||
auto.Click(center_x, center_y)
|
||
time.sleep(0.15)
|
||
auto.WheelDown(wheelTimes=wheel_times)
|
||
time.sleep(0.25)
|
||
return True
|
||
except Exception as e:
|
||
print(f"滚动失败: {e}")
|
||
return False
|
||
|
||
|
||
def main():
|
||
print("=" * 60)
|
||
print("完整截取微信通讯录 - 小步滚动版本")
|
||
print("=" * 60)
|
||
|
||
# 创建新的截图目录
|
||
save_dir = r"D:\夏骥\微信研究\scroll_complete"
|
||
|
||
# 清空或创建目录
|
||
if os.path.exists(save_dir):
|
||
import shutil
|
||
shutil.rmtree(save_dir)
|
||
os.makedirs(save_dir)
|
||
|
||
print(f"截图保存目录: {save_dir}")
|
||
|
||
# 查找微信窗口
|
||
print("\n查找微信窗口...")
|
||
wechat_window = find_wechat_window()
|
||
if not wechat_window:
|
||
print("未找到微信窗口！请确保微信已打开。")
|
||
return
|
||
|
||
print(f"找到微信窗口: {wechat_window.Name}")
|
||
|
||
# 提示用户准备
|
||
print("\n" + "!" * 60)
|
||
print("请确保微信通讯录界面已打开，并滚动到最顶部！")
|
||
print("按字母顺序从A开始显示联系人列表")
|
||
print("!" * 60)
|
||
time.sleep(3)
|
||
|
||
# 开始截图
|
||
print("\n开始截图...")
|
||
screenshots = []
|
||
last_hash = None
|
||
no_change_count = 0
|
||
max_screenshots = 2000 # 最大截图数
|
||
consecutive_same = 3 # 连续相同截图数判定到底
|
||
|
||
for i in range(max_screenshots):
|
||
path = capture_contact_region(wechat_window, i, save_dir)
|
||
if not path:
|
||
print(f"截图 {i} 失败，跳过")
|
||
continue
|
||
|
||
screenshots.append(path)
|
||
print(f" 截图 {i + 1}: {os.path.basename(path)}")
|
||
|
||
# 检测是否到底（图片相似度）
|
||
current_hash = get_image_hash(path)
|
||
if last_hash:
|
||
sim = images_similarity(last_hash, current_hash)
|
||
if sim > 0.98: # 非常相似
|
||
no_change_count += 1
|
||
print(f" -> 相似度 {sim:.2%}，连续相同 {no_change_count}")
|
||
if no_change_count >= consecutive_same:
|
||
print(f"\n检测到底部！连续 {consecutive_same} 张截图相同")
|
||
break
|
||
else:
|
||
no_change_count = 0
|
||
last_hash = current_hash
|
||
|
||
# 小幅度滚动（每次滚动1格）
|
||
scroll_down(wechat_window, wheel_times=1)
|
||
|
||
print("\n" + "=" * 60)
|
||
print(f"截图完成！共 {len(screenshots)} 张")
|
||
print(f"保存目录: {save_dir}")
|
||
print("=" * 60)
|
||
|
||
# 提示下一步
|
||
print("\n下一步：运行 batch_ocr_complete.py 进行OCR识别")
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|