Files
douyin_guaji-main/douyin_screenshot_manager.py
T
Your Name f92933641f feat: Enhance documentation and clean up code structure
- Added comprehensive documentation for the unified screenshot and score recording process in the new markdown file.
- Improved existing markdown files by adding spacing for better readability.
- Cleaned up code by removing unnecessary blank lines across various scripts, enhancing overall code clarity.
- Updated configuration settings to reflect recent changes and ensure consistency across the project.
- Enhanced logging mechanisms to support better debugging and monitoring.
2025-12-25 16:11:25 +08:00

772 lines
28 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
from __future__ import annotations
"""
截图管理模块:双截图记录机制
============================
功能:
1. 实时操作截图(latest_attempt.png):每次识别操作都覆盖保存
2. 成功识别存档截图(last_success.png):仅在成功时保存,不会被覆盖
3. OCR文件夹清理:自动清理旧的OCR图片
"""
import os
import shutil
import time
from typing import Optional, Tuple
from PIL import Image
import path_config
def get_ocr_dir() -> str:
"""获取OCR目录路径"""
return os.path.join(path_config.get_pic_dir(), "ocr")
def get_category_for_picname(picname: str) -> str:
"""根据图片名称判断应该保存到哪个分类目录
参数:
picname: 图片名称(不含扩展名)
返回:
分类目录名称,如 "fudai", "live_room", "popups", "buttons", "stage_diag", "others"
"""
picname_lower = picname.lower()
# 福袋相关
if any(keyword in picname_lower for keyword in ["福袋", "fudai"]):
return "fudai"
# 直播间相关
if any(keyword in picname_lower for keyword in [
"live_room", "直播间", "直播列表", "直播广场", "直播状态", "直播验证"
]):
return "live_room"
# 弹窗相关
if any(keyword in picname_lower for keyword in [
"抽奖结果", "无奖励", "优惠券", "购物红包", "奖励通知", "订单确认",
"lucky_draw", "coupon", "redpacket", "reward", "order"
]):
return "popups"
# 按钮相关
if any(keyword in picname_lower for keyword in [
"参与按钮", "粉丝团", "attend_button", "fans_club"
]):
return "buttons"
# 阶段诊断相关
if any(keyword in picname_lower for keyword in [
"推荐页", "关注列表", "直播列表标签", "recommend", "follow", "live_list"
]):
return "stage_diag"
# 其他
return "others"
def get_latest_attempt_path(operation_type: str = "general") -> str:
"""获取实时操作截图路径
参数:
operation_type: 操作类型,可选值:
- "pixel" 或 "pixel_detect": 像素检测
- "ocr": OCR识别
- "template" 或 "template_match": 模板匹配
- 其他: 通用操作
"""
# 规范化操作类型
if operation_type.startswith("pixel"):
type_key = "pixel"
elif operation_type.startswith("ocr") or operation_type.startswith("cut_pic"):
type_key = "ocr"
elif operation_type.startswith("template"):
type_key = "template"
else:
type_key = "general"
return os.path.join(get_ocr_dir(), f"latest_attempt_{type_key}.png")
def get_last_success_path(operation_type: str = "general") -> str:
"""获取成功识别存档截图路径
参数:
operation_type: 操作类型,可选值:
- "pixel" 或 "pixel_detect": 像素检测
- "ocr": OCR识别
- "template" 或 "template_match": 模板匹配
- 其他: 通用操作
"""
# 规范化操作类型
if operation_type.startswith("pixel"):
type_key = "pixel"
elif operation_type.startswith("ocr") or operation_type.startswith("cut_pic"):
type_key = "ocr"
elif operation_type.startswith("template"):
type_key = "template"
else:
type_key = "general"
return os.path.join(get_ocr_dir(), f"last_success_{type_key}.png")
def ensure_ocr_dir() -> None:
"""确保OCR目录存在"""
ocr_dir = get_ocr_dir()
os.makedirs(ocr_dir, exist_ok=True)
def cleanup_ocr_dir(
keep_latest_attempt: bool = True,
keep_last_success: bool = True,
keep_success_files: bool = True,
max_files: int = 50,
) -> int:
"""清理OCR目录中的旧文件
参数:
keep_latest_attempt: 是否保留所有 latest_attempt_*.png 文件
keep_last_success: 是否保留所有 last_success_*.png 文件
keep_success_files: 是否保留所有 _success.png 文件
max_files: 最多保留的文件数(不包括特殊文件)
返回:
清理的文件数量
"""
try:
ocr_dir = get_ocr_dir()
if not os.path.exists(ocr_dir):
return 0
files = []
for f in os.listdir(ocr_dir):
file_path = os.path.join(ocr_dir, f)
if os.path.isfile(file_path) and f.lower().endswith('.png'):
# 检查是否为特殊文件
is_special = False
if f.startswith("latest_attempt_") and keep_latest_attempt:
is_special = True
elif f.startswith("last_success_") and keep_last_success:
is_special = True
elif f.endswith("_success.png") and keep_success_files:
is_special = True
if not is_special:
files.append((file_path, os.path.getmtime(file_path)))
# 按修改时间排序,保留最新的
files.sort(key=lambda x: x[1], reverse=True)
# 删除超出限制的文件
deleted_count = 0
for file_path, _ in files[max_files:]:
try:
os.remove(file_path)
deleted_count += 1
except Exception:
pass
return deleted_count
except Exception:
return 0
def save_latest_attempt(image: Image.Image, operation_type: str = "") -> bool:
"""保存实时操作截图(覆盖保存)
参数:
image: PIL Image 对象
operation_type: 操作类型(用于分类,如 "template_match", "pixel_detect", "ocr", "cut_pic")
返回:
是否保存成功
"""
try:
ensure_ocr_dir()
path = get_latest_attempt_path(operation_type)
image.save(path, "PNG")
return True
except Exception as e:
try:
print(f"[截图管理] 保存 latest_attempt_{operation_type}.png 失败: {e}")
except Exception:
pass
return False
def save_last_success(image: Image.Image, operation_type: str = "") -> bool:
"""保存成功识别存档截图(不覆盖,仅成功时保存)
参数:
image: PIL Image 对象
operation_type: 操作类型(用于分类,如 "template_match", "pixel_detect", "ocr", "cut_pic")
返回:
是否保存成功
"""
try:
ensure_ocr_dir()
path = get_last_success_path(operation_type)
image.save(path, "PNG")
return True
except Exception as e:
try:
print(f"[截图管理] 保存 last_success_{operation_type}.png 失败: {e}")
except Exception:
pass
return False
def save_attempt_from_file(source_path: str, operation_type: str = "") -> bool:
"""从文件保存实时操作截图
参数:
source_path: 源图片文件路径
operation_type: 操作类型
返回:
是否保存成功
"""
try:
if not os.path.exists(source_path):
return False
image = Image.open(source_path)
return save_latest_attempt(image, operation_type)
except Exception as e:
try:
print(f"[截图管理] 从文件保存 latest_attempt.png 失败: {e}")
except Exception:
pass
return False
def save_success_from_file(source_path: str, operation_type: str = "") -> bool:
"""从文件保存成功识别存档截图
参数:
source_path: 源图片文件路径
operation_type: 操作类型
返回:
是否保存成功
"""
try:
if not os.path.exists(source_path):
return False
image = Image.open(source_path)
return save_last_success(image, operation_type)
except Exception as e:
try:
print(f"[截图管理] 从文件保存 last_success.png 失败: {e}")
except Exception:
pass
return False
def get_debug_captures_dir() -> str:
"""获取调试图像存档目录路径"""
pic_dir = path_config.get_pic_dir()
debug_dir = os.path.join(pic_dir, "debug_captures")
# 按日期分类:YYYY-MM-DD
from datetime import datetime
date_str = datetime.now().strftime("%Y-%m-%d")
return os.path.join(debug_dir, date_str)
def ensure_debug_captures_dir() -> None:
"""确保调试图像存档目录存在"""
debug_dir = get_debug_captures_dir()
os.makedirs(debug_dir, exist_ok=True)
def get_debug_captures_base_dir() -> str:
"""获取调试图像存档根目录路径(不包含日期)"""
pic_dir = path_config.get_pic_dir()
return os.path.join(pic_dir, "debug_captures")
def count_debug_captures_files() -> int:
"""统计所有调试图像文件的总数量
返回:
文件总数
"""
try:
debug_base_dir = get_debug_captures_base_dir()
if not os.path.exists(debug_base_dir):
return 0
total_count = 0
# 遍历所有日期目录
for item in os.listdir(debug_base_dir):
# 跳过隐藏文件和标记文件
if item.startswith('.'):
continue
item_path = os.path.join(debug_base_dir, item)
if not os.path.isdir(item_path):
continue
# 统计该目录下的所有PNG文件
try:
for root, dirs, files in os.walk(item_path):
for f in files:
if f.lower().endswith('.png'):
total_count += 1
except Exception:
pass
return total_count
except Exception:
return 0
def cleanup_debug_captures(keep_days: int = 7, max_files: int = 2000) -> int:
"""清理旧的调试图像存档目录
参数:
keep_days: 保留天数,默认7天,超过此天数的目录将被删除
max_files: 最大文件数量,默认2000,超过此数量时删除最旧的目录
返回:
清理的目录数量
"""
try:
debug_base_dir = get_debug_captures_base_dir()
if not os.path.exists(debug_base_dir):
return 0
from datetime import datetime, timedelta
# 计算截止日期
cutoff_date = datetime.now() - timedelta(days=keep_days)
deleted_count = 0
deleted_dirs = []
total_size_freed = 0
# 收集所有日期目录及其信息
dirs_info = []
for item in os.listdir(debug_base_dir):
# 跳过隐藏文件和标记文件
if item.startswith('.'):
continue
item_path = os.path.join(debug_base_dir, item)
if not os.path.isdir(item_path):
continue
# 尝试解析目录名为日期(格式:YYYY-MM-DD)
try:
dir_date = datetime.strptime(item, "%Y-%m-%d")
# 统计该目录下的文件数量和大小
file_count = 0
dir_size = 0
try:
for root, dirs, files in os.walk(item_path):
for f in files:
if f.lower().endswith('.png'):
file_count += 1
file_path = os.path.join(root, f)
try:
dir_size += os.path.getsize(file_path)
except Exception:
pass
except Exception:
pass
dirs_info.append({
'name': item,
'path': item_path,
'date': dir_date,
'file_count': file_count,
'size': dir_size
})
except ValueError:
# 如果目录名不是日期格式,跳过
continue
# 按日期排序(最旧的在前)
dirs_info.sort(key=lambda x: x['date'])
# 先按天数清理:删除超过保留天数的目录
for dir_info in dirs_info[:]:
if dir_info['date'] < cutoff_date:
try:
shutil.rmtree(dir_info['path'])
deleted_count += 1
deleted_dirs.append(dir_info['name'])
total_size_freed += dir_info['size']
dirs_info.remove(dir_info)
except Exception as e:
try:
print(f"[调试图像清理] 删除目录失败 {dir_info['path']}: {e}")
except Exception:
pass
# 再按文件数量清理:如果文件总数超过max_files,删除最旧的目录
total_files = sum(d['file_count'] for d in dirs_info)
if total_files > max_files:
# 计算需要删除的文件数量
need_delete_count = total_files - max_files
# 从最旧的目录开始删除,直到文件数量降到max_files以下
deleted_files_count = 0
for dir_info in dirs_info[:]:
if deleted_files_count >= need_delete_count:
break
try:
shutil.rmtree(dir_info['path'])
deleted_count += 1
deleted_dirs.append(dir_info['name'])
total_size_freed += dir_info['size']
deleted_files_count += dir_info['file_count']
dirs_info.remove(dir_info)
except Exception as e:
try:
print(f"[调试图像清理] 删除目录失败 {dir_info['path']}: {e}")
except Exception:
pass
if deleted_count > 0:
try:
size_mb = total_size_freed / (1024 * 1024)
reason_parts = []
if total_files > max_files:
reason_parts.append(f"文件数量超过{max_files}")
if any(d['date'] < cutoff_date for d in dirs_info if d not in [{'name': name} for name in deleted_dirs]):
reason_parts.append(f"超过{keep_days}天")
reason = ",".join(reason_parts) if reason_parts else "自动清理"
print(
f"[调试图像清理] 已删除 {deleted_count} 个调试图像目录: {', '.join(deleted_dirs)}"
)
print(f"[调试图像清理] 清理原因: {reason}")
if size_mb > 0.1: # 只显示大于0.1MB的清理
print(f"[调试图像清理] 释放空间: {size_mb:.2f} MB")
except Exception:
pass
return deleted_count
except Exception as e:
# 清理失败不应影响程序运行
try:
print(f"[调试图像清理] 清理旧调试图像时出错: {e}")
except Exception:
pass
return 0
def init_debug_captures_cleanup() -> None:
"""初始化调试图像清理(在程序启动时调用)
从 config.json 读取配置并执行清理
"""
try:
import json
config_path = path_config.get_config_path()
if not os.path.exists(config_path):
return
with open(config_path, 'r', encoding='utf-8') as f:
config = json.load(f)
# 检查是否启用自动清理
auto_cleanup = True
keep_days = 7
max_files = 2000
if 'debug_captures' in config and isinstance(config['debug_captures'], dict):
auto_cleanup = config['debug_captures'].get('auto_cleanup', True)
keep_days = int(config['debug_captures'].get('keep_days', 7))
max_files = int(config['debug_captures'].get('max_files', 2000))
if auto_cleanup:
cleanup_debug_captures(keep_days=keep_days, max_files=max_files)
except Exception:
# 初始化失败不影响程序运行
pass
def _sanitize_filename_part(text: str) -> str:
"""清理文件名部分,移除Windows不允许的字符
参数:
text: 要清理的文本
返回:
清理后的文本
"""
if not text:
return ""
# Windows文件名不允许的字符: < > : " / \ | ? *
# 同时移除路径分隔符和空格(用下划线替换)
invalid_chars = '<>:"/\\|?*'
sanitized = str(text)
# 如果是路径,只保留文件名部分
if os.sep in sanitized or '/' in sanitized:
sanitized = os.path.basename(sanitized)
# 移除所有无效字符
for char in invalid_chars:
sanitized = sanitized.replace(char, '_')
# 移除连续的下划线,替换为单个下划线
while '__' in sanitized:
sanitized = sanitized.replace('__', '_')
# 移除首尾的下划线和空格
sanitized = sanitized.strip('_').strip()
# 如果清理后为空,返回默认值
if not sanitized:
sanitized = "unknown"
return sanitized
def save_debug_image(
image: Image.Image,
operation_type: str = "",
picname: str = "",
step: str = "",
coords: Optional[Tuple[int, int, int, int]] = None,
extra_info: Optional[dict] = None,
session_id: Optional[str] = None,
annotate: bool = True,
auto_cleanup: bool = True,
) -> Optional[str]:
"""保存调试图像到存档目录
参数:
image: PIL Image 对象
operation_type: 操作类型("pixel_detect", "ocr", "template_match", "cut_pic")
picname: 图片名称(可选)
step: 步骤描述(可选,如 "before_detect", "detected")
coords: 坐标信息 (x1, y1, x2, y2)(可选)
extra_info: 额外信息字典(可选)
session_id: 会话ID(可选,默认使用当前日期)
annotate: 是否在图像上添加标注信息(默认True)
auto_cleanup: 是否自动清理旧目录(默认True)
返回:
保存的文件路径,失败返回None
"""
try:
# 自动清理旧目录(仅在每天第一次保存时执行)
if auto_cleanup:
try:
# 检查今天是否已经清理过(使用简单的标记文件)
debug_base_dir = get_debug_captures_base_dir()
cleanup_marker = os.path.join(debug_base_dir, ".cleanup_marker")
from datetime import datetime
today_str = datetime.now().strftime("%Y-%m-%d")
# 读取标记文件,检查今天是否已清理
need_cleanup = True
if os.path.exists(cleanup_marker):
try:
with open(cleanup_marker, 'r', encoding='utf-8') as f:
last_cleanup_date = f.read().strip()
if last_cleanup_date == today_str:
need_cleanup = False
except Exception:
pass
if need_cleanup:
# 从配置读取保留天数、最大文件数和自动清理设置
keep_days = 7 # 默认7天
max_files = 2000 # 默认2000个文件
cleanup_enabled = True
try:
import json
config_path = path_config.get_config_path()
if os.path.exists(config_path):
with open(config_path, 'r', encoding='utf-8') as f:
config = json.load(f)
if 'debug_captures' in config and isinstance(config['debug_captures'], dict):
cleanup_enabled = config['debug_captures'].get('auto_cleanup', True)
keep_days = int(config['debug_captures'].get('keep_days', 7))
max_files = int(config['debug_captures'].get('max_files', 2000))
except Exception:
pass
# 如果启用自动清理,执行清理
if cleanup_enabled:
cleanup_debug_captures(keep_days=keep_days, max_files=max_files)
# 更新标记文件(仅在执行清理后更新)
try:
with open(cleanup_marker, 'w', encoding='utf-8') as f:
f.write(today_str)
except Exception:
pass
else:
# 即使今天已经清理过,也要检查文件数量是否超过限制
# 如果超过,立即清理(不更新标记文件,避免频繁清理)
try:
import json
config_path = path_config.get_config_path()
max_files = 2000
if os.path.exists(config_path):
with open(config_path, 'r', encoding='utf-8') as f:
config = json.load(f)
if 'debug_captures' in config and isinstance(config['debug_captures'], dict):
max_files = int(config['debug_captures'].get('max_files', 2000))
# 检查当前文件数量
current_count = count_debug_captures_files()
if current_count > max_files:
# 文件数量超过限制,立即清理
try:
print(f"[调试图像清理] 检测到文件数量 {current_count} 超过限制 {max_files},立即清理")
except Exception:
pass
cleanup_debug_captures(keep_days=999, max_files=max_files) # keep_days设为999表示只按文件数量清理
except Exception:
pass
except Exception:
# 清理失败不影响保存操作
pass
ensure_debug_captures_dir()
debug_dir = get_debug_captures_dir()
# 生成文件名
from datetime import datetime
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
parts = []
if operation_type:
parts.append(_sanitize_filename_part(operation_type))
if picname:
parts.append(_sanitize_filename_part(picname))
if step:
parts.append(_sanitize_filename_part(step))
if coords:
parts.append(f"({coords[0]},{coords[1]})-({coords[2]},{coords[3]})")
if extra_info:
for key, value in extra_info.items():
# 清理键名和值
clean_key = _sanitize_filename_part(str(key))
clean_value = _sanitize_filename_part(str(value))
# 限制值的长度,避免文件名过长
if len(clean_value) > 50:
clean_value = clean_value[:50]
parts.append(f"{clean_key}_{clean_value}")
filename_parts = [timestamp] + parts
filename = "_".join(str(p) for p in filename_parts if p) + ".png"
# Windows文件名长度限制(260字符),自动截断
max_len = 200 # 留一些余量
if len(filename) > max_len:
# 保留时间戳和关键信息,截断其他部分
base = f"{timestamp}_{operation_type}_{picname}_{step}"
if len(base) < max_len - 20:
remaining = max_len - len(base) - 20
if coords:
coord_str = f"({coords[0]},{coords[1]})-({coords[2]},{coords[3]})"
if len(coord_str) <= remaining:
base += f"_{coord_str}"
filename = base[:max_len] + ".png"
file_path = os.path.join(debug_dir, filename)
# 在保存文件前,再次确保目录存在(防止并发访问或权限问题导致目录不存在)
try:
ensure_debug_captures_dir()
except Exception:
pass # 如果目录创建失败,继续尝试保存,让保存时的异常处理来处理
# 保存图像的辅助函数,带重试机制
def save_image_with_retry(img_to_save: Image.Image, path: str, max_retries: int = 2) -> bool:
"""保存图像,如果目录不存在则创建后重试"""
for attempt in range(max_retries):
try:
img_to_save.save(path, "PNG")
return True
except FileNotFoundError:
# 目录不存在,尝试创建后重试
if attempt < max_retries - 1:
try:
ensure_debug_captures_dir()
except Exception:
pass
else:
# 最后一次尝试失败,抛出异常
raise
except Exception:
# 其他异常直接抛出
raise
return False
# 如果需要标注,在图像上添加信息
if annotate and (coords or extra_info):
try:
from PIL import ImageDraw, ImageFont
annotated_image = image.copy()
draw = ImageDraw.Draw(annotated_image)
# 尝试使用默认字体
try:
font = ImageFont.truetype("arial.ttf", 12)
except Exception:
try:
font = ImageFont.load_default()
except Exception:
font = None
# 绘制坐标框
if coords:
x1, y1, x2, y2 = coords
# 确保坐标在图像范围内
img_w, img_h = annotated_image.size
x1 = max(0, min(x1, img_w - 1))
y1 = max(0, min(y1, img_h - 1))
x2 = max(0, min(x2, img_w - 1))
y2 = max(0, min(y2, img_h - 1))
if x1 < x2 and y1 < y2:
# 使用元组格式 (x1, y1, x2, y2)
rect_coords: Tuple[float, float, float, float] = (float(x1), float(y1), float(x2), float(y2))
draw.rectangle(rect_coords, outline="red", width=2)
# 添加文本信息
if extra_info:
text_lines = [f"{k}: {v}" for k, v in extra_info.items()]
if text_lines:
text = "\n".join(text_lines)
# 在图像左上角添加文本
try:
draw.text((5, 5), text, fill="yellow", font=font)
except Exception:
pass
save_image_with_retry(annotated_image, file_path)
except Exception:
# 如果标注失败,直接保存原图
try:
save_image_with_retry(image, file_path)
except Exception:
# 如果保存原图也失败,抛出异常让外层处理
raise
else:
save_image_with_retry(image, file_path)
return file_path
except Exception as e:
try:
print(f"[截图管理] 保存调试图像失败: {e}")
except Exception:
pass
return None