feat(project): 初始化项目结构和配置
- 添加.gitignore和.flaskenv环境配置文件 - 创建Flask应用基础架构，包括models、services、utils模块 - 配置数据库模型User和Setting，集成SQLAlchemy和Alembic迁移 - 添加前端Vue项目结构，包含Element Plus组件库 - 配置前后端API路由和蓝prints模块 - 实现书籍下载服务BookService功能模块 - 添加代码规范配置.editorconfig、.oxfmtrc.json、.oxlintrc.json - 配置VSCode推荐插件和前端构建工具链 - 实现文件服务FileService和相关业务逻辑
This commit is contained in:
@@ -0,0 +1,26 @@
|
||||
from flask import Flask
|
||||
from flask_cors import CORS
|
||||
from .extensions import db, migrate
|
||||
from .config import DevelopmentConfig, ProductionConfig, TestingConfig
|
||||
|
||||
|
||||
def create_app(config_name="development"):
|
||||
app = Flask(__name__)
|
||||
CORS(app)
|
||||
app.config.from_object(DevelopmentConfig)
|
||||
|
||||
match config_name:
|
||||
case 'production':
|
||||
app.config.from_object(ProductionConfig)
|
||||
case 'testing':
|
||||
app.config.from_object(TestingConfig)
|
||||
case _:
|
||||
app.config.from_object(DevelopmentConfig)
|
||||
|
||||
db.init_app(app)
|
||||
migrate.init_app(app, db)
|
||||
|
||||
from .blueprints.api import bp as api_bp
|
||||
app.register_blueprint(api_bp, url_prefix='/api')
|
||||
|
||||
return app
|
||||
@@ -0,0 +1,91 @@
|
||||
from typing import List
|
||||
from flask import Blueprint, jsonify, Response, current_app
|
||||
from app.services import FileService, VideoService, TorrentService, BookService, ImageService, MusicService
|
||||
|
||||
bp = Blueprint("api", __name__)
|
||||
|
||||
|
||||
@bp.route("/book/download")
|
||||
def book_download():
|
||||
book_object = BookService()
|
||||
app = current_app._get_current_object()
|
||||
|
||||
def generate():
|
||||
with app.app_context():
|
||||
yield from book_object.book_download()
|
||||
|
||||
return Response(generate(), mimetype='text/event-stream')
|
||||
|
||||
@bp.route("/video/findDeduplication")
|
||||
def video_find_deduplication():
|
||||
video_object = VideoService(paths=[
|
||||
"C:\\迅雷下载\\0_done",
|
||||
"D:\\",
|
||||
"E:\\",
|
||||
"F:\\"
|
||||
])
|
||||
|
||||
return jsonify({"code": 200, "message": video_object.find_deduplication()})
|
||||
|
||||
|
||||
@bp.route('/video/deduplication')
|
||||
def video_deduplication():
|
||||
video_object = VideoService(paths=[
|
||||
"C:\\迅雷下载\\0_done",
|
||||
"D:\\",
|
||||
"E:\\",
|
||||
"F:\\"
|
||||
])
|
||||
|
||||
return jsonify({"code": 200, "message": video_object.deduplication()})
|
||||
|
||||
|
||||
@bp.route("/video/hasTorrent")
|
||||
def video_has_torrent():
|
||||
torrent_obj = TorrentService(["E:\\"])
|
||||
return jsonify({"code": 200, "message": torrent_obj.has_torrent()})
|
||||
|
||||
|
||||
@bp.route('/files/rename')
|
||||
def files_rename():
|
||||
paths: List[str] = [
|
||||
"C:\\迅雷下载\\0_done",
|
||||
"C:\\Users\\Localhost\\Desktop\\BT",
|
||||
]
|
||||
|
||||
file_object = FileService(paths)
|
||||
return jsonify({"code": 200, "message": file_object.rename()})
|
||||
|
||||
|
||||
@bp.route('/torrent/deduplication')
|
||||
def torrent_deduplication():
|
||||
torrent_object = TorrentService(["C:\\Users\\Localhost\\Desktop\\BT"])
|
||||
return jsonify({"code": 200, "message": torrent_object.deduplication()})
|
||||
|
||||
|
||||
@bp.route("/image/export")
|
||||
def image_export():
|
||||
image_object = ImageService()
|
||||
|
||||
def generate():
|
||||
yield from image_object.export()
|
||||
|
||||
return Response(generate(), mimetype='text/event-stream')
|
||||
|
||||
|
||||
@bp.route("/image/hasTorrent")
|
||||
def image_has_torrent():
|
||||
torrent_obj = TorrentService(["C:\\Users\\Localhost\\Desktop\\Images"])
|
||||
return jsonify({"code": 200, "message": torrent_obj.has_torrent()})
|
||||
|
||||
|
||||
@bp.route("/music/rename")
|
||||
def music_rename():
|
||||
music_object = MusicService()
|
||||
return jsonify({"code": 200, "message": music_object.rename()})
|
||||
|
||||
@bp.route("/torrent/statistics")
|
||||
def torrent_statistics():
|
||||
torrent_object = TorrentService(["C:\\Users\\Localhost\\Desktop\\BT"])
|
||||
return jsonify({"code": 200, "message": torrent_object.statistics()})
|
||||
|
||||
@@ -0,0 +1,16 @@
|
||||
class Config:
|
||||
SECRET_KEY = 'mysecretkey'
|
||||
SQLALCHEMY_DATABASE_URI = 'sqlite:///flask.db'
|
||||
SQLALCHEMY_TRACK_MODIFICATIONS = False
|
||||
|
||||
|
||||
class DevelopmentConfig(Config):
|
||||
DEBUG = True
|
||||
|
||||
|
||||
class ProductionConfig(Config):
|
||||
DEBUG = False
|
||||
|
||||
|
||||
class TestingConfig(Config):
|
||||
TESTING = True
|
||||
@@ -0,0 +1,17 @@
|
||||
import os
|
||||
IGNORE_DIRS = {
|
||||
"System Volume Information",
|
||||
"$RECYCLE.BIN",
|
||||
"Prevent Disk Sleep.txt",
|
||||
"PREVENT DISK SLEEP.txt",
|
||||
"images",
|
||||
"done_images",
|
||||
"女同"
|
||||
}
|
||||
SPECIAL_PREFIXES = {"T28", "FC2"}
|
||||
SEPARATORS = {"♀ ", "♀ ", "+"}
|
||||
SPECIAL_DIRS = {"川村まや", "上原亜衣", "上原志織"}
|
||||
IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.gif', '.bmp', '.tiff', '.webp', '.svg'}
|
||||
DISLIKE_DIRS = {"篠真有", "二羽紗愛", "綾瀬天"}
|
||||
USERPROFILE = os.environ.get("USERPROFILE")
|
||||
TORRENT_ROOT_FOLDER: str = os.path.join(USERPROFILE, "Desktop\\BT")
|
||||
@@ -0,0 +1,5 @@
|
||||
from flask_migrate import Migrate
|
||||
from flask_sqlalchemy import SQLAlchemy
|
||||
|
||||
db = SQLAlchemy()
|
||||
migrate = Migrate()
|
||||
@@ -0,0 +1,2 @@
|
||||
from .user import User
|
||||
from .setting import Setting
|
||||
@@ -0,0 +1,29 @@
|
||||
from ..extensions import db
|
||||
|
||||
|
||||
class Setting(db.Model):
|
||||
name = db.Column(db.String(64), nullable=False)
|
||||
mod = db.Column(db.String(64), index=True, unique=True)
|
||||
fid = db.Column(db.Integer, primary_key=True)
|
||||
orderby = db.Column(db.String(64))
|
||||
baseUrl = db.Column(db.String(64))
|
||||
targetDate = db.Column(db.String(64))
|
||||
targetCountdownPage = db.Column(db.Integer)
|
||||
totalPage = db.Column(db.Integer)
|
||||
privilegeLevel = db.Column(db.Integer)
|
||||
|
||||
def __repr__(self):
|
||||
return '<Setting %r>' % self.name
|
||||
|
||||
def to_dict(self):
|
||||
return {
|
||||
'name': self.name,
|
||||
'mod': self.mod,
|
||||
'fid': self.fid,
|
||||
'orderby': self.orderby,
|
||||
'baseUrl': self.baseUrl,
|
||||
'targetDate': self.targetDate,
|
||||
'targetCountdownPage': self.targetCountdownPage,
|
||||
'totalPage': self.totalPage,
|
||||
'privilegeLevel': self.privilegeLevel
|
||||
}
|
||||
@@ -0,0 +1,11 @@
|
||||
from ..extensions import db
|
||||
|
||||
|
||||
class Torrent(db.Model):
|
||||
id = db.Column(db.Integer, primary_key=True)
|
||||
name = db.Column(db.String(64), index=True, unique=True)
|
||||
captions_exists = db.Column(db.Boolean, server_default=db.false())
|
||||
captions_effective = db.Column(db.Boolean, server_default=db.false())
|
||||
|
||||
def __repr__(self):
|
||||
return '<Torrent %r>' % self.id
|
||||
@@ -0,0 +1,17 @@
|
||||
from ..extensions import db
|
||||
# 定义模型类（数据表）
|
||||
class User(db.Model):
|
||||
id = db.Column(db.Integer, primary_key=True)
|
||||
username = db.Column(db.String(80), unique=True, nullable=False)
|
||||
email = db.Column(db.String(120), unique=True, nullable=False)
|
||||
|
||||
def __repr__(self):
|
||||
return f'<User {self.username}>'
|
||||
|
||||
# 将对象转换为字典，方便返回 JSON
|
||||
def to_dict(self):
|
||||
return {
|
||||
'id': self.id,
|
||||
'username': self.username,
|
||||
'email': self.email
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
from .folder_service import FolderService
|
||||
from .file_service import FileService
|
||||
from .torrent_service import TorrentService
|
||||
from .book_service import BookService
|
||||
from .image_service import ImageService
|
||||
from .music_service import MusicService
|
||||
from .video_service import VideoService
|
||||
@@ -0,0 +1,163 @@
|
||||
import os
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from app.extensions import db
|
||||
from tenacity import retry, stop_after_attempt, RetryError
|
||||
from app.utils import datetime_to_timestamp, timestamp_to_datetime, get_today_timestamp
|
||||
from app.models import Setting
|
||||
|
||||
|
||||
class BookService:
|
||||
def __init__(self):
|
||||
self.setting = Setting.query.filter_by(name="book_download").first().to_dict()
|
||||
self.setting["targetDate"] = timestamp_to_datetime(datetime_to_timestamp(self.setting["targetDate"]) - 24 * 60 * 60)
|
||||
app_dir = os.path.dirname(os.path.dirname(__file__))
|
||||
self.download_path = os.path.join(os.path.dirname(app_dir), "download") # 下载目录
|
||||
self.today_timestamp = get_today_timestamp()
|
||||
self.one_date_loading = False
|
||||
self.headers = {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36",
|
||||
"cookie": "cPNj_2132_saltkey=CeJLs8Ed; "
|
||||
"cPNj_2132_auth=44bdzFfx4TYjBMhuKf4AZdi2JM%2BXZ0Okxd0JEl1Hmwbz%2Fr3WiX0sLmATmolWkLlRgorFz%2BULizz5o6G%2FJ3YGWYPF0xw; "
|
||||
}
|
||||
|
||||
def legitimate_naming(self, name): # 合法命名
|
||||
name = name.replace(":", "：")
|
||||
name = name.replace("<", "《")
|
||||
name = name.replace(">", "》")
|
||||
name = name.replace("/", " ")
|
||||
name = name.replace("\\", " ")
|
||||
name = name.replace("?", "？")
|
||||
return name
|
||||
|
||||
def create_folder(self, target_dir, name): # 创建文件夹
|
||||
real_dir = os.path.join(target_dir, name)
|
||||
folder = os.path.exists(real_dir)
|
||||
if not folder:
|
||||
os.makedirs(real_dir)
|
||||
else:
|
||||
print(f"文件夹：{name} 已存在")
|
||||
|
||||
def isDownloadTarget(self, soup): # 是否是可以下载的文件
|
||||
return soup.headers.get('Content-Type') in ['"application/octet-stream"', "application/octet-stream"]
|
||||
|
||||
def post_page(self, name, url): # 帖子页面
|
||||
response = requests.get(f"{self.setting["baseUrl"]}{url}", headers=self.headers)
|
||||
print(f"详情页面状态码：{str(response.status_code)}")
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
resource_boxs = soup.select('ignore_js_op')
|
||||
for i in resource_boxs:
|
||||
download_dir_path = os.path.join(self.download_path, self.setting["targetDate"])
|
||||
self.create_folder(download_dir_path, name)
|
||||
try:
|
||||
for string in i.select_one(".tip.tip_4").stripped_strings:
|
||||
if "阅读权限: " in repr(string):
|
||||
privilege_level = int(
|
||||
repr(string).strip("'").strip('阅读权限: '))
|
||||
if privilege_level > self.setting["privilegeLevel"]:
|
||||
print("下载失败，权限等级不够")
|
||||
return
|
||||
yield from self.download_file(f"{self.setting["baseUrl"]}{i.select_one(
|
||||
'a')['href']}", name, i.select_one('a').string)
|
||||
except RetryError as e:
|
||||
print('重试三次也不成功')
|
||||
|
||||
@retry(stop=stop_after_attempt(3))
|
||||
def download_file(self, file_url, dir_name, file_name): # 下载文件
|
||||
file_res = requests.get(file_url, headers=self.headers, stream=True, allow_redirects=False)
|
||||
if file_res.status_code in (301, 302, 307, 308): # 非200状态码，重新请求
|
||||
location = file_res.headers["location"]
|
||||
print(f'跳转页面了：{location}')
|
||||
file_res = requests.get(location, headers={"referer": location}, stream=True)
|
||||
print(f"下载状态码：{file_res.status_code} {file_url}")
|
||||
print(dir_name + "/" + file_name)
|
||||
yield f"data: {self.setting["targetDate"]} {file_name}\n\n"
|
||||
if self.isDownloadTarget(file_res):
|
||||
with open(f"download/{self.setting["targetDate"]}/{dir_name}/{file_name}", 'wb') as file2:
|
||||
for chunk in file_res.iter_content(chunk_size=1024):
|
||||
if chunk:
|
||||
file2.write(chunk)
|
||||
|
||||
def section_page(self, page): # 版块页面
|
||||
print(f"当前页面 {page}")
|
||||
target_date_timestamp = datetime_to_timestamp(self.setting["targetDate"]) # 目标时间戳
|
||||
if target_date_timestamp >= self.today_timestamp: # 判断时间（是否大于当前时间戳）
|
||||
# print("不允许下载当天的")
|
||||
yield f"data: 不允许下载当天的\n\n"
|
||||
return None
|
||||
# yield f"data: 当前页面 {page}\n\n"
|
||||
url = f"{self.setting["baseUrl"]}forum.php?mod={self.setting["mod"]}&fid={self.setting["fid"]}&page={page}" # 版块页面地址
|
||||
response = requests.get(url, headers=self.headers) # 请求
|
||||
soup = BeautifulSoup(response.text, 'lxml') # 解析
|
||||
total_page_element = soup.select_one("a.bm_h") # 获取总页数元素
|
||||
if total_page_element is not None: # 总页数元素存在 则更新总页数
|
||||
new_total_page = int(total_page_element.get("totalpage")) # 获取总页数
|
||||
if self.setting["totalPage"] != new_total_page: # 总页数有更新
|
||||
self.setting["totalPage"] = new_total_page # 更新总页数
|
||||
Setting.query.filter_by(name="book_download").update({"totalPage": self.setting["totalPage"]})
|
||||
db.session.commit()
|
||||
yield from self.section_page(new_total_page - self.setting["targetCountdownPage"]) # 重新跳转指点版块页面
|
||||
return None
|
||||
|
||||
posts = soup.select("table#threadlisttableid tbody[id^=normalthread]") # 获取帖子列表
|
||||
posts.reverse() # 帖子列表倒序
|
||||
posts_min_timestamp = datetime_to_timestamp(self.get_post_date(posts[0])) # 帖子列表最小时间戳
|
||||
posts_max_timestamp = datetime_to_timestamp(self.get_post_date(posts[-1])) # 帖子列表最大时间戳
|
||||
|
||||
# 本页最早的帖子时间戳小于等于目标时间戳 且 倒计时页数大于 0 则跳转到上一页继续查找
|
||||
if posts_min_timestamp >= target_date_timestamp and not self.one_date_loading and self.setting["targetCountdownPage"] > 0:
|
||||
print("跳转到上一页")
|
||||
# yield f"data: 跳转到上一页\n\n"
|
||||
self.setting["targetCountdownPage"] = max(self.setting["targetCountdownPage"] - 1, 0)
|
||||
Setting.query.filter_by(name="book_download").update({"targetCountdownPage": self.setting["targetCountdownPage"]})
|
||||
db.session.commit()
|
||||
yield from self.section_page(self.setting["totalPage"] - self.setting["targetCountdownPage"])
|
||||
return None
|
||||
else:
|
||||
print("不需要跳转上一页")
|
||||
self.one_date_loading = True
|
||||
# yield f"data: 不需要跳转上一页\n\n"
|
||||
for post in posts:
|
||||
post_element = post.select_one(".s.xst")
|
||||
post_date = self.get_post_date(post) # 获取帖子时间
|
||||
post_date_timestamp = datetime_to_timestamp(post_date) # 帖子时间戳
|
||||
if post_date_timestamp == target_date_timestamp: # 判断是否是目标时间
|
||||
print(f"目标时间是{post_date}")
|
||||
# yield f"data: 目标时间是{post_date}\n\n"
|
||||
yield from self.post_page(self.legitimate_naming(post_element.string), post_element['href']) # 跳转帖子页面
|
||||
if post_date_timestamp > target_date_timestamp: # 帖子时间大于目标时间并且没有下一天时间
|
||||
self.setting["targetDate"] = post_date
|
||||
Setting.query.filter_by(name="book_download").update({"targetDate": self.setting["targetDate"]})
|
||||
db.session.commit()
|
||||
print(f"下一天是 {post_date}")
|
||||
# yield f"data: 下一天是 {post_date}\n\n"
|
||||
self.one_date_loading = False
|
||||
yield from self.section_page(self.setting["totalPage"] - self.setting["targetCountdownPage"])
|
||||
return None
|
||||
# 判断是否需要跳转到下一页
|
||||
if posts_max_timestamp <= target_date_timestamp and self.setting["targetCountdownPage"] < self.setting[
|
||||
"totalPage"] - 1:
|
||||
print("跳转到下一页")
|
||||
# yield f"data: 跳转到下一页\n\n"
|
||||
self.setting["targetCountdownPage"] = min(self.setting["targetCountdownPage"] + 1,
|
||||
self.setting["totalPage"] - 1)
|
||||
Setting.query.filter_by(name="book_download").update(
|
||||
{"targetCountdownPage": self.setting["targetCountdownPage"]})
|
||||
db.session.commit()
|
||||
yield from self.section_page(self.setting["totalPage"] - self.setting["targetCountdownPage"])
|
||||
return None
|
||||
|
||||
def get_post_date(self, element):
|
||||
if element.select_one(".by em span span"):
|
||||
if element.select_one(".by em span span").get("title"):
|
||||
return element.select_one(".by em span span").get("title")
|
||||
else:
|
||||
return element.select_one(".by em span span").string
|
||||
else:
|
||||
return element.select_one(".by em span").string
|
||||
|
||||
def book_download(self):
|
||||
self.create_folder(self.download_path, self.setting["targetDate"]) # 创建文件夹
|
||||
target_page = self.setting["totalPage"] - self.setting["targetCountdownPage"] # 目标页
|
||||
yield from self.section_page(target_page) # 前往目标页
|
||||
yield f"event: close\ndata: 已完成\n\n"
|
||||
@@ -0,0 +1,75 @@
|
||||
import os
|
||||
from typing import List, Optional
|
||||
|
||||
from app.services import FolderService
|
||||
from app.utils import windows_sort_unicode
|
||||
from app.constants import IGNORE_DIRS, SEPARATORS, SPECIAL_PREFIXES, SPECIAL_DIRS
|
||||
|
||||
|
||||
class FileService:
|
||||
def __init__(self, paths: List[str]):
|
||||
self.paths = paths
|
||||
self.result_list: list[str] = []
|
||||
|
||||
def perform_rename(self, entry: os.DirEntry[str], new_name: str) -> Optional[str]:
|
||||
if new_name == entry.name:
|
||||
return None
|
||||
|
||||
new_path = os.path.join(os.path.dirname(entry.path), new_name)
|
||||
os.rename(entry.path, new_path)
|
||||
self.result_list.insert(0, new_path)
|
||||
# return new_path
|
||||
|
||||
def process_folder_name(self, entry: os.DirEntry[str]) -> Optional[str]:
|
||||
if not any(sep in entry.name for sep in SEPARATORS):
|
||||
return None
|
||||
|
||||
# 替换所有分隔符为+
|
||||
new_name = entry.name
|
||||
for sep in SEPARATORS:
|
||||
new_name = new_name.replace(sep, "+")
|
||||
|
||||
# 分割并排序各部分
|
||||
parts = new_name.split("+")
|
||||
sorted_parts = windows_sort_unicode(parts)
|
||||
new_name = "+".join(sorted_parts)
|
||||
|
||||
if new_name == entry.name:
|
||||
return None
|
||||
|
||||
return self.perform_rename(entry, new_name)
|
||||
|
||||
def process_file_name(self, entry: os.DirEntry[str]) -> Optional[str]:
|
||||
parent_dir = os.path.basename(os.path.dirname(entry.path))
|
||||
name, ext = os.path.splitext(entry.name)
|
||||
ext = ext.lower()
|
||||
name = name.upper()
|
||||
|
||||
# 排除特殊文件夹，仅处理大小写问题
|
||||
if parent_dir in SPECIAL_DIRS:
|
||||
return self.perform_rename(entry, f"{name}{ext}")
|
||||
|
||||
name = name.replace("-", "")
|
||||
|
||||
# 处理特殊前缀
|
||||
for prefix in SPECIAL_PREFIXES:
|
||||
if name.startswith(prefix):
|
||||
return self.perform_rename(entry, f"{prefix}-{name[len(prefix):]}{ext}")
|
||||
|
||||
# 在字母和数字之间添加连字符
|
||||
new_name = []
|
||||
for i, char in enumerate(name):
|
||||
if i > 0 and not name[i - 1].isnumeric() and char.isnumeric():
|
||||
new_name.append(f"-{char}")
|
||||
else:
|
||||
new_name.append(char)
|
||||
|
||||
if ''.join(new_name[-2:]) == "4K":
|
||||
new_name.insert(-2, "-")
|
||||
|
||||
return self.perform_rename(entry, f"{''.join(new_name)}{ext}")
|
||||
|
||||
def rename(self) -> List[str]:
|
||||
FolderService(paths=self.paths, ignore_dirs=IGNORE_DIRS, folder_callback=self.process_folder_name,
|
||||
file_callback=self.process_file_name).process_folder()
|
||||
return self.result_list
|
||||
@@ -0,0 +1,46 @@
|
||||
import os
|
||||
from typing import Optional, Callable, List
|
||||
|
||||
|
||||
class FolderService:
|
||||
def __init__(
|
||||
self,
|
||||
paths: List[str] | str,
|
||||
ignore_dirs: Optional[set] = None,
|
||||
folder_callback: Optional[Callable] = None,
|
||||
file_callback: Optional[Callable] = None,
|
||||
empty_folder_callback: Optional[Callable] = None,
|
||||
max_depth: Optional[int] = None
|
||||
):
|
||||
self.paths: List[str] = paths if type(paths) is not str else [paths]
|
||||
self.ignore_dirs = ignore_dirs or set()
|
||||
self.folder_callback = folder_callback
|
||||
self.file_callback = file_callback
|
||||
self.empty_folder_callback = empty_folder_callback
|
||||
self.max_depth = max_depth
|
||||
|
||||
def _traverse_folder(self, path: Optional[str] = None, depth: Optional[int] = 0) -> None:
|
||||
"""处理目录"""
|
||||
for entry in os.scandir(path):
|
||||
if entry.name in self.ignore_dirs:
|
||||
continue
|
||||
if entry.is_dir():
|
||||
# 判断要加载的文件夹深度
|
||||
if self.max_depth is not None and depth >= self.max_depth:
|
||||
return
|
||||
# 循环加载
|
||||
self._traverse_folder(entry.path, depth + 1)
|
||||
# 判断是空文件夹
|
||||
if not os.listdir(entry.path) and self.empty_folder_callback:
|
||||
self.empty_folder_callback(entry)
|
||||
# 文件夹处理的回调
|
||||
if self.folder_callback:
|
||||
self.folder_callback(entry)
|
||||
elif entry.is_file():
|
||||
if self.file_callback:
|
||||
self.file_callback(entry)
|
||||
|
||||
def process_folder(self) -> None:
|
||||
for path in self.paths:
|
||||
if os.path.exists(path):
|
||||
self._traverse_folder(path)
|
||||
@@ -0,0 +1,40 @@
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
|
||||
from app.services import FolderService
|
||||
from app.constants import IMAGE_EXTENSIONS, IGNORE_DIRS
|
||||
|
||||
|
||||
class ImageService:
|
||||
def __init__(self):
|
||||
self.prefix_pattern = re.compile(r'(?i)[A-Z]+\.')
|
||||
self.paths = ["C:\\Users\\Localhost\\Desktop\\images"]
|
||||
self.image_root_folder = "C:\\Users\\Localhost\\Desktop\\images"
|
||||
self.done_image = "C:\\Users\\Localhost\\Desktop\\BT\\done_images"
|
||||
|
||||
def export_callback(self, entry: os.DirEntry[str]) -> None:
|
||||
name, ext = os.path.splitext(entry.name)
|
||||
ext = ext.lower()
|
||||
if ext in IMAGE_EXTENSIONS:
|
||||
file_parent_dir = os.path.basename(os.path.dirname(entry.path))
|
||||
dest_dir = os.path.join(self.image_root_folder, file_parent_dir)
|
||||
os.makedirs(dest_dir, exist_ok=True)
|
||||
|
||||
dest_file = os.path.join(dest_dir, entry.name)
|
||||
if os.path.exists(dest_file):
|
||||
yield f"data: {entry.name} 已存在\n\n"
|
||||
return
|
||||
|
||||
try:
|
||||
shutil.move(entry.path, dest_file)
|
||||
except shutil.Error as e:
|
||||
yield f"data: 移动失败: {e}\n\n"
|
||||
|
||||
def export(self):
|
||||
FolderService(self.paths, ignore_dirs=IGNORE_DIRS, file_callback=self.export_callback).process_folder()
|
||||
|
||||
# 去结尾字母，已使用过了
|
||||
def remove_last_letter(self, entry: os.DirEntry[str]):
|
||||
without_modifier_file_name = self.prefix_pattern.sub('.', entry.name)
|
||||
os.rename(entry.path, os.path.join(os.path.dirname(entry.path), without_modifier_file_name))
|
||||
@@ -0,0 +1,22 @@
|
||||
import os
|
||||
from typing import List
|
||||
from app.services import FolderService
|
||||
from app.utils import windows_sort_unicode
|
||||
|
||||
class MusicService:
|
||||
def __init__(self):
|
||||
self.paths: List[str] = ["C:\\Users\\Localhost\\Desktop\\Music"]
|
||||
self.result_list: List[str] = []
|
||||
|
||||
def perform_rename(self, entry: os.DirEntry[str]):
|
||||
name, ext = os.path.splitext(entry.name)
|
||||
music_artist, music_name = name.split(" - ")
|
||||
music_artist_list = music_artist.split("、")
|
||||
sorted_music_artist_list = windows_sort_unicode(music_artist_list)
|
||||
new_music_artist = "、".join(sorted_music_artist_list)
|
||||
if music_artist != new_music_artist:
|
||||
self.result_list.insert(0, f"{new_music_artist} - {music_name}")
|
||||
|
||||
def rename(self):
|
||||
FolderService(paths=self.paths, ignore_dirs={"old", "专辑"}, file_callback=self.perform_rename).process_folder()
|
||||
return self.result_list
|
||||
@@ -0,0 +1,81 @@
|
||||
import os
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from typing import List
|
||||
|
||||
from app.constants import IGNORE_DIRS
|
||||
from app.services import FolderService
|
||||
from app.utils import to_json_serializable
|
||||
|
||||
|
||||
class TorrentService:
|
||||
def __init__(self, paths: List[str]):
|
||||
self.paths: List[str] = paths
|
||||
self.torrent_root_folder = ["C:\\Users\\Localhost\\Desktop\\BT"]
|
||||
self.prefix_pattern = re.compile(r'(?i)[A-Z]+\.')
|
||||
self.torrent_list = defaultdict(set)
|
||||
self.list_of_duplicate_torrent: List[str] = []
|
||||
self.result_list = []
|
||||
self.torrent_name = defaultdict(lambda: defaultdict(set))
|
||||
|
||||
def process_torrent_file(self, entry: os.DirEntry[str]) -> None:
|
||||
temp_name = entry.name.replace("-4K", "")
|
||||
without_modifier_file_name = self.prefix_pattern.sub('.', temp_name)
|
||||
name, ext = os.path.splitext(without_modifier_file_name)
|
||||
if name not in self.torrent_list:
|
||||
self.torrent_list[name].add(os.path.basename(os.path.dirname(entry.path)))
|
||||
else:
|
||||
for torrent_path in self.torrent_list[name]:
|
||||
if not os.path.exists(os.path.join(os.path.dirname(entry.path), f"{name}A{ext}")):
|
||||
self.list_of_duplicate_torrent.insert(0, name)
|
||||
print(f"data: {entry.name} 已有种子: {torrent_path}")
|
||||
|
||||
def generate_torrent_list(self):
|
||||
folder_obj = FolderService(paths=self.paths, ignore_dirs=IGNORE_DIRS, file_callback=self.process_torrent_file)
|
||||
folder_obj.process_folder()
|
||||
return self.torrent_list
|
||||
|
||||
def deduplication(self):
|
||||
self.generate_torrent_list()
|
||||
return self.list_of_duplicate_torrent
|
||||
|
||||
def has_torrent_callback(self, entry: os.DirEntry):
|
||||
temp_name = entry.name
|
||||
temp_name = temp_name.replace("-4K", "")
|
||||
without_modifier_file_name = self.prefix_pattern.sub('.', temp_name)
|
||||
name, ext = os.path.splitext(without_modifier_file_name)
|
||||
if name not in self.torrent_list:
|
||||
self.result_list.insert(0, f"{os.path.basename(os.path.dirname(entry.path))} {entry.name} 该文件无种子")
|
||||
|
||||
def has_torrent(self):
|
||||
FolderService(paths=self.torrent_root_folder, ignore_dirs=IGNORE_DIRS,
|
||||
file_callback=self.process_torrent_file).process_folder()
|
||||
FolderService(paths=self.paths, ignore_dirs=IGNORE_DIRS,
|
||||
file_callback=self.has_torrent_callback).process_folder()
|
||||
return self.result_list
|
||||
|
||||
def statistics_file_callback(self, entry: os.DirEntry):
|
||||
path_arr = entry.path.split(os.sep)
|
||||
torrent_sub_type = {"0_多人", "FWAY", "0_女同", "_temp"}
|
||||
torrent_type = {"4k2", "4K原版", "456k", "1024", "2048", "done", "FC2", "hhd800", "other", "高清中文字幕",
|
||||
"三级写真", "无码流出", "亚洲有码原创"}
|
||||
if path_arr[-2] not in torrent_type and path_arr[-2] not in torrent_sub_type:
|
||||
if path_arr[-3] in torrent_sub_type:
|
||||
# print(path_arr[-3])
|
||||
if path_arr[-4] in torrent_type:
|
||||
# print(path_arr[-4])
|
||||
pass
|
||||
else:
|
||||
print(f"有奇怪的东西混入{path_arr}")
|
||||
pass
|
||||
elif path_arr[-3] in torrent_type:
|
||||
self.torrent_name[path_arr[-2]][path_arr[-3]].add(entry.name)
|
||||
pass
|
||||
else:
|
||||
print(f"有奇怪的东西混入2{path_arr}")
|
||||
|
||||
def statistics(self):
|
||||
FolderService(paths=self.paths,
|
||||
ignore_dirs=IGNORE_DIRS,
|
||||
file_callback=self.statistics_file_callback).process_folder()
|
||||
return to_json_serializable(self.torrent_name)
|
||||
@@ -0,0 +1,94 @@
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
from collections import defaultdict
|
||||
|
||||
from app.constants import IGNORE_DIRS, TORRENT_ROOT_FOLDER
|
||||
from app.services import FolderService
|
||||
|
||||
|
||||
class VideoService:
|
||||
def __init__(self, paths: list[str]):
|
||||
self.paths: list[str] = paths
|
||||
self.prefix_pattern = re.compile(r'(?i)[A-Z]+\.')
|
||||
self.torrent_root_folder = "C:\\Users\\Localhost\\Desktop\\BT"
|
||||
self.torrent_folder_depth = len(TORRENT_ROOT_FOLDER.split(os.sep))
|
||||
self.new_paths: dict[str, dict[str, list[str]]] = defaultdict(dict)
|
||||
self.new_paths_2: dict[str, list[str]] = defaultdict(dict)
|
||||
self.current_folder = ""
|
||||
self.result_list: list[str] = []
|
||||
self.func_type = None
|
||||
|
||||
def process_torrent_file(self, entry: os.DirEntry):
|
||||
name, ext = os.path.splitext(self.prefix_pattern.sub('.', entry.name))
|
||||
if name not in self.new_paths[self.current_folder]:
|
||||
self.new_paths[self.current_folder][name] = []
|
||||
self.new_paths[self.current_folder][name].append(entry.path)
|
||||
if name not in self.new_paths_2:
|
||||
self.new_paths_2[name] = []
|
||||
self.new_paths_2[name].append(entry.path)
|
||||
# if self.func_type != "remove_deduplication":
|
||||
# if ext != ".mp4":
|
||||
# self.result_list.insert(0, f"重复文件：{name} {ext}")
|
||||
# if len(self.new_paths[self.current_folder][name]) > 1:
|
||||
# print(name, ext)
|
||||
|
||||
def get_init_folder(self, entry: os.DirEntry):
|
||||
temp_path: list[str] = []
|
||||
for path in self.paths:
|
||||
if os.path.exists(path) and os.path.exists(os.path.join(path, entry.name)):
|
||||
temp_path.append(os.path.join(path, entry.name))
|
||||
self.current_folder = entry.name
|
||||
FolderService(paths=temp_path, ignore_dirs=IGNORE_DIRS,
|
||||
file_callback=self.process_torrent_file,
|
||||
empty_folder_callback=self.remove_folder).process_folder()
|
||||
if self.func_type != "remove_deduplication":
|
||||
return
|
||||
FolderService(paths=entry.path, ignore_dirs=IGNORE_DIRS,
|
||||
file_callback=self.torrent_deduplication,
|
||||
empty_folder_callback=self.remove_folder).process_folder()
|
||||
|
||||
def torrent_deduplication(self, entry: os.DirEntry):
|
||||
without_modifier_file_name = self.prefix_pattern.sub('.', entry.name)
|
||||
name, ext = os.path.splitext(without_modifier_file_name)
|
||||
if name in self.new_paths[entry.path.split(os.sep)[self.torrent_folder_depth]]:
|
||||
folder_arr = entry.path.split(os.sep)[self.torrent_folder_depth:-1]
|
||||
folder_arr.insert(0, "done")
|
||||
new_path = os.path.join(TORRENT_ROOT_FOLDER, *folder_arr)
|
||||
print(os.path.join(new_path, entry.name))
|
||||
os.makedirs(new_path, exist_ok=True)
|
||||
try:
|
||||
shutil.move(entry.path, os.path.join(new_path, entry.name))
|
||||
self.result_list.insert(0, f"移动到文件夹：{os.path.join(new_path, entry.name)}")
|
||||
except shutil.Error:
|
||||
pass
|
||||
|
||||
def remove_folder(self, entry: os.DirEntry):
|
||||
if entry.name == self.current_folder:
|
||||
return
|
||||
os.rmdir(entry.path)
|
||||
self.result_list.insert(0, f"删除文件夹：{entry.path}")
|
||||
|
||||
def deduplication(self):
|
||||
self.func_type = "remove_deduplication"
|
||||
FolderService(paths=TORRENT_ROOT_FOLDER, ignore_dirs=IGNORE_DIRS | {"done"}, max_depth=1,
|
||||
folder_callback=self.get_init_folder).process_folder()
|
||||
return self.result_list
|
||||
|
||||
def find_deduplication(self):
|
||||
self.func_type = "find_deduplication"
|
||||
FolderService(paths=TORRENT_ROOT_FOLDER, ignore_dirs=IGNORE_DIRS | {"done"}, max_depth=1,
|
||||
folder_callback=self.get_init_folder).process_folder()
|
||||
for name in self.new_paths_2:
|
||||
if len(self.new_paths_2[name]) > 1:
|
||||
temp_name = []
|
||||
for path_2 in self.new_paths_2[name]:
|
||||
name_2 = os.path.splitext(os.path.basename(path_2))[0]
|
||||
if name_2 not in temp_name:
|
||||
temp_name.append(name_2)
|
||||
else:
|
||||
self.result_list.insert(0, name_2)
|
||||
print(name_2)
|
||||
if len(temp_name)>1 and name in temp_name:
|
||||
self.result_list.insert(0, name)
|
||||
return self.result_list
|
||||
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"mod": "forumdisplay",
|
||||
"fid": "139",
|
||||
"orderby": "dateline",
|
||||
"baseUrl": "http://127.0.0.1:20000/",
|
||||
"targetDate": "2026-03-23",
|
||||
"targetCountdownPage": 998,
|
||||
"totalPage": 999,
|
||||
"privilegeLevel": 20,
|
||||
"headers": {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36",
|
||||
"cookie": "cPNj_2132_lastfp=079737cd852f396e59ea74a50e4ff9f1; cPNj_2132_saltkey=CeJLs8Ed; cPNj_2132_lastvisit=1726724743; _safe=h4uHX8t74U1uC89h; cPNj_2132_nofavfid=1; cPNj_2132_smile=1D1; cPNj_2132_secqaaqSARdM0=1286544.1fe30bcf776352790f; cPNj_2132_atarget=1; cPNj_2132__refer=%252Fhome.php%253Fmod%253Dspacecp%2526ac%253Dprofile%2526op%253Dpassword; cPNj_2132_auth=44bdzFfx4TYjBMhuKf4AZdi2JM%2BXZ0Okxd0JEl1Hmwbz%2Fr3WiX0sLmATmolWkLlRgorFz%2BULizz5o6G%2FJ3YGWYPF0xw; cPNj_2132_lastcheckfeed=508551%7C1726728824; cPNj_2132_lip=8.219.243.67%2C1726728824; cPNj_2132_secqaaqSAp9u0=1287401.84f80cf53671988988; cPNj_2132_home_diymode=1; cPNj_2132_sid=0; cPNj_2132_st_t=508551%7C1729318359%7C645e73a57f2807c1a85c994685fbe7b7; cPNj_2132_forum_lastvisit=D_151_1726729986D_36_1726732739D_95_1726751606D_103_1729304183D_139_1729318359; cPNj_2132_visitedfid=139D103D159D95D141D143D166D36D170D151; cPNj_2132_ulastactivity=1729318359%7C0; cf_clearance=wXzU4znYwA5CfAohAd3fPolFurbPcgWGacwTjhmMmQs-1729318361-1.2.1.1-YhnHHOA0XWfeDsF2TdvRrtWHzFTfFlZCf5l3u5AFdto2u16rpdDDZGgi6OkrKmJ6gw4bFgh1P1PcvBtfxw4wA3ME2BcVkNhYscsgDJ_V0Dgh91hgopC85KB4LlV2rcz_K0UL7NMyAgbhID4AC.eeLsjlPmxd_Xq8SJCDctTvfRimKb22bGEuyXA_bKL_k2X5lDLDJSXfjx3285g0X2WUQroJKymoOBHn0MBUYrnP1h_dyD7KzZYkj38J3_aiM22H_rtzKO3O2sD_fitnDRuM.BAJhdr2bYdrM_UXdJAj4IF3MY_BqlCyYHSX.AaVqOz3MyK7j7Dj_jv9PdThWwcA_kjRuK4hVmxoofcu._2tw5_EY28D2.0CDIgAbjidrIUW; cPNj_2132_st_p=508551%7C1729318366%7Cf7f4e3654f2de21700cdd0472289b3e2; cPNj_2132_viewid=tid_2380153; cPNj_2132_lastact=1729318373%09forum.php%09attachment"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,106 @@
|
||||
import json
|
||||
import time
|
||||
import ctypes
|
||||
from collections import defaultdict
|
||||
from typing import List
|
||||
from datetime import datetime
|
||||
from functools import cmp_to_key
|
||||
|
||||
|
||||
|
||||
def windows_sort_unicode(items: List[str]) -> List[str]:
|
||||
"""
|
||||
使用Windows API实现字符串列表的排序。
|
||||
|
||||
该函数通过调用Windows的Shlwapi.dll库中的StrCmpLogicalW函数进行字符串的比较，以实现自然排序。
|
||||
自然排序是指在排序数字和字母组合的字符串时，数字按照数值来比较，而不是按照字符的ASCII值来比较。
|
||||
|
||||
:param items: List[str] - 需要排序的字符串列表。
|
||||
:return: List[str] - 排序后的字符串列表。
|
||||
"""
|
||||
shlwapi = ctypes.windll.LoadLibrary('Shlwapi.dll')
|
||||
StrCmpLogicalW = shlwapi.StrCmpLogicalW
|
||||
StrCmpLogicalW.argtypes = [ctypes.c_wchar_p, ctypes.c_wchar_p]
|
||||
StrCmpLogicalW.restype = ctypes.c_int
|
||||
|
||||
def compare(a: str, b: str) -> int:
|
||||
"""
|
||||
比较两个字符串的函数，用于在排序时调用。
|
||||
|
||||
:param a: str - 第一个字符串。
|
||||
:param b: str - 第二个字符串。
|
||||
:return: int - StrCmpLogicalW函数的返回值，表示两个字符串的比较结果。
|
||||
"""
|
||||
return StrCmpLogicalW(str(a), str(b))
|
||||
|
||||
return sorted(items, key=cmp_to_key(compare))
|
||||
|
||||
|
||||
def read_json_file(json_path): # 读取json文件
|
||||
with open(json_path, 'r', encoding='utf-8') as file:
|
||||
data = json.load(file)
|
||||
return data
|
||||
|
||||
|
||||
def write_json_file(json_path, data): # 写入json文件
|
||||
with open(json_path, 'w') as file:
|
||||
json.dump(data, file, sort_keys=False, indent=4)
|
||||
|
||||
|
||||
def datetime_to_timestamp(date) -> int:
|
||||
"""
|
||||
日期转时间戳
|
||||
:param date: 需要转换的日期
|
||||
:return:
|
||||
"""
|
||||
return int(datetime.strptime(date, "%Y-%m-%d").timestamp())
|
||||
|
||||
|
||||
def timestamp_to_datetime(timestamp):
|
||||
"""
|
||||
时间戳转日期
|
||||
:param timestamp: 需要转换的时间戳
|
||||
:return:
|
||||
"""
|
||||
return datetime.fromtimestamp(timestamp).strftime("%Y-%m-%d")
|
||||
|
||||
|
||||
def get_today_timestamp():
|
||||
"""
|
||||
获取今日时间戳
|
||||
:return:
|
||||
"""
|
||||
return datetime_to_timestamp(datetime.now().strftime("%Y-%m-%d"))
|
||||
|
||||
|
||||
def show_delay_progress(delay_time: float) -> None:
|
||||
"""在控制台显示延迟进度条"""
|
||||
total_blocks = 30 # 进度条总长度
|
||||
start_time = time.time()
|
||||
end_time = start_time + delay_time
|
||||
|
||||
print(f"\n等待 {delay_time:.1f} 秒... [{' ' * total_blocks}]", end='', flush=True)
|
||||
|
||||
while time.time() < end_time:
|
||||
elapsed = time.time() - start_time
|
||||
progress = min(1.0, elapsed / delay_time)
|
||||
filled = int(progress * total_blocks)
|
||||
remaining = end_time - time.time()
|
||||
|
||||
print(f"\r等待 {delay_time:.1f} 秒... [{'=' * filled}>{' ' * (total_blocks - filled - 1)}]"
|
||||
f" 剩余: {remaining:.1f}s", end='', flush=True)
|
||||
time.sleep(0.1)
|
||||
|
||||
print("\r" + " " * 80 + "\r", end='', flush=True) # 清空进度行
|
||||
|
||||
def to_json_serializable(obj):
|
||||
"""递归将 defaultdict 和 set 转换为 JSON 可序列化的类型"""
|
||||
if isinstance(obj, defaultdict):
|
||||
# 转为普通字典，并递归处理每个值
|
||||
obj = dict(obj)
|
||||
if isinstance(obj, dict):
|
||||
return {k: to_json_serializable(v) for k, v in obj.items()}
|
||||
if isinstance(obj, set):
|
||||
return list(obj) # 集合转列表
|
||||
# 其他基本类型（str, int, float, list, tuple, None）直接返回
|
||||
return obj
|
||||
Reference in New Issue
Block a user