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 +1,7 @@
|
||||
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
|
||||
Reference in New Issue
Block a user