def get_dir_list(self, folder_id=-1) -> FolderList:
"""获取子文件夹列表"""
folder_list = FolderList()
para = {
'item': 'files',
'action': 'index',
'folder_node': 1,
'folder_id': folder_id
}
html = self._get(self._mydisk_url, params=para)
if not html:
return folder_list
info = re.findall(
r' (.+?)</a> .+"folk(\d+)"(.*?)>.+#BBBBBB">\[?(.*?)\.*\]?</font>',
html.text)
for folder_name, fid, pwd_flag, desc in info:
folder_list.append(
Folder(
id=int(fid),
name=folder_name.replace('&', '&'), # 修复网页中的 & 为 &
has_pwd=True if pwd_flag else
False, # 有密码时 pwd_flag 值为 style="display:initial"
desc=desc # 文件夹描述信息
))
return folder_list
def get_rec_dir_list(self) -> FolderList:
"""获取回收站文件夹列表"""
# 回收站中文件(夹)名只能显示前 17 个中文字符或者 34 个英文字符，如果这些字符相同，则在文件(夹)名后添加 (序号) ，以便区分
html = self._get(self._mydisk_url,
params={
'item': 'recycle',
'action': 'files'
})
if not html:
return FolderList()
dirs = re.findall(
r'folder_id=(\d+).+?> (.+?)\.{0,3}</a>.*\n+.*<td.+?>(.+?)</td>.*\n.*<td.+?>(.+?)</td>',
html.text)
all_dir_list = FolderList() # 文件夹信息列表
dir_name_list = [] # 文件夹名列表d
counter = 1 # 重复计数器
for fid, name, size, time in dirs:
if name in dir_name_list: # 文件夹名前 17 个中文或 34 个英文重复
counter += 1
name = f'{name}({counter})'
else:
counter = 1
dir_name_list.append(name)
all_dir_list.append(RecFolder(name, int(fid), size, time, None))
return all_dir_list
def get_move_folders(self) -> FolderList:
"""获取全部文件夹 id-name 列表，用于移动文件至新的文件夹"""
# 这里 file_id 可以为任意值,不会对结果产生影响
result = FolderList()
result.append(FolderId(name='LanZouCloud', id=-1))
resp = self._post(self._doupload_url, data={"task": 19, "file_id": -1})
if not resp or resp.json()['zt'] != 1: # 获取失败或者网络异常
return result
for folder in resp.json()['info']:
folder_id, folder_name = int(folder['folder_id']), folder['folder_name']
result.append(FolderId(folder_name, folder_id))
return result
def get_move_paths(self) -> List[FolderList]:
"""获取所有文件夹的绝对路径(耗时长)"""
result = []
root = FolderList()
root.append(FolderId('LanZouCloud', -1))
result.append(root)
resp = self._post(self._doupload_url, data={"task": 19, "file_id": -1})
if not resp or resp.json()['zt'] != 1: # 获取失败或者网络异常
return result
ex = ThreadPoolExecutor() # 线程数 min(32, os.cpu_count() + 4)
id_list = [int(folder['folder_id']) for folder in resp.json()['info']]
task_list = [ex.submit(self.get_full_path, fid) for fid in id_list]
for task in as_completed(task_list):
result.append(task.result())
return sorted(result)
def get_rec_all(self):
"""获取整理后回收站的所有信息"""
root_files = self.get_rec_file_list() # 回收站根目录文件列表
folder_list = FolderList() # 保存整理后的文件夹列表
for folder in self.get_rec_dir_list(): # 遍历所有子文件夹
this_folder = RecFolder(folder.name, folder.id, folder.size, folder.time, FileList())
for file in self.get_rec_file_list(folder.id): # 文件夹内的文件属性: name,id,type,size
if root_files.find_by_id(file.id): # 根目录存在同名文件
file_time = root_files.pop_by_id(file.id).time # 从根目录删除, time 信息用来补充文件夹中的文件
file = file._replace(time=file_time) # 不能直接更新 namedtuple, 需要 _replace
this_folder.files.append(file)
else: # 根目录没有同名文件(用户手动删了),文件还在文件夹中，只是根目录不显示，time 信息无法补全了
file = file._replace(time=folder.time) # 那就设置时间为文件夹的创建时间
this_folder.files.append(file)
folder_list.append(this_folder)
return root_files, folder_list
def get_full_path(self, folder_id=-1) -> FolderList:
"""获取文件夹完整路径"""
path_list = FolderList()
path_list.append(FolderId('LanZouCloud', -1))
html = self._get(self._mydisk_url, params={'item': 'files', 'action': 'index', 'folder_id': folder_id})
if not html:
return path_list
html = remove_notes(html.text)
path = re.findall(r'» .+?folder_id=(\d+)">.+? (.+?)</a>', html)
for fid, name in path:
path_list.append(FolderId(name, int(fid)))
# 获取当前文件夹名称
if folder_id != -1:
current_folder = re.search(r'align="(top|absmiddle)" /> (.+?)\s<(span|font)', html).group(2).replace(
'&', '&')
path_list.append(FolderId(current_folder, folder_id))
return path_list