def download(self,
file_url: str,
goal_path: str = None,
rename: str = None,
file_exists: str = 'rename',
show_msg: bool = False,
**kwargs) -> tuple:
"""下载一个文件 \n
:param file_url: 文件url
:param goal_path: 存放路径
:param rename: 重命名文件，可不写扩展名
:param file_exists: 若存在同名文件，可选择 'rename', 'overwrite', 'skip' 方式处理
:param show_msg: 是否显示下载信息
:param kwargs: 连接参数
:return: 下载是否成功（bool）和状态信息（成功时信息为文件路径）的元组
"""
# 生成的response不写入self._response，是临时的
goal_path = goal_path or OptionsManager().get_value(
'paths', 'global_tmp_path')
if not goal_path:
raise IOError('No path specified.')
kwargs['stream'] = True
if 'timeout' not in kwargs:
kwargs['timeout'] = 20
r, info = self._make_response(file_url, mode='get', **kwargs)
if not r:
if show_msg:
print(info)
return False, info
# -------------------获取文件名-------------------
# header里有文件名，则使用它，否则在url里截取，但不能保证url包含文件名
if 'Content-disposition' in r.headers:
file_name = r.headers['Content-disposition'].split('"')[1].encode(
'ISO-8859-1').decode('utf-8')
elif os_PATH.basename(file_url):
file_name = os_PATH.basename(file_url).split("?")[0]
else:
file_name = f'untitled_{time()}_{randint(0, 100)}'
file_name = re_SUB(r'[\\/*:|<>?"]', '', file_name).strip()
if rename: # 重命名文件，不改变扩展名
rename = re_SUB(r'[\\/*:|<>?"]', '', rename).strip()
ext_name = file_name.split('.')[-1]
if rename.lower().endswith(
f'.{ext_name}'.lower()) or ext_name == file_name:
full_name = rename
else:
full_name = f'{rename}.{ext_name}'
else:
full_name = file_name
goal_Path = Path(goal_path)
goal_path = ''
for key, i in enumerate(goal_Path.parts): # 去除路径中的非法字符
goal_path += goal_Path.drive if key == 0 and goal_Path.drive else re_SUB(
r'[*:|<>?"]', '', i).strip()
goal_path += '\\' if i != '\\' and key < len(
goal_Path.parts) - 1 else ''
goal_Path = Path(goal_path)
goal_Path.mkdir(parents=True, exist_ok=True)
goal_path = goal_Path.absolute()
full_path = Path(f'{goal_path}\\{full_name}')
if full_path.exists():
if file_exists == 'skip':
return False, 'A file with the same name already exists.'
elif file_exists == 'overwrite':
pass
elif file_exists == 'rename':
full_name = get_available_file_name(goal_path, full_name)
full_path = Path(f'{goal_path}\\{full_name}')
else:
raise ValueError(
"Argument file_exists can only be 'skip', 'overwrite', 'rename'."
)
if show_msg: # 打印要下载的文件
print(full_name if file_name ==
full_name else f'{file_name} -> {full_name}')
print(f'Downloading to: {goal_path}')
# -------------------开始下载-------------------
# 获取远程文件大小
file_size = int(r.headers['Content-Length']
) if 'Content-Length' in r.headers else None
downloaded_size, download_status = 0, False # 已下载文件大小和下载状态
try:
with open(str(full_path), 'wb') as tmpFile:
for chunk in r.iter_content(chunk_size=1024):
if chunk:
tmpFile.write(chunk)
if show_msg and file_size: # 如表头有返回文件大小，显示进度
downloaded_size += 1024
rate = downloaded_size / file_size if downloaded_size < file_size else 1
print('\r {:.0%} '.format(rate), end="")
except Exception as e:
download_status, info = False, f'Download failed.\n{e}'
else:
download_status, info = (
False,
'File size is 0.') if full_path.stat().st_size == 0 else (
True, 'Success.')
finally:
# 删除下载出错文件
if not download_status and full_path.exists():
full_path.unlink()
r.close()
# -------------------显示并返回值-------------------
if show_msg:
print(info)
info = f'{goal_path}\\{full_name}' if download_status else info
return download_status, info
def download(self,
file_url: str,
goal_path: str = None,
rename: str = None,
file_exists: str = 'rename',
post_data: dict = None,
show_msg: bool = False,
show_errmsg: bool = False,
**kwargs) -> tuple:
"""下载一个文件 \n
:param file_url: 文件url
:param goal_path: 存放路径
:param rename: 重命名文件，可不写扩展名
:param file_exists: 若存在同名文件，可选择 'rename', 'overwrite', 'skip' 方式处理
:param show_msg: 是否显示下载信息
:param show_errmsg: 是否抛出和显示异常
:param kwargs: 连接参数
:return: 下载是否成功（bool）和状态信息（成功时信息为文件路径）的元组
"""
# 生成的response不写入self._response，是临时的
goal_path = goal_path or OptionsManager().get_value(
'paths', 'global_tmp_path')
if not goal_path:
raise IOError('No path specified.')
kwargs['stream'] = True
if 'timeout' not in kwargs:
kwargs['timeout'] = 20
if not post_data:
r, info = self._make_response(file_url,
mode='get',
show_errmsg=show_errmsg,
**kwargs)
else:
r, info = self._make_response(file_url,
mode='post',
data=post_data,
show_errmsg=show_errmsg,
**kwargs)
if r is None:
if show_msg:
print(info)
return False, info
if not r.ok:
if show_errmsg:
raise ConnectionError(f'Status code: {r.status_code}.')
return False, f'Status code: {r.status_code}.'
# -------------------获取文件名-------------------
file_name = ''
content_disposition = tuple(x for x in r.headers
if x.lower() == 'content-disposition')
if content_disposition: # header里有文件名，则使用它
file_name = r.headers[content_disposition[0]].encode(
'ISO-8859-1').decode('utf-8')
file_name = re.search(r'filename *= *"?([^";]+)', file_name)
if file_name:
file_name = file_name.group(1)
if file_name[0] == file_name[-1] == "'":
file_name = file_name.strip("'")
if not file_name and os_PATH.basename(file_url): # 在url里获取文件名
file_name = os_PATH.basename(file_url).split("?")[0]
if not file_name: # 找不到则用时间和随机数生成文件名
file_name = f'untitled_{time()}_{randint(0, 100)}'
file_name = re_SUB(r'[\\/*:|<>?"]', '', file_name).strip() # 去除非法字符
file_name = parse.unquote(file_name)
# -------------------重命名文件名-------------------
if rename: # 重命名文件，不改变扩展名
rename = re_SUB(r'[\\/*:|<>?"]', '', rename).strip()
ext_name = file_name.split('.')[-1]
if '.' in rename or ext_name == file_name:
full_name = rename
else:
full_name = f'{rename}.{ext_name}'
else:
full_name = file_name
# -------------------生成路径-------------------
goal_Path = Path(goal_path)
goal_path = ''
for key, i in enumerate(goal_Path.parts): # 去除路径中的非法字符
goal_path += goal_Path.drive if key == 0 and goal_Path.drive else re_SUB(
r'[*:|<>?"]', '', i).strip()
goal_path += '\\' if i != '\\' and key < len(
goal_Path.parts) - 1 else ''
goal_Path = Path(goal_path)
goal_Path.mkdir(parents=True, exist_ok=True)
goal_path = goal_Path.absolute()
full_path = Path(f'{goal_path}\\{full_name}')
if full_path.exists():
if file_exists == 'skip':
return False, 'A file with the same name already exists.'
elif file_exists == 'overwrite':
pass
elif file_exists == 'rename':
full_name = get_available_file_name(goal_path, full_name)
full_path = Path(f'{goal_path}\\{full_name}')
else:
raise ValueError(
"Argument file_exists can only be 'skip', 'overwrite', 'rename'."
)
# -------------------打印要下载的文件-------------------
if show_msg:
print(full_name if file_name ==
full_name else f'{file_name} -> {full_name}')
print(f'Downloading to: {goal_path}')
# -------------------开始下载-------------------
# 获取远程文件大小
content_length = tuple(x for x in r.headers
if x.lower() == 'content-length')
file_size = int(r.headers[content_length]) if content_length else None
downloaded_size, download_status = 0, False # 已下载文件大小和下载状态
try:
with open(str(full_path), 'wb') as tmpFile:
for chunk in r.iter_content(chunk_size=1024):
if chunk:
tmpFile.write(chunk)
if show_msg and file_size: # 如表头有返回文件大小，显示进度
downloaded_size += 1024
rate = downloaded_size / file_size if downloaded_size < file_size else 1
print('\r {:.0%} '.format(rate), end="")
except Exception as e:
if show_errmsg:
raise ConnectionError(e)
download_status, info = False, f'Download failed.\n{e}'
else:
if full_path.stat().st_size == 0:
if show_errmsg:
raise ValueError('File size is 0.')
download_status, info = False, 'File size is 0.'
else:
download_status, info = True, 'Success.'
finally:
if not download_status and full_path.exists():
full_path.unlink() # 删除下载出错文件
r.close()
# -------------------显示并返回值-------------------
if show_msg:
print(info)
info = f'{goal_path}\\{full_name}' if download_status else info
return download_status, info
def do(url: str,
goal: str,
new_name: str = None,
exists: str = 'rename',
data: dict = None,
msg: bool = False,
errmsg: bool = False,
**args) -> tuple:
args['stream'] = True
if 'timeout' not in args:
args['timeout'] = 20
mode = 'post' if data else 'get'
# 生成的response不写入self._response，是临时的
r, info = self._make_response(url,
mode=mode,
data=data,
show_errmsg=errmsg,
**args)
if r is None:
if msg:
print(info)
return False, info
if not r.ok:
if errmsg:
raise ConnectionError(f'Status code: {r.status_code}.')
return False, f'Status code: {r.status_code}.'
# -------------------获取文件名-------------------
file_name = ''
content_disposition = r.headers.get('content-disposition')
# 使用header里的文件名
if content_disposition:
file_name = r.headers[content_disposition[0]].encode(
'ISO-8859-1').decode('utf-8')
file_name = re.search(r'filename *= *"?([^";]+)', file_name)
if file_name:
file_name = file_name.group(1)
if file_name[0] == file_name[-1] == "'":
file_name = file_name[1:-1]
# 在url里获取文件名
if not file_name and os_PATH.basename(url):
file_name = os_PATH.basename(url).split("?")[0]
# 找不到则用时间和随机数生成文件名
if not file_name:
file_name = f'untitled_{time()}_{randint(0, 100)}'
# 去除非法字符
file_name = re_SUB(r'[\\/*:|<>?"]', '', file_name).strip()
file_name = unquote(file_name)
# -------------------重命名，不改变扩展名-------------------
if new_name:
new_name = re_SUB(r'[\\/*:|<>?"]', '', new_name).strip()
ext_name = file_name.split('.')[-1]
if '.' in new_name or ext_name == file_name:
full_name = new_name
else:
full_name = f'{new_name}.{ext_name}'
else:
full_name = file_name
# -------------------生成路径-------------------
goal_Path = Path(goal)
goal = ''
skip = False
for key, i in enumerate(goal_Path.parts): # 去除路径中的非法字符
goal += goal_Path.drive if key == 0 and goal_Path.drive else re_SUB(
r'[*:|<>?"]', '', i).strip()
goal += '\\' if i != '\\' and key < len(
goal_Path.parts) - 1 else ''
goal_Path = Path(goal).absolute()
goal_Path.mkdir(parents=True, exist_ok=True)
full_path = Path(f'{goal}\\{full_name}')
if full_path.exists():
if file_exists == 'rename':
full_name = get_available_file_name(goal, full_name)
full_path = Path(f'{goal}\\{full_name}')
elif exists == 'skip':
skip = True
elif exists == 'overwrite':
pass
else:
raise ValueError(
"Argument file_exists can only be 'skip', 'overwrite', 'rename'."
)
# -------------------打印要下载的文件-------------------
if msg:
print(file_url)
print(full_name if file_name ==
full_name else f'{file_name} -> {full_name}')
print(f'Downloading to: {goal}')
if skip:
print('Skipped.\n')
# -------------------开始下载-------------------
if skip:
return False, 'Skipped because a file with the same name already exists.'
# 获取远程文件大小
content_length = r.headers.get('content-length')
file_size = int(content_length) if content_length else None
# 已下载文件大小和下载状态
downloaded_size, download_status = 0, False
try:
with open(str(full_path), 'wb') as tmpFile:
for chunk in r.iter_content(chunk_size=1024):
if chunk:
tmpFile.write(chunk)
# 如表头有返回文件大小，显示进度
if msg and file_size:
downloaded_size += 1024
rate = downloaded_size / file_size if downloaded_size < file_size else 1
print('\r {:.0%} '.format(rate), end="")
except Exception as e:
if errmsg:
raise ConnectionError(e)
download_status, info = False, f'Download failed.\n{e}'
else:
if full_path.stat().st_size == 0:
if errmsg:
raise ValueError('File size is 0.')
download_status, info = False, 'File size is 0.'
else:
download_status, info = True, str(full_path)
finally:
# 删除下载出错文件
if not download_status and full_path.exists():
full_path.unlink()
r.close()
# -------------------显示并返回值-------------------
if msg:
print(info, '\n')
info = f'{goal}\\{full_name}' if download_status else info
return download_status, info
