def extract_rar(rar: rarfile.RarFile,
rar_entry: rarfile.RarInfo,
tmp_dir_name,
passwd=None):
"""
Extract rar entry from archive using unrar module,
also realise smart behaviour - apply a list of predefined passwords to encrypted rar entry
if passwd param is not set. Look at DEFAULT_ARC_PASSWORDS in configuration.
:param rar: unrar.rarfile.RarFile instance
:param rar_entry: unrar.rarfile.RarInfo instance
:param tmp_dir_name: path to tmp dir (string)
:param passwd: password string
:return: Nothing
"""
try:
rar.extract(rar_entry.filename, tmp_dir_name, pwd=passwd)
log.debug(
f"===>Extracted:{rar_entry.filename} to {tmp_dir_name} without pwd"
)
return
except (rarfile.BadRarFile,
RuntimeError) as err: # Only if no password given
log.debug(
f"===>Can't extract:{rar_entry.filename} to {tmp_dir_name} without pwd: {str(err)}"
)
if str(err).startswith('Bad header data') or \
str(err).startswith('File is encrypted'): # may be file is encrypted
for passwd in cfg.DEFAULT_ARC_PASSWORDS: # TODO - store passwords encrypted in db
try:
rar.extract(rar_entry.filename, tmp_dir_name, pwd=passwd)
log.debug(
f"===>Extracted:{rar_entry.filename} to {tmp_dir_name} with pwd"
)
return
except (rarfile.BadRarFile, RuntimeError) as e: # Bad password
log.debug(
f"===>Can't extract:{rar_entry.filename} to {tmp_dir_name} with pwd: {str(e)}"
)
continue
raise err
class PackFile:
def __init__(self, file, mode=None):
"""
:param file: 要处理的文件
:param mode: 要处理的格式，不输入会有一套智能匹配算法
'rar'：
'zip'： docx后缀的，默认采用zip格式解压
"""
# 1、确定压缩格式
name, ext = os.path.splitext(file)
ext = ext.lower()
if not mode:
if ext in ('.docx', '.zip'):
mode = 'zip'
elif ext == '.rar':
mode = 'rar'
else:
dprint(ext) # 从文件扩展名无法得知压缩格式
raise ValueError
self.mode = mode
# 2、确定是用的解压“引擎”
if mode == 'zip':
self.proc = zipfile.ZipFile(file)
elif mode == 'rar':
try:
from unrar.rarfile import RarFile
except ModuleNotFoundError:
dprint(
) # 缺少unrar模块，安装详见： https://blog.csdn.net/code4101/article/details/79328636
raise ModuleNotFoundError
self.proc = RarFile(file)
# 3、解压文件夹目录，None表示还未解压
self.tempfolder = None
def open(self, member, pwd=None):
"""Return file-like object for 'member'.
'member' may be a filename or a RarInfo object.
"""
return self.proc.open(member, pwd)
def read(self, member, pwd=None):
"""Return file bytes (as a string) for name."""
return self.proc.read(member, pwd)
def namelist(self):
""">> self.namelist() # 获得文件清单列表
1 [Content_Types].xml
2 _rels/.rels
......
20 word/fontTable.xml
21 docProps/app.xml
"""
return self.proc.namelist()
def setpassword(self, pwd):
"""Set default password for encrypted files."""
return self.proc.setpassword(pwd)
def getinfo(self, name):
"""
>> self.getinfo('word/document.xml') # 获得某个文件的信息
<ZipInfo filename='word/document.xml' compress_type=deflate file_size=140518 compress_size=10004>
"""
return self.proc.getinfo(name)
def infolist(self, prefix=None, zipinfo=True):
""">> self.infolist() # getinfo的多文件版本
1 <ZipInfo filename='[Content_Types].xml' compress_type=deflate file_size=1495 compress_size=383>
2 <ZipInfo filename='_rels/.rels' compress_type=deflate file_size=590 compress_size=243>
......
20 <ZipInfo filename='word/fontTable.xml' compress_type=deflate file_size=1590 compress_size=521>
21 <ZipInfo filename='docProps/app.xml' compress_type=deflate file_size=720 compress_size=384>
:param prefix:
可以筛选文件的前缀，例如“word/”可以筛选出word目录下的
:param zipinfo:
返回的list每个元素是zipinfo数据类型
"""
ls = self.proc.infolist()
if prefix:
ls = list(filter(lambda t: t.filename.startswith(prefix), ls))
if not zipinfo:
ls = list(map(lambda x: x.filename, ls))
return ls
def printdir(self):
"""Print a table of contents for the RAR file."""
return self.proc.printdir()
def testrar(self):
"""Read all the files and check the CRC."""
return self.proc.testrar()
def extract(self, member, path=None, pwd=None):
"""注意，如果写extract('word/document.xml', 'a')，那么提取出来的文件是在'a/word/document.xml'
"""
return self.proc.extract(member, path, pwd)
def extractall(self, path=None, members=None, pwd=None):
"""Extract all members from the archive to the current working
directory. `path' specifies a different directory to extract to.
`members' is optional and must be a subset of the list returned
by namelist().
"""
return self.proc.extractall(path, members, pwd)
def extractall2tempfolder(self):
"""将文件解压到一个临时文件夹，并返回临时文件夹目录"""
if not self.tempfolder:
self.tempfolder = tempfile.mkdtemp()
self.proc.extractall(path=self.tempfolder)
return self.tempfolder
def clear_tempfolder(self):
"""删除创建的临时文件夹内容"""
filesdel(self.tempfolder)
def __enter__(self):
"""使用with ... as ...语法能自动建立解压目录和删除
注意：这里返回的不是PackFile对象，而是解压后的目录
"""
path = self.extractall2tempfolder()
return path
def __exit__(self, exc_type, exc_val, exc_tb):
self.clear_tempfolder()
