def un_pack(compressed_files_path):
try:
file_name = os.path.basename(compressed_files_path)
file_info = file_name.rsplit(".", 1)
name = file_info[0]
suffix = file_info[1]
# 拼接文件解压路径
uncompress_dir = os.path.join(
os.path.dirname(compressed_files_path), name)
if not os.path.exists(uncompress_dir):
os.makedirs(uncompress_dir)
else:
shutil.rmtree(uncompress_dir)
os.makedirs(uncompress_dir)
# 根据文件类型做解压操作
if suffix in ["rar"]:
# RarFile(compressed_files_path).extractall(uncompress_dir)
os.system(
f"unrar x -o- -y {compressed_files_path} {uncompress_dir}")
elif suffix in ["zip", "Zip"]:
shutil.unpack_archive(compressed_files_path, uncompress_dir,
suffix)
os.remove(compressed_files_path)
return uncompress_dir
except Exception as e:
logger.exception(e)
return None
def del_file(dir_path):
try:
for file in os.listdir(dir_path):
if file.startswith("."):
os.remove(file)
except Exception as e:
logger.exception(e)
def _word_to_pdf_batch(dir_path, transform=None, delete=True):
if transform is None:
transform = ["doc", "docx"]
try:
if dir_path and os.path.exists(dir_path) and transform:
for file_type in transform:
if os.system(
f"soffice --headless -convert-to pdf {dir_path}/*.{file_type} --outdir {dir_path}"
) in [0, "0"] and delete:
try:
os.system(rf"rm -f {dir_path}/*.{file_type}")
logger.info(f"rm -f {dir_path}/*.{file_type}")
except Exception as e:
logger.exception(e)
except Exception as e:
logger.exception(e)
def recursion_decompressing(self, files_path):
"""
对传入对文件夹遍历判断需要再次解压的文件，进行解压处理
Args:
files_path: 上一层解压后文件集中路径
Returns:
"""
try:
if files_path and os.path.exists(files_path):
for file in os.listdir(files_path):
if file.rsplit(".", 1)[-1] in [
"rar", "zip"
] and not file.startswith("."):
abs_file_path = os.path.join(files_path, file)
self.uncompress(abs_file_path)
except Exception as e:
logger.exception(e)
def get_message(self, key, func):
try:
index = 0
while True:
message = cache.rpop(key)
if message:
logger.info(f"{key}, message{message}")
# message = deserialization(self.__cls__().Default, message, url="default")
merge_process = Thread(target=func, args=(eval(message), ))
merge_process.start()
index = 0
else:
if index >= self.timeout:
exit()
index += 1
# logger.info(f"{key}: {index}")
time.sleep(1)
except Exception as e:
logger.exception(e)
def check_libre_office_status():
"""
检查系统是否安装了libreoffice，没有安装的话，进行软件的安装
Returns:
"""
try:
office_info = os.system("libreoffice --version")
logger.info(f"{office_info}")
if office_info not in [0, "0"]:
logger.info(f"系统内部没有安装")
logger.info(f"start install libreoffice")
if os.system("yum install -y libreoffice") in [0, "0"]:
logger.info(f"安装成功")
else:
logger.info(f"安装失败")
else:
logger.info(f"系统已安装")
except Exception as e:
logger.exception(e)
def start(self):
try:
self.push_item_in_redis_list(self.message_a, self.start_item)
thr_downloader = Thread(target=self.get_message, args=(self.message_a, self.download_page))
thr_primary = Thread(target=self.get_message, args=(self.message_b, self.primary))
thr_merge_result = Thread(target=self.get_message, args=(self.message_c, self.merger_result))
thr_downloader.start()
logger.info("下载线程开启！")
time.sleep(3)
thr_primary.start()
logger.info("抽取线程开启！")
thr_merge_result.start()
logger.info("数据合并线程开启")
thr_merge_result.join()
return self.result
except Exception as identifier:
logger.exception(identifier)
def word_to_pdf_single(word_path: str, dir_path, delete=True):
"""
ubuntu中使用命令行将doc、docx文件转换为pdf，并根据状态是否删除源文件
Args:
word_path: doc、docx文件路径
dir_path: 转换后文件保存位置
delete: 是否删除，默认删除
Returns:
"""
try:
if word_path and os.path.exists(word_path):
try:
status = os.system(
f"soffice --headless -convert-to pdf {word_path} --outdir {dir_path}"
)
if status in [0, "0"] and delete:
try:
os.remove(word_path)
logger.info(f"rm {word_path}")
except Exception as e:
logger.exception(e)
except Exception as e:
logger.exception(e)
except Exception as e:
logger.exception(e)
def word_to_pdf_batch(self, dir_path):
"""
文件夹内的word文件批量转换为PDF，
主要使用的是word中插入的图片，对文本没有要求
Args:
dir_path: 需要处理的文件夹
Returns:
"""
if dir_path:
try:
all_word_files = []
for root, dirs, files in os.walk(dir_path):
[
self.word_to_pdf_single(os.path.join(root, x),
dir_path) for x in files
if x.rsplit(".", 1)[-1] in ['doc', "docx"]
and not x.startswith(".")
]
logger.info(all_word_files)
except Exception as e:
logger.exception(e)