Reparieren Sie beschädigte Word-Dateien mit Win32com-Python ⇐ Python

[Anonymous]

Ich versuche, DOCX -Dateien mit dem folgenden Code in PDF zu konvertieren: < /p>

Code: Select all

import os
import time
import datetime
import win32com.client
import traceback
import zoneinfo
import gc

def dlt():
tz_at = zoneinfo.ZoneInfo('UTC')
datetime_at = datetime.datetime.now(tz_at)
return datetime_at.strftime("%Y-%m-%d %H:%M:%S")

def convert(word, in_file, out_file):
in_path = os.path.abspath(in_file)
out_path = os.path.abspath(out_file)
doc = None
try:
print('[{}] Start convert {}'.format(dlt(), in_path))
doc = word.Documents.Open(in_path, OpenAndRepair=True,ReadOnly=False)
doc.SaveAs(out_path, FileFormat=17)
print('[{}] Convert {} Done!'.format(dlt(), out_path))
except Exception as e:
traceback.print_exc()
finally:
if doc is not None:
try:
doc.Close()
doc = None
gc.collect()
except:
print('Failed to close doc {}'.format(out_path))

def get_word_object():
try:
w = win32com.client.GetActiveObject("Word.Application")
print("Running Word instance found, returning object")
except:
w = win32com.client.Dispatch('Word.Application')
print("No running Word instances, returning new instance")
return w

def loop():
while True:
w = get_word_object()
for f in os.listdir():
if not f.startswith('~$') and f.endswith('.docx'):
o = f.replace('.docx', '.pdf')
if not os.path.isfile(o):
convert(w, f, o)
time.sleep(1)

if __name__ == '__main__':
loop()
< /code>
Und es funktioniert gut, aber nicht für beschädigte Dateien! Tun?doc = word.Documents.Open(in_path, OpenAndRepair=True,ReadOnly=False)