def convert_pdf_to_docx_with_abiword(input_path, out_path):
run_with_timeout(["abiword", '--to=docx', input_path])
filename_wo_extenstion, _ = os.path.splitext(input_path)
temp_outfile = filename_wo_extenstion + ".docx"
if not os.path.exists(temp_outfile):
return 1
shutil.move(temp_outfile, out_path)
def convert_to_html_with_soffice(self, inp):
run_with_timeout(
[self.soffice, '--headless', '--convert-to', 'html', inp])
filename_wo_extenstion, _ = os.path.splitext(inp)
temp_outfile = filename_wo_extenstion + ".html"
if not os.path.exists(temp_outfile):
return None
with open(temp_outfile, encoding="utf8") as inp:
html = inp.read()
os.unlink(temp_outfile)
return html
def convert_to_pdf(self, inp, out):
if os.path.exists(out):
os.unlink(out)
run_with_timeout([
self.soffice, '--headless', '--writer', '--convert-to', 'pdf', inp
])
filename_wo_extenstion, _ = os.path.splitext(inp)
temp_outfile = os.path.basename(filename_wo_extenstion + ".pdf")
if not os.path.exists(temp_outfile):
return 1
shutil.move(temp_outfile, out)
def run_soffice(self, inp, out):
run_with_timeout([
self.soffice, '--headless', '--writer', '--convert-to',
'txt:Text (encoded):UTF8', inp
])
filename_wo_extenstion, _ = os.path.splitext(inp)
temp_outfile = filename_wo_extenstion + ".txt"
if not os.path.exists(temp_outfile):
return 1
shutil.move(temp_outfile, out)
return 0
def run_calibre(self, inp, out):
return run_with_timeout([self.calibre, inp, out])