-
-
Save webstyle/3c1e1b464f32139a65fa16b2f745162e to your computer and use it in GitHub Desktop.
Converting DOCX to PDF using Python
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import subprocess | |
import re | |
def convert_to(folder, source, timeout=None): | |
args = [libreoffice_exec(), '--headless', '--convert-to', 'pdf', '--outdir', folder, source] | |
process = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, timeout=timeout) | |
filename = re.search('-> (.*?) using filter', process.stdout.decode()) | |
if filename is None: | |
raise LibreOfficeError(process.stdout.decode()) | |
else: | |
return filename.group(1) | |
def libreoffice_exec(): | |
# TODO: Provide support for more platforms | |
if sys.platform == 'darwin': | |
return '/Applications/LibreOffice.app/Contents/MacOS/soffice' | |
return 'libreoffice' | |
class LibreOfficeError(Exception): | |
def __init__(self, output): | |
self.output = output | |
if __name__ == '__main__': | |
print('Converted to ' + convert_to(sys.argv[1], sys.argv[2])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment