Scenario: you have 100’s of pdf files which needs to be converted to .docx format
Tools required :
Python
Packages : pip install pdf2docx
Keep all pdf files in src folders
create a dest folder and all converted docx files will appear here
Python Code:
from pdf2docx import Converter
import os
# Specifying the pdf & docx files
def allfiles():
p = os.listdir('src')
for m in p:
pdf_file = m
docx_file = m.replace(".pdf",".docx")
condoc('src/'+pdf_file, 'dest/'+docx_file)
def condoc(pdf_file, docx_file):
try:
# Converting PDF to Docx
cv_obj = Converter(pdf_file)
cv_obj.convert(docx_file)
cv_obj.close()
except:
print('Conversion Failed')
else:
print('File Converted Successfully')
allfiles()
