pdf to doc

ilanj · Nov 27, 2022 · e0e6a89 · e0e6a89
1 parent 3f3a6ef
commit e0e6a89
Showing 1 changed file with 9 additions and 0 deletions.
diff --git a/ocr/pdf_word/pdf_word.py b/ocr/pdf_word/pdf_word.py
@@ -0,0 +1,9 @@
+from pdf2docx import Converter
+
+pdf_file = 'ila.pdf'
+docx_file = 'ila.docx'
+
+# convert pdf to docx
+cv = Converter(pdf_file)
+cv.convert(docx_file)      # all pages by default
+cv.close()