Final version of script

Author: pkjagesia

AUTOMATION/converted_pdf.txt

@@ -0,0 +1,28 @@
+Adobe Acrobat PDF Files
+
+Adobe® Portable Document Format (PDF) is a universal file format that preserves all
+of the fonts, formatting, colours and graphics  of any  source document,  regardless of
+the application and platform used to create it.
+
+Adobe PDF is an ideal format for electronic document distribution as it overcomes the
+problems commonly encountered with electronic file sharing.
+
+•  Anyone, anywhere can open a PDF file. All you need is the free Adobe Acrobat
+Reader.  Recipients  of  other  file  formats  sometimes  can't  open  files  because  they
+don't have the applications used to create the documents.
+
+•  PDF files always print correctly on any printing device.
+
+•  PDF  files  always  display  exactly  as  created,  regardless  of  fonts,  software,  and
+operating systems. Fonts, and graphics are not lost due to platform, software, and
+version incompatibilities.
+
+•  The  free  Acrobat  Reader  is  easy  to  download  and  can  be  freely  distributed  by
+
+anyone.
+
+•  Compact  PDF  files  are  smaller  than  their  source  files  and  download  a
+
+page at a time for fast display on the Web.
+
+

AUTOMATION/pdfToText.py

@@ -3,13 +3,15 @@
 
 # Extract text with Pdfminer.six Module
 def With_PdfMiner(pdf):
-	with open(pdf,'rb') as file_handle:
-		doc = pdfminer.high_level.extract_text(file_handle)
-		print(doc)
+	with open(pdf,'rb') as file_handle_1:
+		doc = pdfminer.high_level.extract_text(file_handle_1)
+
+	with open('converted_pdf.txt','w') as file_handle_2 :
+		file_handle_2.write(doc)
+
 
 if __name__ == '__main__':
 	parser = argparse.ArgumentParser()
 	parser.add_argument("file", help = "PDF file from which we extract text")
 	args = parser.parse_args()
-	# print()
 	With_PdfMiner(args.file)