Created
October 30, 2019 11:16
-
-
Save giasuddin90/a50eb06cde48dc89e593291de1f46639 to your computer and use it in GitHub Desktop.
By using python PyPDF2 and openpyxl library read data from pdf file and write data in xlsx file
This file contains 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
#-*- coding: utf-8 -*- | |
import PyPDF2 | |
from openpyxl import Workbook | |
def pypd(): | |
pdfFileObj = open('principle of marketing.pdf', 'rb') | |
pdfReader = PyPDF2.PdfFileReader(pdfFileObj) | |
# allpage= pdfReader.numPages | |
pages = range(939, 959) | |
# pages = range(939, 940) | |
wb = Workbook() | |
ws = wb.active | |
for page in pages: | |
pageObj = pdfReader.getPage(page) | |
page_text=pageObj.extractText().encode('utf8').split('.') | |
print(len(page_text)) | |
for item in page_text: | |
list_item=item.split("—") | |
ws.append(list_item) | |
print(list_item) | |
wb.save('jargon.xlsx') | |
if __name__ == '__main__': | |
pypd() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment