Import multiple PDF files from a folder in python and write them to multiple text files, all with the same name as the PDF they were created from.

Answer 1

Here's the solution with explanations in the code in the form of comments:

from os import listdir

from os.path import isfile, join

import PyPDF2 # python3 -m pip install PyPDF2

'''

Change path to the local location of your folder:

path = 'C:\Users\FooBar\Desktop\test-folder' # for Windows

path = '/Users/FooBar/Desktop/test-folder' # for Mac

'''

path = ''

# Make a list of absolute path's to all of the PDF files in the target folder

files = [join(path, f) for f in listdir(path) if isfile(join(path, f)) and join(path, f).endswith('.pdf')]

# Iterate through the list of PDF files using the PDF's aboslute path

for f in files:

with open(f, 'rb') as file_handle:

# Set strict=False to allow PDF files that don't comply to the PDF spec: https://www.pdfa.org/resource/pdf-specification-index/

pdf_reader = PyPDF2.PdfFileReader(file_handle, strict=False)

page_text = ''

# Iterate through each page in the PDF document to extract the text and add to plain-text string

for page_num in range(0, pdf_reader.getNumPages()):

page = pdf_reader.getPage(page_num)

page_text += page.extract_text()

# Write the plain text string to a file with the same name

with open(f.replace('.pdf', '.txt'), 'a+') as text_file_handle:

text_file_handle.writelines(page_text)