Python: Extract text from multiple pdf and paste on excel

You basically want to put the code you wrote which reads the pdf file into a for loop which iterates over the filenames (in this case, the filenames are stored as a tuple).

Using enumerate, row increments every iteration of the loop, and starts at 1. So the text and filename will be put into A1 and B1, then A2 and B2, and so on.

import PyPDF2
import openpyxl

filenames = ("file.pdf", 
             "file2.pdf", 
             "file3.pdf", 
            )

wb = openpyxl.load_workbook('excel.xlsx')
sheet = wb.active
sheet.title = 'MyPDF'

for row, filename in enumerate(filenames, start=1):
    with open(filename, 'rb') as f:
        pdfReader = PyPDF2.PdfFileReader(f)
        pdfReader.numPages
        pageObj = pdfReader.getPage(0)
        mytext = pageObj.extractText()
    
    sheet[f'A{row}'].value = mytext
    sheet[f'B{row}'].value = filename

wb.save('excel.xlsx')
print('DONE!!')

You can get a list of all the filenames ending in .pdf quite easily by iterating over all the files in a directory, and checking if the filename ends in .pdf. If it does, use os.path.join to give you the full filepath, and append it to the filenames list.

You could also use the glob module, too.

import os

filenames = []
directory = r"C:StuffPDF Files"
for filename in os.listdir(directory):
    if filename.lower().endswith(".pdf"):
        filenames.append(os.path.join(directory, filename))

Updated code:

import PyPDF2
import openpyxl
import os
import glob
import re
import itertools

# Used to strip characters that can't be written to a spreadsheet
# See https://stackoverflow.com/a/93029/3589122
control_chars = ''.join(map(chr, itertools.chain(range(0x00,0x20), range(0x7f,0xa0))))
control_char_re = re.compile('[%s]' % re.escape(control_chars))

def remove_control_chars(s):
    return control_char_re.sub('', s)

root_dir = 'your directory' # root_dir needs a trailing slash (i.e. /root/dir/)

filenames = (filename for filename in glob.iglob(root_dir + '/**/*.pdf', recursive=True))

wb = openpyxl.load_workbook('excel.xlsx') # your file excel
sheet = wb.active
sheet.title = 'MyPDF'

row = 1
for filename in filenames:
    with open(filename, 'rb') as f:
        try:
            pdfReader = PyPDF2.PdfFileReader(f)
            count = pdfReader.numPages
            
            output = []
            for i in range(count): 
                print(i, filename)
                page = pdfReader.getPage(i)
                output.append(page.extractText())
                #print(output)
        except Exception as e:
            print(f'Error: PyPDF2 could not read {filename}. Continuing... ({e})')
            continue
    
    sheet[f'A{row}'].value = 'n'.join(remove_control_chars(output))
    sheet[f'B{row}'].value = filename
    row += 1

wb.save('excel.xlsx') #your file excel
print('DONE!!')