How to extract text from pdf in Python 3.7

Question

I am trying to extract text from a PDF file using Python. My main goal is I am trying to create a program that reads a bank statement and extracts its text to update an exce

Answer 1

If you are looking for a maintained, bigger project, have a look at PyMuPDF. Install it with pip install pymupdf and use it like this:

import fitz

def get_text(filepath: str) -> str:
    with fitz.open(filepath) as doc:
        text = ""
        for page in doc:
            text += page.getText().strip()
        return text

Answer 2

import pdftables_api
import os

c = pdftables_api.Client('MY-API-KEY')

file_path = "C:\\Users\\MyName\\Documents\\PDFTablesCode\\"

for file in os.listdir(file_path):
    if file.endswith(".pdf"):
        c.xlsx(os.path.join(file_path,file), file+'.xlsx')

Go to https://pdftables.com to get an API key.

CSV, format=csv

XML, format=xml

HTML, format=html

XLSX, format=xlsx-single, format=xlsx-multiple

Answer 3

Here is an alternative solution in Windows 10, Python 3.8

Example test pdf: https://drive.google.com/file/d/1aUfQAlvq5hA9kz2c9CyJADiY3KpY3-Vn/view?usp=sharing

#pip install pdfminer.six
import io

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage


def convert_pdf_to_txt(path):
    '''Convert pdf content from a file path to text

    :path the file path
    '''
    rsrcmgr = PDFResourceManager()
    codec = 'utf-8'
    laparams = LAParams()

    with io.StringIO() as retstr:
        with TextConverter(rsrcmgr, retstr, codec=codec,
                           laparams=laparams) as device:
            with open(path, 'rb') as fp:
                interpreter = PDFPageInterpreter(rsrcmgr, device)
                password = ""
                maxpages = 0
                caching = True
                pagenos = set()

                for page in PDFPage.get_pages(fp,
                                              pagenos,
                                              maxpages=maxpages,
                                              password=password,
                                              caching=caching,
                                              check_extractable=True):
                    interpreter.process_page(page)

                return retstr.getvalue()


if __name__ == "__main__":
    print(convert_pdf_to_txt('C:\\Path\\To\\Test_PDF.pdf'))

Answer 4

PyPDF2 does not read whole pdf correctly. You must use this code.

    import pdftotext

    pdfFileObj = open("January2019.pdf", 'rb')


    pdf = pdftotext.PDF(pdfFileObj)

    # Iterate over all the pages
    for page in pdf:
        print(page)