use pdfminer to extract pdf

convert_pdf.py

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter, XMLConverter, HTMLConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import BytesIO

def convert_pdf(path, format='text', codec='utf-8', password=''):
    rsrcmgr = PDFResourceManager()
    retstr = BytesIO()
    laparams = LAParams()
    if format == 'text':
        device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    elif format == 'html':
        device = HTMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    elif format == 'xml':
        device = XMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    else:
        raise ValueError('provide format, either text, html or xml!')
    fp = open(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    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)

    text = retstr.getvalue().decode()
    fp.close()
    device.close()
    retstr.close()
    return text

init() got an unexpected keyword arguement 'codec' ... ??

EDIT : class TextConverter(PDFConverter) does not take codec arguement

def __init__(self, rsrcmgr, outfp, pageno=1, laparams=None,
showpageno=False, imagewriter=None):
PDFConverter.__init__(self, rsrcmgr, outfp, pageno=pageno, laparams=laparams)

while running above code getting this error

Traceback (most recent call last):
File "C:/Users//AppData/Roaming/JetBrains/PyCharmCE2021.1/scratches/scratch_10.py", line 41, in
if name == main():
File "C:/Users//AppData/Roaming/JetBrains/PyCharmCE2021.1/scratches/scratch_10.py", line 38, in main
out = convert_pdf(fileName, codec)
File "C:/Users//AppData/Roaming/JetBrains/PyCharmCE2021.1/scratches/scratch_10.py", line 18, in convert_pdf
device = XMLConverter(rsrcmgr, retstr, laparams=laparams)
File "C:\Users*\PycharmProjects\gcs-authoring_authoring-service\venv\lib\site-packages\pdfminer\converter.py", line 407, in init
self.write_header()
File "C:\Users*****\PycharmProjects\gcs-authoring_authoring-service\venv\lib\site-packages\pdfminer\converter.py", line 411, in write_header
self.outfp.write('\n')
TypeError: a bytes-like object is required, not 'str'

We need to add the last line:


After which we get this:

using crutches we can fix it this way: