Extracting entire pdf data with python pdfminer

Question

I am using pdfminer to extract data from pdf files using python. I would like to extract all the data present in pdf irrespective of wheather it is an image or text or whatever it is. Can we do that in a single line(or two if needed, without much work). Any help is appreciated. Thanks in advance

Answer 1

Can we do that in a single line(or two if needed, without much work).

No, you cannot. Pdfminer is powerful but it's rather low-level.

Unfortunately, the documentation is not exactly exhaustive. I was able to find my way around it thanks to some code by Denis Papathanasiou. The code is discussed in his blog, and you can find the source here: layout_scanner.py

See also this answer, where I give a little more detail.

Answer 2

For Python 3:

pip install pdfminer.six

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

def convert_pdf_to_txt(path, codec='utf-8'):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = open(path, 'rb')
    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)

    text = retstr.getvalue()

    fp.close()
    device.close()
    retstr.close()
    return text

Answer 3

for python3 , there is another one : pip install pdfminer3k

from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
import time
from functools import wraps

def fn_timer(function)://this is for calculating the run time(function)
    @wraps(function)
    def function_timer(*args, **kwargs):
        t0 = time.time()
        result = function(*args, **kwargs)
        t1 = time.time()
        print ("Total time running %s: %s seconds" %
                ('test', str(t1-t0))
                )
        return result
    return function_timer

@fn_timer
def convert_pdf(path, pages):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, laparams=laparams)

    fp = open(path, 'rb')
    process_pdf(rsrcmgr, device, fp,pages)
    fp.close()
    device.close()

    str = retstr.getvalue()
    retstr.close()
    return str

file = r'M:\a.pdf'

print(convert_pdf(file,[1,]))