Pdfminer python 3.5

There is a solution for Python 3.5: you need pdfminer.six. Under win10 I could easy install it with

pip install pdfminer.six

You can check the installed version with

pdfminer.__version__

I haven't tested it intensively yet. But I could run the following code for the conversion pdf→text and pdf→html

In my case on Python 3.7 I tried using it and it worked like a charm for me!

here is the code I used:

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

Improved solution (Dez 2016)

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

def convert(case,fname, pages=None):
    if not pages: pagenums = set();
    else:         pagenums = set(pages);      
    manager = PDFResourceManager() 
    codec = 'utf-8'
    caching = True

    if case == 'text' :
        output = io.StringIO()
        converter = TextConverter(manager, output, codec=codec, laparams=LAParams())     
    if case == 'HTML' :
        output = io.BytesIO()
        converter = HTMLConverter(manager, output, codec=codec, laparams=LAParams())

    interpreter = PDFPageInterpreter(manager, converter)   
    infile = open(fname, 'rb')

    for page in PDFPage.get_pages(infile, pagenums,caching=caching, check_extractable=True):
        interpreter.process_page(page)

    convertedPDF = output.getvalue()  

    infile.close(); converter.close(); output.close()
    return convertedPDF

#//////////// main ///////////////////////
filePDF  = 'myDir//myPDF.pdf'     # input
fileHTML = 'myDir//myHTML.html'   # output
fileTXT  = 'myDir//myTXT.txt'     # output

case = "HTML"

if case == 'HTML' :
    convertedPDF = convert('HTML', filePDF, pages=[0,1])
    fileConverted = open(fileHTML, "wb", encoding="utf-8")
if case == 'text' :
    convertedPDF = convert('text', filePDF, pages=[0,1])
    fileConverted = open(fileTXT, "w", encoding="utf-8")

fileConverted.write(convertedPDF)
fileConverted.close()
#print(convertedPDF)