Modificado arquivo de exemplo do pdfminer para ler um pdf do banco central

getFile.py

"""
Extract PDF text using PDFMiner. Adapted from
http://stackoverflow.com/questions/5725278/python-help-using-pdfminer-as-a-library
"""
# nao esqueca de instalar a biblioteca Pedro
# modificado de acordo com a doc == https://github.com/euske/pdfminer/

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

from cStringIO import StringIO

def pdf_to_text(pdfname):

    rsrcmgr = PDFResourceManager()
    sio = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, sio, codec=codec, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    fp = file(pdfname, 'rb')
    for page in PDFPage.get_pages(fp):
        interpreter.process_page(page)
    fp.close()

    text = sio.getvalue()

    device.close()
    sio.close()

    return text
# http://www.bcb.gov.br/pec/GCI/PORT/readout/R20170519.pdf
# extrai o arquivo e jogue na pasta
url = "R20170519.pdf"
print(pdf_to_text(url))