For python version 3.6, install pdfminer.six or pdfminer3k using pip install
from io import StringIO
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_text(fname, pages=None):
if not pages:
pagenums = set()
else:
pagenums = set(pages)
output = StringIO()
manager = PDFResourceManager()
converter = TextConverter(manager, output, laparams=LAParams())
interpreter = PDFPageInterpreter(manager, converter)
infile = open(fname, 'rb')
for page in PDFPage.get_pages(infile, pagenums):
interpreter.process_page(page)
infile.close()
converter.close()
text = output.getvalue()
output.close
return text
pdf_text = convert_pdf_to_text("1DD76387.pdf")
print(pdf_text)
----------------------------------------------------------------------------------------------------------------
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import HTMLConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import BytesIO
def convert_pdf_to_html(path):
rsrcmgr = PDFResourceManager()
retstr = BytesIO()
codec = 'utf-8'
laparams = LAParams()
device = HTMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = open(path, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0 #is for all
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)
fp.close()
device.close()
str = retstr.getvalue()
retstr.close()
return str
test = convert_pdf_to_html('1DD76387.pdf')
