def pdf_2_text(pdf_file_name: str,
password='',
page_numbers=None,
maxpages=0,
caching=True,
laparams=None) -> str:
"""
This is a re-write of the function pdfminer.high_level.extract_text
https://github.com/pdfminer/pdfminer.six/blob/0b44f7771462363528c109f263276eb254c4fcd0/pdfminer/high_level.py#L90
It produces result, which does not have this issue: https://github.com/pdfminer/pdfminer.six/issues/466
: pdf_file_name - name of the input PDF file
: password: For encrypted PDFs, the password to decrypt.
: page_numbers: zero-indexed page numbers to operate on
: maxpages: How many pages to stop parsing after
:
"""
result = ""
with open_filename(pdf_file_name, "rb") as pdf_file_object:
for page in PDFPage.get_pages(
pdf_file_object,
page_numbers,
maxpages=maxpages,
password=password,
caching=caching,
):
result = result + _PDFpage2txt(page, laparams)
return result
def extract_text(pdf_file, password='', page_numbers=None, maxpages=0,
caching=True, codec='utf-8', laparams=None):
"""Parse and return the text contained in a PDF file.
:param pdf_file: Either a file path or a file-like object for the PDF file
to be worked on.
:param password: For encrypted PDFs, the password to decrypt.
:param page_numbers: List of zero-indexed page numbers to extract.
:param maxpages: The maximum number of pages to parse
:param caching: If resources should be cached
:param codec: Text decoding codec
:param laparams: An LAParams object from pdfminer.layout. If None, uses
some default settings that often work well.
:return: a string containing all of the text extracted.
"""
if laparams is None:
laparams = None
with open_filename(pdf_file, "rb") as fp, StringIO() as output_string:
rsrcmgr = PDFResourceManager(caching=caching)
device = TextConverter(rsrcmgr, output_string, codec=codec,
laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(
fp,
page_numbers,
maxpages=maxpages,
password=password,
caching=caching,
):
interpreter.process_page(page)
return output_string.getvalue()
def extract_text_by_page(pdf_file, password='', page_numbers=None, maxpages=0,
caching=True, codec='utf-8', laparams=None):
"""
Parse and return the text contained in each page of a PDF file. Taken from
https://github.com/pdfminer/pdfminer.six/blob/master/pdfminer/high_level.py#L90-L123
and adapted to return the text of each page separately as a dictionary obj.
:param pdf_file: Either a file path or a file-like object for the PDF file
to be worked on.
:param password: For encrypted PDFs, the password to decrypt.
:param page_numbers: List of zero-indexed page numbers to extract.
:param maxpages: The maximum number of pages to parse
:param caching: If resources should be cached
:param codec: Text decoding codec
:param laparams: An LAParams object from pdfminer.layout. If None, uses
some default settings that often work well.
:return: a dict containing the text from each page (keys = page numbers)
"""
if laparams is None:
laparams = LAParams()
text_by_page = {}
with open_filename(pdf_file, "rb") as fp:
rsrcmgr = PDFResourceManager()
pages_iterable = PDFPage.get_pages(fp, page_numbers, maxpages=maxpages, password=password, caching=caching)
if page_numbers is None:
tuples_iterable = enumerate(pages_iterable)
else:
tuples_iterable = zip(page_numbers, pages_iterable)
for page_num, page in tuples_iterable:
# print('Processing page_num', page_num)
with StringIO() as output_string:
device = TextConverter(rsrcmgr, output_string, codec=codec, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
interpreter.process_page(page)
text_by_page[page_num] = output_string.getvalue()
return text_by_page
def test_string_input(self):
filename = absolute_sample_path("simple1.pdf")
opened = open_filename(filename)
assert_equal(opened.closing, True)
def test_file_input(self):
filename = absolute_sample_path("simple1.pdf")
with open(filename, "rb") as in_file:
opened = open_filename(in_file)
assert_equal(opened.file_handler, in_file)
def test_pathlib_input(self):
filename = pathlib.Path(absolute_sample_path("simple1.pdf"))
opened = open_filename(filename)
assert_equal(opened.closing, True)