def text(self, clean=True):
"""
Returns the text of the PDF as a single string.
Options:
:clean:
Removes misc cruft, like lots of whitespace.
"""
if clean:
return utils.normalise_whitespace(''.join(self))
else:
return ''.join(self)
def text(self, clean=True, stringify=True):
"""
Returns the text of the PDF as a single string.
Options:
:clean:
Removes misc cruft, like lots of whitespace.
"""
as_text = b''.join(self)
if stringify and sys.version_info.major > 2:
# Modern Python; detect encoding and cast to string
guessed_encoding = chardet.detect(as_text)
as_text = as_text.decode(guessed_encoding['encoding'])
if clean:
return utils.normalise_whitespace(as_text)
else:
return as_text