-
Notifications
You must be signed in to change notification settings - Fork 1.6k
pypdf.errors.PdfReadError: Could not read Boolean object #2082
Description
i'm getting an error when i try and read a pdf from a specific company
pycharm
File "C:\Users\jerem\PycharmProjects\testing\main.py", line 16, in
main()
File "C:\Users\jerem\PycharmProjects\testing\main.py", line 8, in main
text = pypdf.PdfReader('test.pdf')
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf_reader.py", line 318, in init
self.read(stream)
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf_reader.py", line 1548, in read
self._read_xref_tables_and_trailers(stream, startxref, xref_issue_nr)
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf_reader.py", line 1758, in _read_xref_tables_and_trailers
startxref = self._read_xref(stream)
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf_reader.py", line 1794, in _read_xref
self._read_standard_xref_table(stream)
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf_reader.py", line 1657, in _read_standard_xref_table
size = cast(int, read_object(stream, self))
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf\generic_data_structures.py", line 1229, in read_object
return BooleanObject.read_from_stream(stream)
File "C:\Users\jerem\AppData\Local\Programs\Python\Python310\lib\site-packages\pypdf\generic_base.py", line 257, in read_from_stream
raise PdfReadError("Could not read Boolean object")
pypdf.errors.PdfReadError: Could not read Boolean object
Process finished with exit code 1
################CODE################
import pypdf
def main():
text = pypdf.PdfReader('test.pdf') #FAILS HERE
out = text.pages[0].extract_text()
if name == 'main':
pdf_file = 'test.pdf'
main()