Я попробовал библиотеку с именем pytotree, но я не получил никакого ответа. Это код:
import pdftotree
file= open('C:/Users/chaitanya.naidu/Downloads/test.pdf', 'rb')
f = pdftotree.parse(file)
Я получаю эту ошибку
Traceback (most recent call last):
File "<ipython-input-4-4a9a6b72801d>", line 1, in <module>
f = pdftotree.parse(file)
File "C:\Users\chaitanya.naidu\AppData\Local\Continuum\Anaconda3\lib\site-packages\pdftotree\core.py", line 63, in parse
if not extractor.is_scanned():
File "C:\Users\chaitanya.naidu\AppData\Local\Continuum\Anaconda3\lib\site-packages\pdftotree\TreeExtract.py", line 121, in is_scanned
self.parse()
File "C:\Users\chaitanya.naidu\AppData\Local\Continuum\Anaconda3\lib\site-packages\pdftotree\TreeExtract.py", line 91, in parse
for page_num, layout in enumerate(analyze_pages(self.pdf_file)):
File "C:\Users\chaitanya.naidu\AppData\Local\Continuum\Anaconda3\lib\site-packages\pdftotree\utils\pdf\pdf_utils.py", line 117, in analyze_pages
with open(os.path.realpath(file_name), "rb") as fp:
File "C:\Users\chaitanya.naidu\AppData\Local\Continuum\Anaconda3\lib\ntpath.py", line 542, in abspath
path = os.fspath(path)
TypeError: expected str, bytes or os.PathLike object, not _io.BufferedReader