2019-12-04 14:24:30 +01:00
|
|
|
from PyPDF2 import PdfFileReader
|
|
|
|
from PyPDF2.utils import PdfReadError
|
|
|
|
|
|
|
|
|
|
|
|
def bytes_to_human(size):
|
|
|
|
# TODO: Read http://stackoverflow.com/a/1094933 and think about it.
|
|
|
|
if size < 1024:
|
|
|
|
size_string = "< 1 kB"
|
|
|
|
elif size >= 1024 * 1024:
|
|
|
|
mB = size / 1024 / 1024
|
|
|
|
size_string = "%d MB" % mB
|
|
|
|
else:
|
|
|
|
kB = size / 1024
|
|
|
|
size_string = "%d kB" % kB
|
|
|
|
return size_string
|
|
|
|
|
|
|
|
|
|
|
|
def get_pdf_information(mediafile):
|
|
|
|
result = {}
|
|
|
|
try:
|
|
|
|
pdf = PdfFileReader(mediafile)
|
|
|
|
result["pages"] = pdf.getNumPages()
|
2021-03-18 13:52:51 +01:00
|
|
|
except PdfReadError:
|
2019-12-04 14:24:30 +01:00
|
|
|
# File could be encrypted but not be detected by PyPDF.
|
|
|
|
result["pages"] = 0
|
|
|
|
result["encrypted"] = True
|
2021-03-18 13:52:51 +01:00
|
|
|
except (KeyError, OSError):
|
|
|
|
# Other errors. Mostly very rare to occur, but do not raise a 500:
|
|
|
|
# KeyError: https://github.com/mstamy2/PyPDF2/issues/353
|
|
|
|
# OSError: https://github.com/mstamy2/PyPDF2/issues/530
|
|
|
|
result["pages"] = 0
|
|
|
|
result["read_error"] = True
|
2019-12-04 14:24:30 +01:00
|
|
|
return result
|