def __init__(self,
file_name,
rotation,
suffix='rotated',
tempdir=None,
method='pdfrw'):
self.file_name = file_name
self.rotation = rotation
self.suffix = suffix
self.tempdir = tempdir
if tempdir:
with NamedTemporaryFile(suffix='.pdf', dir=tempdir,
delete=False) as temp:
self.outfn = temp.name
elif suffix:
self.outfn = os.path.join(os.path.dirname(file_name),
add_suffix(file_name, suffix))
else:
self.outfn = NamedTemporaryFile(suffix='.pdf').name
if method == 'pypdf3':
self.pypdf3()
else:
self.pdfrw()
def _get_output(self, index):
if self.output:
return self.output
elif not self.tempdir:
output_file = add_suffix(self.file_name, str(index + 1), ext=self.ext)
return os.path.join(self.output_dir, output_file)
else:
with NamedTemporaryFile(suffix=self.ext, dir=self.tempdir, delete=True) as temp:
return temp.name
def save(self, remove_temps=True):
if self.imgs is None:
self.get_imgs()
i2p = IMG2PDF(self.imgs, self.directory, self.tempdir,
self.progress_bar)
self.pdf = i2p.save(clean_temp=False,
output_name=add_suffix(self._file_name,
self.suffix))
self.cleanup(remove_temps)
return self.pdf
def slicer(document,
first_page=None,
last_page=None,
suffix='sliced',
tempdir=None):
"""Slice a PDF document to remove pages."""
# Set output file name
if tempdir:
with NamedTemporaryFile(suffix='.pdf', dir=tempdir,
delete=False) as temp:
output = temp.name
elif suffix:
output = os.path.join(os.path.dirname(document),
add_suffix(document, suffix))
else:
with NamedTemporaryFile(suffix='.pdf') as temp:
output = temp.name
# Reindex page selections for simple user input
first_page = first_page - 1 if not None else None
# Validate page range by comparing selection to number of pages in PDF document
pages = Info(document).pages
invalid = 'Number of pages: ' + str(
pages) + ' ----> Page Range Input: ' + str(first_page) + '-' + str(
last_page)
assert first_page <= last_page <= pages, invalid
pdf = PdfFileReader(document)
writer = PdfFileWriter()
pages = list(range(pdf.getNumPages()))[first_page:last_page]
for page in pages:
writer.addPage(pdf.getPage(page))
with open(output, 'wb') as out:
writer.write(out)
return output
def __init__(self,
file_name,
margin_x=0,
margin_y=0,
scale=1.5,
suffix='scaled',
tempdir=None,
method='pdfrw'):
self.file_name = file_name
self.margin_x = margin_x
self.margin_y = margin_y
self.scale = scale
self.suffix = suffix
# Set output file name
if tempdir:
with NamedTemporaryFile(suffix='_' + suffix + '.pdf',
dir=tempdir,
delete=False) as temp:
self.output = temp.name
elif suffix:
self.output = os.path.join(os.path.dirname(file_name),
add_suffix(file_name, suffix))
else:
self.output = NamedTemporaryFile(suffix='_' + suffix + '.pdf').name
# Get target width and height
dims = Info(self.file_name).dimensions
self.target_w = dims['w'] * self.scale
self.target_h = dims['h'] * self.scale
# Execute either pdfrw or PyPDF3 method
if method == 'pypdf3':
self.pypdf3()
else:
self.pdfrw()