def save_page(filepath, page_number):
infile = PdfFileReader(open(filepath, "rb"), strict=False)
page = infile.getPage(page_number - 1)
outfile = PdfFileWriter()
outfile.addPage(page)
outpath = os.path.join(os.path.dirname(filepath),
f"page-{page_number}.pdf")
with open(outpath, "wb") as f:
outfile.write(f)
froot, fext = os.path.splitext(outpath)
layout, __ = get_page_layout(outpath)
# fix rotated PDF
chars = get_text_objects(layout, ltype="char")
horizontal_text = get_text_objects(layout, ltype="horizontal_text")
vertical_text = get_text_objects(layout, ltype="vertical_text")
rotation = get_rotation(chars, horizontal_text, vertical_text)
if rotation != "":
outpath_new = "".join([froot.replace("page", "p"), "_rotated", fext])
os.rename(outpath, outpath_new)
infile = PdfFileReader(open(outpath_new, "rb"), strict=False)
if infile.isEncrypted:
infile.decrypt("")
outfile = PdfFileWriter()
p = infile.getPage(0)
if rotation == "anticlockwise":
p.rotateClockwise(90)
elif rotation == "clockwise":
p.rotateCounterClockwise(90)
outfile.addPage(p)
with open(outpath, "wb") as f:
outfile.write(f)
def save_page(filepath, page_number):
infile = PdfFileReader(open(filepath, 'rb'), strict=False)
page = infile.getPage(page_number - 1)
outfile = PdfFileWriter()
outfile.addPage(page)
outpath = os.path.join(os.path.dirname(filepath), 'page-{}.pdf'.format(page_number))
with open(outpath, 'wb') as f:
outfile.write(f)
froot, fext = os.path.splitext(outpath)
layout, __ = get_page_layout(outpath)
# fix rotated PDF
chars = get_text_objects(layout, ltype="char")
horizontal_text = get_text_objects(layout, ltype="horizontal_text")
vertical_text = get_text_objects(layout, ltype="vertical_text")
rotation = get_rotation(chars, horizontal_text, vertical_text)
if rotation != '':
outpath_new = ''.join([froot.replace('page', 'p'), '_rotated', fext])
os.rename(outpath, outpath_new)
infile = PdfFileReader(open(outpath_new, 'rb'), strict=False)
if infile.isEncrypted:
infile.decrypt('')
outfile = PdfFileWriter()
p = infile.getPage(0)
if rotation == 'anticlockwise':
p.rotateClockwise(90)
elif rotation == 'clockwise':
p.rotateCounterClockwise(90)
outfile.addPage(p)
with open(outpath, 'wb') as f:
outfile.write(f)
def _generate_layout(self, filename, layout_kwargs):
# Copied from camelot/parsers/base/BaseParser._generate_layout()
# with removing the actual layout generation because we already
# have the layout for other needs.
self.filename = filename
self.layout_kwargs = layout_kwargs
# self.layout, self.dimensions = get_page_layout(filename, **layout_kwargs)
self.images = get_text_objects(self.layout, ltype="image")
self.horizontal_text = get_text_objects(self.layout,
ltype="horizontal_text")
self.vertical_text = get_text_objects(self.layout,
ltype="vertical_text")
self.pdf_width, self.pdf_height = self.dimensions
self.rootname, __ = os.path.splitext(self.filename)