def decrypt(query, pdfs):
"""Decrypt PDF files."""
try:
for pdf in pdfs:
reader = PdfFileReader(pdf, strict=False)
if reader.isEncrypted:
reader.decrypt(query)
writer = PdfFileWriter()
for i in xrange(reader.numPages):
writer.addPage(reader.getPage(i))
noextpath = os.path.splitext(pdf)[0]
out_file = "{} (decrypted).pdf".format(noextpath)
with open(out_file, 'wb') as f:
writer.write(f)
notify.notify('Alfred PDF Tools',
'Decryption successfully completed.')
else:
notify.notify('Alfred PDF Tools',
'The PDF file is not encrypted.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'The entered password is not valid.')
def main():
""" [EXPLAIN.] """
if len(sys.argv) != 2:
print("{}: <filepath>".format(sys.argv[0]))
return 1
filepath = sys.argv[1].strip()
r__ = PdfFileReader(open(filepath, "rb"))
page_number = 0
while page_number < r__.numPages:
page = r__.getPage(page_number)
if "/XObject" in page["/Resources"]:
x_object = page["/Resources"]["/XObject"].getObject()
for obj in x_object:
if x_object[obj]["/Subtype"] == "/Image":
size = (x_object[obj]["/Width"], x_object[obj]["/Height"])
data = x_object[obj].getData()
if x_object[obj]["/ColorSpace"] == "/DeviceRGB":
mode = "RGB"
else:
mode = "P"
_handle_filter(x_object, obj, mode, size, data)
else:
print("No image found.")
page_number += 1
def __init__(self,
args: Args,
str="booklet.pdf",
bind: str = "left") -> None:
self.doc = PdfFileReader(args.docPath)
self.numPages = self.doc.numPages
assert (not self.numPages %
4), "your source pdf must have number of pages divisible by 4"
outPath = args.outPath if args.outPath else "booklet.pdf"
self.writer = PdfFileWriter(outPath)
self.bind = bind
def get_metadata(filename):
f = open(filename, 'rb')
pdf = PdfFileReader(f)
if hasattr(pdf, 'getDocumentInfo'):
info = pdf.getDocumentInfo() # PyPDF3 and earlier
else:
info = pdf.documentInfo # PyPDF4
#print(info)
#print(info.title)
#print(info['/Title'])
f.close()
return info
def main():
if len(sys.argv) != 2:
print("{}: <filepath>".format(sys.argv[0]))
return 1
filepath = sys.argv[1].strip()
r = PdfFileReader(open(filepath, "rb"))
pageNo = 0
while (pageNo < r.numPages):
page = r.getPage(pageNo)
if '/XObject' in page['/Resources']:
xObject = page['/Resources']['/XObject'].getObject()
for obj in xObject:
if xObject[obj]['/Subtype'] == '/Image':
size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
data = xObject[obj].getData()
if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
mode = "RGB"
else:
mode = "P"
if '/Filter' in xObject[obj]:
if xObject[obj]['/Filter'] == '/FlateDecode':
img = Image.frombytes(mode, size, data)
img.save(obj[1:] + ".png")
elif xObject[obj]['/Filter'] == '/DCTDecode':
img = open(obj[1:] + ".jpg", "wb")
img.write(data)
img.close()
elif xObject[obj]['/Filter'] == '/JPXDecode':
img = open(obj[1:] + ".jp2", "wb")
img.write(data)
img.close()
elif xObject[obj]['/Filter'] == '/CCITTFaxDecode':
img = open(obj[1:] + ".tiff", "wb")
img.write(data)
img.close()
else:
img = Image.frombytes(mode, size, data)
img.save(obj[1:] + ".png")
else:
print("No image found.")
pageNo += 1
class Booklet:
def __init__(self,
args: Args,
str="booklet.pdf",
bind: str = "left") -> None:
self.doc = PdfFileReader(args.docPath)
self.numPages = self.doc.numPages
assert (not self.numPages %
4), "your source pdf must have number of pages divisible by 4"
outPath = args.outPath if args.outPath else "booklet.pdf"
self.writer = PdfFileWriter(outPath)
self.bind = bind
def yieldSequence(self) -> Generator[List[int], None, None]:
for i in range(0, self.numPages // 2):
currentPage = [self.numPages // 2 - i - 1, self.numPages // 2 + i]
if self.bind == "right" and not i % 2:
currentPage = currentPage[::-1]
if i % 2 and self.bind != "right":
currentPage = currentPage[::-1]
yield currentPage
def makeBooklet(self) -> None:
for spread in self.yieldSequence():
print(f"processing {spread}")
width: List[int]
height: List[int]
width, height = [], []
for i, pageNum in enumerate(spread):
width.append(self.doc.getPage(pageNum).mediaBox.getWidth())
height.append(self.doc.getPage(pageNum).mediaBox.getHeight())
sheet = PageObject.createBlankPage(None, sum(width), max(height))
for i, pageNum in enumerate(spread):
shift = 0 if i == 0 else width[i - 1]
page = self.doc.getPage(pageNum)
sheet.mergeScaledTranslatedPage(page, 1, shift, 0)
self.writer.addPage(sheet)
def writeBooklet(self) -> None:
self.writer.write()
print("booklet is done")
def main():
if len(sys.argv) != 3:
print("usage: python 2-up.py input_file output_file")
sys.exit(1)
print("2-up input " + sys.argv[1])
input1 = PdfFileReader(open(sys.argv[1], "rb"))
output = PdfFileWriter()
for i in range(0, input1.numPages - 1, 2):
lhs = input1.getPage(i)
rhs = input1.getPage(i + 1)
lhs.mergeTranslatedPage(rhs, lhs.mediaBox.getUpperRight_x(), 0, True)
output.addPage(lhs)
print(str(i) + " "),
sys.stdout.flush()
print("writing " + sys.argv[2])
output_stream = open(sys.argv[2], "wb")
output.write()
print("done.")
def scale(query, pdfs):
"""Scale PDF files to a given page size."""
try:
for pdf in pdfs:
reader = PdfFileReader(pdf, strict=False)
if reader.isEncrypted:
raise FileEncryptedError
writer = PdfFileWriter()
w, h = [float(i) * 72 for i in query.split('x')]
for i in xrange(reader.numPages):
inp_page = reader.getPage(i)
inp_page_w = float(inp_page.mediaBox[2])
inp_page_h = float(inp_page.mediaBox[3])
scale_w = w / inp_page_w
scale_h = h / inp_page_h
scale = min(scale_w, scale_h)
out_page = PageObject.createBlankPage(None, w, h)
out_page.mergeScaledTranslatedPage(inp_page, scale, 0, 0)
writer.addPage(out_page)
noextpath = os.path.splitext(pdf)[0]
out_file = '{} (scaled).pdf'.format(noextpath)
with open(out_file, 'wb') as f:
writer.write(f)
except FileEncryptedError:
notify.notify('Alfred PDF Tools',
'Scale action cannot handle an encrypted PDF file.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'Cannot scale a malformed PDF file.')
def encrypt(query, pdfs):
"""Encrypt PDF files."""
for pdf in pdfs:
reader = PdfFileReader(pdf, strict=False)
if not reader.isEncrypted:
writer = PdfFileWriter()
for i in xrange(reader.numPages):
writer.addPage(reader.getPage(i))
writer.encrypt(query)
noextpath = os.path.splitext(pdf)[0]
out_file = "{} (encrypted).pdf".format(noextpath)
with open(out_file, 'wb') as f:
writer.write(f)
notify.notify('Alfred PDF Tools',
'Encryption successfully completed.')
else:
notify.notify('Alfred PDF Tools',
'The PDF file is already encrypted.')
def main():
requiredPages = 3
output = "PyPDF-Merging-Output.pdf"
if set(argv) & FLAG_HELP:
print(USAGE)
exit(0)
elif len(argv) < 4:
print(USAGE)
exit(1)
else:
files = [f.strip() for f in argv[1:4]]
if len(argv) > 4:
output = argv[4].strip()
reader1 = PdfFileReader(files[0])
merger = PdfFileMerger()
if reader1.numPages < requiredPages:
print(
"File 1 requires %d pages, but it has just %d" %
(requiredPages, reader1.numPages)
)
exit(1)
input1 = open(files[0], "rb")
input2 = open(files[1], "rb")
input3 = open(files[2], "rb")
# Add the first 3 pages of input1 to output
merger.append(fileobj=input1, pages=(0, 3))
# Insert the first page of input2 into the output beginning after the
# second page
merger.merge(position=2, fileobj=input2, pages=(0, 1))
# Append entire input3 document to the end of the output document
merger.append(input3)
# Write to an output PDF document
with open(output, "wb") as outputStream:
merger.write(outputStream)
print("Output successfully written to", output)
def merge(query, pdfs, should_trash):
"""Merge PDF files."""
try:
paths = [os.path.split(path)[0] for path in pdfs]
if len(pdfs) < 2:
raise SelectionError
if not paths[1:] == paths[:-1]:
raise MultiplePathsError
merger = PdfFileMerger(strict=False)
for pdf in pdfs:
reader = PdfFileReader(pdf)
if reader.isEncrypted:
raise FileEncryptedError
merger.append(reader)
if should_trash:
for pdf in pdfs:
send2trash(pdf)
merger.write(paths[0] + '/' + query + '.pdf')
except SelectionError:
notify.notify('Alfred PDF Tools',
'You must select at least two PDF files to merge.')
except MultiplePathsError:
notify.notify('Alfred PDF Tools',
'Cannot merge PDF files from multiple paths.')
except FileEncryptedError:
notify.notify('Alfred PDF Tools',
'Merge action cannot handle an encrypted PDF file.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'Cannot merge a malformed PDF file.')
def crop(pdfs):
"""Crop two-column pages."""
try:
for pdf in pdfs:
reader = PdfFileReader(pdf, strict=False)
if reader.isEncrypted:
raise FileEncryptedError
writer = PdfFileWriter()
for i in xrange(reader.numPages):
# Make two copies of the input page.
pp = reader.getPage(i)
p = copy(pp)
q = copy(pp)
# The new media boxes are the previous crop boxes.
p.mediaBox = copy(p.cropBox)
q.mediaBox = copy(p.cropBox)
x1, x2 = p.mediaBox.lowerLeft
x3, x4 = p.mediaBox.upperRight
x1, x2 = floor(x1), floor(x2)
x3, x4 = floor(x3), floor(x4)
x5, x6 = x1 + floor((x3 - x1) / 2), x2 + floor((x4 - x2) / 2)
if (x3 - x1) > (x4 - x2):
# Horizontal
q.mediaBox.upperRight = (x5, x4)
q.mediaBox.lowerLeft = (x1, x2)
p.mediaBox.upperRight = (x3, x4)
p.mediaBox.lowerLeft = (x5, x2)
else:
# Vertical
p.mediaBox.upperRight = (x3, x4)
p.mediaBox.lowerLeft = (x1, x6)
q.mediaBox.upperRight = (x3, x6)
q.mediaBox.lowerLeft = (x1, x2)
p.artBox = p.mediaBox
p.bleedBox = p.mediaBox
p.cropBox = p.mediaBox
q.artBox = q.mediaBox
q.bleedBox = q.mediaBox
q.cropBox = q.mediaBox
writer.addPage(q)
writer.addPage(p)
noextpath = os.path.splitext(pdf)[0]
out_file = '{} (cropped).pdf'.format(noextpath)
with open(out_file, 'wb') as f:
writer.write(f)
except FileEncryptedError:
notify.notify('Alfred PDF Tools',
'Crop action cannot handle an encrypted PDF file.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'Cannot crop a malformed PDF file.')
def slice_(query, abs_path, single, suffix):
"""Slice PDF files."""
try:
reader = PdfFileReader(abs_path)
if reader.isEncrypted:
raise FileEncryptedError
writer = PdfFileWriter()
for i in xrange(reader.numPages):
writer.addPage(reader.getPage(i))
tmp_file = tempfile.NamedTemporaryFile()
writer.removeLinks()
writer.write(tmp_file)
reader = PdfFileReader(tmp_file)
pages = [x.strip() for x in query.split(',')]
for page in pages:
if not page.replace('-', '').isdigit():
raise SyntaxError
for page in pages:
if "-" in page:
if page.split('-')[1]:
stop = int(page.split('-')[1])
else:
stop = reader.numPages
else:
stop = int(page)
if stop > reader.numPages:
raise IndexError
noextpath = os.path.splitext(abs_path)[0]
if single:
merger = PdfFileMerger(strict=False)
for page in pages:
if "-" in page:
start = int(page.split('-')[0]) - 1
stop_str = page.split('-')[1]
if stop_str:
stop = int(stop_str)
else:
stop = reader.numPages
if start == -1:
raise StartValueZeroError
if start >= stop:
raise StartValueReverseError
else:
start = int(page) - 1
stop = int(page)
merger.append(reader, pages=(start, stop))
merger.write(noextpath + ' (sliced).pdf')
else:
part_no = 0
for page in pages:
merger = PdfFileMerger(strict=False)
if "-" in page:
start = int(page.split('-')[0]) - 1
stop_str = page.split('-')[1]
if stop_str:
stop = int(stop_str)
else:
stop = reader.numPages
if start == -1:
raise StartValueZeroError
if start >= stop:
raise StartValueReverseError
else:
start = int(page) - 1
stop = int(page)
out_file = '{} ({} {}).pdf'.format(noextpath, suffix,
part_no + 1)
merger.append(reader, pages=(start, stop))
merger.write(out_file)
part_no += 1
tmp_file.close()
except SyntaxError:
notify.notify('Alfred PDF Tools', 'The input syntax is not valid.')
except IndexError:
notify.notify('Alfred PDF Tools', 'Page number out of range.')
except StartValueZeroError:
notify.notify('Alfred PDF Tools', 'Page number cannot be zero.')
except StartValueReverseError:
notify.notify('Alfred PDF Tools',
'You cannot set a page range in reverse order.')
except FileEncryptedError:
notify.notify('Alfred PDF Tools',
'Slice action cannot handle an encrypted PDF file.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'Cannot slice a malformed PDF file.')
def split_size(query, abs_path, suffix):
"""Split PDF file by file size."""
try:
if float(query) < 0:
raise ValueError
max_part_size = float(query) * 1000000
noextpath = os.path.splitext(abs_path)[0]
reader = PdfFileReader(abs_path, strict=False)
pg_cnt = reader.numPages
if reader.isEncrypted:
raise FileEncryptedError
pg_sizes = []
for i in xrange(pg_cnt):
writer = PdfFileWriter()
writer.addPage(reader.getPage(i))
writer.removeLinks()
tmp_file = tempfile.NamedTemporaryFile()
writer.write(tmp_file)
file_size = os.path.getsize(tmp_file.name)
pg_sizes.append(file_size)
tmp_file.close()
writer = PdfFileWriter()
for i in xrange(pg_cnt):
writer.addPage(reader.getPage(i))
inp_file = tempfile.NamedTemporaryFile()
writer.write(inp_file)
inp_file_size = os.path.getsize(abs_path)
sum_pg_sizes = sum(pg_sizes)
dividend = min(inp_file_size, sum_pg_sizes)
divisor = max(inp_file_size, sum_pg_sizes)
quotient = dividend / divisor
start = 0
stop = 1
pg_no = 0
while not stop > pg_cnt:
out_file = '{} ({} {}).pdf'.format(noextpath, suffix, pg_no + 1)
if quotient > 0.95:
part = pg_sizes[start:stop]
part_size = sum(part)
part_pg_cnt = len(part)
if part_size < max_part_size:
if stop != pg_cnt:
stop += 1
else:
merger = PdfFileMerger(strict=False)
merger.append(inp_file, pages=(start, stop))
merger.write(out_file)
break
else:
if part_pg_cnt == 1:
merger = PdfFileMerger(strict=False)
merger.append(inp_file, pages=(start, stop))
merger.write(out_file)
start = stop
stop += 1
pg_no += 1
else:
stop -= 1
merger = PdfFileMerger(strict=False)
merger.append(inp_file, pages=(start, stop))
merger.write(out_file)
start = stop
stop += 1
pg_no += 1
else:
part = pg_sizes[start:stop]
part_size = sum(part)
part_pg_cnt = len(part)
if part_size < max_part_size:
if stop != pg_cnt:
stop += 1
else:
merger = PdfFileMerger(strict=False)
merger.append(inp_file, pages=(start, stop))
merger.write(out_file)
break
else:
if part_pg_cnt == 1:
merger = PdfFileMerger(strict=False)
merger.append(inp_file, pages=(start, stop))
merger.write(out_file)
start = stop
stop += 1
pg_no += 1
else:
stop -= 1
merger = PdfFileMerger(strict=False)
merger.append(inp_file, pages=(start, stop))
merger.write(out_file)
part_size = os.path.getsize(out_file)
next_page = pg_sizes[stop:stop + 1][0]
if part_size + next_page < max_part_size:
os.remove(out_file)
part_size_real = part_size / (stop - start)
pg_sizes_real = []
for i in xrange(pg_cnt):
if i >= start and i < stop:
pg_sizes_real.append(part_size_real)
else:
pg_sizes_real.append(pg_sizes[i])
pg_sizes = pg_sizes_real
stop += 1
else:
start = stop
stop += 1
pg_no += 1
inp_file.close()
except ValueError:
notify.notify('Alfred PDF Tools',
'The argument must be a positive numeric value.')
except FileEncryptedError:
notify.notify('Alfred PDF Tools',
'Split action cannot handle an encrypted PDF file.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'Cannot split a malformed PDF file.')
def split_count(query, abs_path, suffix):
"""Split PDF file by page count"""
try:
if not query.lstrip('+-').isdigit():
raise NotIntegerError
if int(query) < 0:
raise NegativeValueError
reader = PdfFileReader(abs_path)
if reader.isEncrypted:
raise FileEncryptedError
pg_cnt = int(query)
start = 0
stop = pg_cnt
writer = PdfFileWriter()
for i in xrange(reader.numPages):
writer.addPage(reader.getPage(i))
tmp_file = tempfile.NamedTemporaryFile()
writer.removeLinks()
writer.write(tmp_file)
reader = PdfFileReader(tmp_file)
num_pages = int(reader.numPages)
quotient = num_pages / pg_cnt
if quotient.is_integer():
for i in xrange(int(quotient)):
merger = PdfFileMerger(strict=False)
merger.append(tmp_file, pages=(start, stop))
noextpath = os.path.splitext(abs_path)[0]
out_file = "{} ({} {}).pdf".format(noextpath, suffix, i + 1)
merger.write(out_file)
start = stop
stop = start + pg_cnt
else:
for i in xrange(int(quotient) + 1):
merger = PdfFileMerger(strict=False)
merger.append(tmp_file, pages=(start, stop))
noextpath = os.path.splitext(abs_path)[0]
out_file = "{} ({} {}).pdf".format(noextpath, suffix, i + 1)
merger.write(out_file)
if i != int(quotient) - 1:
start = stop
stop = start + pg_cnt
else:
start = int(quotient) * pg_cnt
stop = num_pages
tmp_file.close()
except NotIntegerError:
notify.notify('Alfred PDF Tools', 'The argument is not an integer.')
except NegativeValueError:
notify.notify('Alfred PDF Tools',
'Negative integer is not a valid argument.')
except ZeroDivisionError:
notify.notify('Alfred PDF Tools', 'Zero is not a valid argument.')
except FileEncryptedError:
notify.notify('Alfred PDF Tools',
'Split action cannot handle an encrypted PDF file.')
except PdfReadError:
notify.notify('Alfred PDF Tools', 'Cannot split a malformed PDF file.')
def merge_watermark(pdf_file, save_dir, owner_pwd, p_value, wm_attrs):
out_file = os.path.join(save_dir, os.path.basename(pdf_file))
try:
pdf_reader = PdfFileReader(pdf_file)
except Exception as e:
print('try to repair %s' % pdf_file)
import fitz
pdf_doc = fitz.open(pdf_file)
repair_pdf_file = pdf_file.replace('.pdf', '_repaired.pdf')
pdf_doc.save(repair_pdf_file)
pdf_doc.close()
shutil.move(repair_pdf_file, pdf_file)
pdf_reader = PdfFileReader(pdf_file)
if pdf_reader.isEncrypted:
pdf_reader.decrypt('')
pdf_writer = PdfFileWriter(out_file)
first_page = pdf_reader.getPage(0)
page_width = first_page.mediaBox.getWidth()
page_height = first_page.mediaBox.getHeight()
wm_attrs.update({'pagesize': (page_width, page_height)})
wm_file = create_watermark(**wm_attrs) # for Portrait
wm_obj = PdfFileReader(wm_file)
wm_page = wm_obj.getPage(0)
for page_num in range(pdf_reader.numPages):
current_page = pdf_reader.getPage(page_num)
current_page.mergePage(wm_page)
pdf_writer.addPage(current_page)
if owner_pwd.lower() not in ['-1', 'no', 'none', 'null']:
pdf_writer.encrypt('', ownerPwd=owner_pwd, P=p_value)
key_file = os.path.join(wm_attrs['out_dir'], '..', 'permission_key')
old_keys = None
if os.path.exists(key_file):
old_key_file = open(key_file, 'r', encoding='utf-8')
old_keys = old_key_file.readlines()
old_key_file.close()
with open(key_file, 'w', encoding='utf-8') as f_log:
if old_keys is not None:
f_log.writelines(old_keys[-1000:])
f_log.write('%s %s %s\n' % (time.strftime('%Y-%m-%d %H:%M:%S'),
os.path.relpath(out_file), owner_pwd))
pdf_writer.write()
pdf_writer.close()
if os.path.exists(wm_file):
os.remove(wm_file)
