def encrypt_file(self):
path = self.file_selector.getpath()
if not path:
messagebox.showerror(MESSAGE_TITLE, "You must select a PDF file.")
return
if not self.password.get():
messagebox.showerror(MESSAGE_TITLE, "You must enter a password.")
return
pdf_reader = PdfFileReader(path)
if pdf_reader.isEncrypted:
messagebox.showwarning(MESSAGE_TITLE, "File is already encrypted.")
return
pdf_writer = PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
pdf_writer.encrypt(self.password.get())
save_path = save_as_pdf(parent=self)
if not save_path:
messagebox.showerror(MESSAGE_TITLE,
"You must specify a file save path")
if save_path[-4:].lower() != ".pdf":
save_path += ".pdf"
with Path(save_path).open(mode="wb") as save_file:
pdf_writer.write(save_file)
messagebox.showinfo(MESSAGE_TITLE, "PDF encrypted.")
def rotate(input, output, pages, verbosity, rotate, **kwargs):
"""rotate selected pages
Rotate selected pages and outputs in new pdf
"""
source = PdfFileReader(input)
angle = {'left': -90, 'right': 90, 'inverted': 180}[rotate]
if pages is None:
pages = range(1, source.numPages)
selection = []
for page_num in range(1, source.getNumPages()):
real_page = page_num - 1
if verbosity >= 1:
click.echo(".", nl=False)
if verbosity >= 2:
click.echo("Extracting page %s" % page_num)
page = source.getPage(real_page)
if page_num in pages:
page._rotate(angle)
selection.append(page)
output_pdf = PdfFileWriter()
for page in selection:
output_pdf.addPage(page)
if verbosity >= 1:
click.echo("Writing %s" % output.name)
output_pdf.write(output)
def split(input, destination, pages, format, verbosity, **kwargs):
"""split pdf into single page file.
pdfcli split document.pdf --format page-%02d.pd -p 1,10-20
"""
source = PdfFileReader(input)
if pages is None:
pages = range(1, source.numPages + 1)
to_dir = Path(destination)
if not to_dir.exists():
to_dir.mkdir(parents=True)
for page_num in pages:
real_page = page_num - 1
if verbosity >= 1:
click.echo("Extracting page %s" % page_num)
# due to a bug PyPDF4 file need to be reopened
source = PdfFileReader(input)
dest_file = (to_dir / Path(format % page_num)).absolute()
page = source.getPage(real_page)
output_pdf = PdfFileWriter()
output_pdf.addPage(page)
with open(str(dest_file), "wb") as f:
output_pdf.write(f)
def join(ctx, inputs, output, verbosity, **kwargs):
"""join multiple pdf together in a single file.
pdfcli join files*.pdf -o joined.pdf
"""
if not inputs:
click.echo("No input files")
ctx.exit(1)
for input in inputs:
if not Path(input).exists():
if verbosity >= 1:
click.echo("File not found '%s'" % input, err=True)
ctx.exit(1)
out = PdfFileWriter()
for input in inputs:
source = PdfFileReader(input)
if verbosity >= 1:
click.echo("Adding %s" % input)
for page_num in range(0, source.numPages):
out.addPage(source.getPage(page_num))
out.write(output)
if verbosity >= 1:
click.echo("Writing %s" % output.name)
def splitPages(testNameNum, testPath, pageRanges, outputDirs):
temp = 1
key = 0
for bookmark in pageRanges:
f = open(testPath, 'rb')
pdf = PdfFileReader(f)
pdfWriter = PdfFileWriter()
#add watermark to original cover
origCover = pdf.getPage(0)
newCover = addWaterMark(origCover, key)
#put new cover on the front
pdfWriter.addPage(newCover)
for page in range(temp, bookmark):
pdfWriter.addPage(pdf.getPage(page))
outputFileName = genSectionFilePath(outputDirs, testNameNum[1],
testNameNum[0], key)
with open(outputFileName, 'wb') as out:
pdfWriter.write(out)
temp = bookmark
key += 1
f.close()
def add_watermark(file_path, file_stage, fileno):
"""把水印添加到pdf中"""
pdf_input = PdfFileReader(file_path)
if pdf_input.isEncrypted:
return
pdf_info = pdf_input.getDocumentInfo()
w, h = pdf_input.getPage(0).mediaBox[2:]
# 页面尺寸转换为毫米
page = (int(w) * 0.3528, int(h) * 0.3528)
# 创建水印文件
#mark = str(int(time.time()))+'.pdf'
#mark = os.path.join('d:/', mark)
mark = create_watermark(page, file_stage, fileno)
# 读入水印pdf文件
pageNum = pdf_input.getNumPages()
pdf_output = PdfFileWriter()
pdf_watermark = PdfFileReader(open(mark, 'rb'), strict=False)
for i in range(pageNum):
page = pdf_input.getPage(i)
page.mergePage(pdf_watermark.getPage(0))
pdf_output.addPage(page)
#print('merg 结束...' + str(datetime.now()))
# 加密码
pdf_output.encrypt(user_pwd='', owner_pwd='12345', use_128bit=True)
pdf_output.addMetadata(pdf_info)
pdf_output.write(open(file_path, 'wb'))
def unwatermark_pdf(input_file: str, wm_text: str, pages: Tuple = None):
"""
Removes watermark from the pdf file.
"""
pdf_reader = PdfFileReader(open(input_file, 'rb'), strict=False)
pdf_writer = PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
# If required for specific pages
if pages:
if str(page) not in pages:
continue
page = pdf_reader.getPage(page)
# Get the page content
content_object = page["/Contents"].getObject()
content = ContentStream(content_object, pdf_reader)
# Loop through all the elements page elements
for operands, operator in content.operations:
# Checks the TJ operator and replaces the corresponding string operand (Watermark text) with ''
if operator == b_("Tj"):
text = operands[0]
if isinstance(text, str) and text.startswith(wm_text):
operands[0] = TextStringObject('')
page.__setitem__(NameObject('/Contents'), content)
pdf_writer.addPage(page)
return True, pdf_reader, pdf_writer
def split_pages(testnamenum, test_path, page_ranges): temp = 1 key = 0 for bookmark in page_ranges: f = open(test_path, 'rb') pdf = PdfFileReader(f) pdf_writer = PdfFileWriter() #add watermark to original cover orig_cover = pdf.getPage(0) new_cover = add_watermark(orig_cover, key) #put new cover on the front pdf_writer.addPage(new_cover) for page in range(temp, bookmark): pdf_writer.addPage(pdf.getPage(page)) local_filename = generate_section_filepath(CONST_LOCAL, testnamenum, key) # output_filename = generate_section_filepath(output_dirs, testnamenum, key) with open(local_filename, 'wb') as out: pdf_writer.write(out) # upload_dropbox(local_filename, output_filename) temp = bookmark key += 1 f.close()
def ohin(obj_pages: List[int], save_path: str, input_path: str, img_path: str, position: List[float], img_size: List[float], pdf_size: str = "A4") -> None:
overlay_pdf_maker("overlay.pdf", img_path, position, img_size, pdf_size)
f_overlay = open("overlay.pdf", 'rb')
overlay = PdfFileReader(f_overlay).getPage(0)
f_target = open(input_path, 'rb')
reader = PdfFileReader(f_target)
num_pages = reader.getNumPages()
assert num_pages >= max(obj_pages)
for p in obj_pages:
page = reader.getPage(p - 1)
page.mergePage(overlay)
writer = PdfFileWriter()
for p in range(num_pages):
page = reader.getPage(p)
writer.addPage(page)
with open(save_path, 'wb') as f:
writer.write(f)
f_overlay.close()
f_target.close()
os.remove("overlay.pdf")
def main():
parser = argparse.ArgumentParser(
prog='ca6fix',
description=
"Fix some disappointmented points in Computer Architecture Quantitative Approach 6th Edition Japanese translation PDF file.",
usage='ca6fix -i ca6.pdf -o ca6_fixed.pdf',
add_help=True)
parser.add_argument('-i', '--input', help='input PDF file', required=True)
parser.add_argument('-o',
'--output',
help='output PDF file',
required=True)
args = parser.parse_args()
reader = PdfFileReader(args.input)
writer = PdfFileWriter()
for p in range(reader.getNumPages()):
page = reader.getPage(p)
writer.addPage(page)
writer.insertBlankPage(None, None, 4)
for index in outline:
add_outline(writer, index, 21)
writer.setPageLayout('/TwoPageRight')
writer.addMetadata({
'/Title':
'コンピュータアーキテクチャ 定量的アプローチ［第6版］',
'/Author':
'ジョン・L・ヘネシー, デイビッド・A・パターソン(著), 中條拓伯, 天野英晴, 鈴木 貢(訳)'
})
with open(args.output, 'wb') as fh:
writer.write(fh)
def extract(input, output, pages, verbosity, **kwargs):
"""extract one or multiple pages and build a new document.
pdfcli extract source.pdf -o clear.pdf -p 1,3-5
"""
source = PdfFileReader(input)
if pages is None:
pages = range(1, source.numPages)
selection = []
for page_num in pages:
real_page = page_num - 1
if verbosity >= 1:
click.echo(".", nl=False)
if verbosity >= 2:
click.echo("Extracting page %s" % page_num)
selection.append(source.getPage(real_page))
output_pdf = PdfFileWriter()
for page in selection:
output_pdf.addPage(page)
if verbosity >= 1:
click.echo("Writing %s" % output.name)
output_pdf.write(output)
def remove_watermark(wm_text, inputFile, outputFile):
from PyPDF4 import PdfFileReader, PdfFileWriter
from PyPDF4.pdf import ContentStream
from PyPDF4.generic import TextStringObject, NameObject
from PyPDF4.utils import b_
with open(inputFile, "rb") as f:
source = PdfFileReader(f, "rb")
output = PdfFileWriter()
for page in range(source.getNumPages()):
page = source.getPage(page)
content_object = page["/Contents"].getObject()
content = ContentStream(content_object, source)
for operands, operator in content.operations:
if operator == b_("Tj"):
text = operands[0]
if isinstance(text, str) and text.startswith(wm_text):
operands[0] = TextStringObject('')
page.__setitem__(NameObject('/Contents'), content)
output.addPage(page)
with open(outputFile, "wb") as outputStream:
output.write(outputStream)
def splitPdf(path='./input.pdf', N=5):
if not os.path.isfile(path):
return
pdfFileWriter = PdfFileWriter()
pdfFileReader = PdfFileReader(path) # 获取 PdfFileReader 对象
# 或者这个方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
numPages = pdfFileReader.getNumPages() # 文档总页数
print(numPages)
# fname = os.path.splitext(os.path.basename(path))[0]
fname = os.path.splitext(path)[0]
outFile1 = '{}p1_{}.pdf'.format(fname, N)
outFile2 = '{}p{}_{}.pdf'.format(fname, N + 1, numPages)
print(outFile1, outFile2)
if numPages > N:
# 第N页之前的页面，输出到一个新的文件中，即分割文档
for index in range(N - 1):
pageObj = pdfFileReader.getPage(index)
pdfFileWriter.addPage(pageObj)
# 添加完每页，再一起保存至文件中
pdfFileWriter.write(open(outFile1, 'wb'))
# 从第N页之后的页面，输出到一个新的文件中，即分割文档
for index in range(N, numPages):
pageObj = pdfFileReader.getPage(index)
pdfFileWriter.addPage(pageObj)
# 添加完每页，再一起保存至文件中
pdfFileWriter.write(open(outFile2, 'wb'))
def _merge_documents_PyPDF4(self, file_name, paths):
""" Merge documents. """
output = settings.SAVE_PATH / file_name
try:
pdf_writer = PdfFileWriter()
for file_path in paths:
if file_path:
pdf_reader = PdfFileReader(str(file_path), strict=False)
for page in range(pdf_reader.getNumPages()):
# Add each page to the writer object
pdf_writer.addPage(pdf_reader.getPage(page))
# Write out the merged PDF
output = settings.SAVE_PATH / file_name
with open(output, 'wb') as out:
pdf_writer.write(out)
return output
except utils.PdfReadError as error:
LogHandler.execution_log(error=error)
LogHandler.execution_log(
error=f'ERROR ON: {output.name.replace(".PDF", "")}')
return output
def merge(self):
save_path = save_as_pdf()
if not save_path:
messagebox.showerror(MESSAGE_TITLE, "You must specify a file save path.")
return
if save_path[-4:].lower() != ".pdf":
save_path += ".pdf"
pdf_writer = PdfFileWriter()
for item in self.tree.get_children():
item_values = self.tree.item(item, option="values")
path = item_values[1]
pdf_reader = PdfFileReader(path)
if pdf_reader.isEncrypted and not decrypt(pdf_reader, MESSAGE_TITLE):
messagebox.showwarning(MESSAGE_TITLE, f"{item_values[0]} could not be decrypted. It will not be "
f"included in the merge.")
continue
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
with Path(save_path).open(mode="wb") as save_file:
pdf_writer.write(save_file)
messagebox.showinfo(MESSAGE_TITLE, "PDF Merged")
def rotate_pdf(self, path: str, page_num: str, rotate_type: str,
outpdf: str):
"""
旋转pdf页面
path； 需要处理的pdf文件路径
page_num: 页面编号
rotate_type: 0或1，为顺时针或逆时针旋转
outpdf: 输出pdf名称，不包含路径
"""
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(path)
# 顺时针旋转90°
if rotate_type == "0":
page_1 = pdf_reader.getPage(int(page_num)).rotateClockwise(90)
pdf_writer.addPage(page_1)
elif rotate_type == "1":
# 逆时针旋转90°
page_2 = pdf_reader.getPage(
int(page_num)).rotateCounterClockwise(90)
pdf_writer.addPage(page_2)
else:
return "输入错误，请重新输入！"
with open(self.processed + outpdf, "wb") as f:
pdf_writer.write(f)
# print("旋转页面完成！")
return "旋转页面完成！"
def put_watermark(input_pdf, output_pdf, watermark):
# reads the watermark pdf file through
# PdfFileReader
watermark_instance = PdfFileReader(watermark)
# fetches the respective page of
# watermark(1st page)
watermark_page = watermark_instance.getPage(0)
# reads the input pdf file
pdf_reader = PdfFileReader(input_pdf)
# It creates a pdf writer object for the
# output file
pdf_writer = PdfFileWriter()
# iterates through the original pdf to
# merge watermarks
for page in range(pdf_reader.getNumPages()):
page = pdf_reader.getPage(page)
# will overlay the watermark_page on top
# of the current page.
page.mergePage(watermark_page)
# add that newly merged page to the
# pdf_writer object.
pdf_writer.addPage(page)
with open(output_pdf, 'wb') as out:
# writes to the respective output_pdf provided
pdf_writer.write(out)
def readWritePdf():
with open("./Python 面试题.pdf", "rb") as f:
pdfReader = PdfFileReader(f)
pdfWriter = PdfFileWriter()
page = pdfReader.getPage(0)
pdfWriter.addPage(page)
with open("./new.pdf", "wb") as f1:
pdfWriter.write(f1)
def rotate_pdf(path, degrees, output):
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
original = pdf_reader.getPage(page)
pdf_writer.addPage(original.rotateClockwise(int(degrees)))
pdf_writer.write(output)
def merge(pdf_input, mark):
pageNum = pdf_input.getNumPages()
pdf_output = PdfFileWriter()
pdf_watermark = PdfFileReader(open(mark, 'rb'), strict=False)
for i in range(pageNum):
page = pdf_input.getPage(i)
page.mergePage(pdf_watermark.getPage(0))
pdf_output.addPage(page)
return pdf_output
def join_pdfs(paths, output):
pdf_writer = PdfFileWriter()
for path in paths:
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
pdf_writer.write(output)
def mergePdfFiles(paths, outputPath):
pdf_writer = PdfFileWriter()
for path in paths:
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
with open(outputPath, 'wb') as out:
pdf_writer.write(out)
def extractPdfPage(path, pageIndex, extractedPdfName):
pdf = PdfFileReader(path)
for page in range(pdf.getNumPages()):
if page != pageIndex:
continue
pdf_writer = PdfFileWriter()
pdf_writer.addPage(pdf.getPage(page))
with open(extractedPdfName, 'wb') as output_pdf:
pdf_writer.write(output_pdf)
def split_pdf_by_page(input_pdf_filepath, output_pdf_dir):
pdf_reader = getPdfReader(input_pdf_filepath)
# 获取pdf页数
page_count = pdf_reader.getNumPages()
# 获取pdf第n页的内容
for page_num in range(page_count):
writer = PdfFileWriter()
writer.addPage(pdf_reader.getPage(page_num))
#temp = NamedTemporaryFile(prefix=str(page_num), suffix=".pdf", delete=False)
tempname = '{}/{}.pdf'.format(output_pdf_dir, page_num)
writer.write(open(tempname, 'wb'))
def add_encryption(input_pdf, output_pdf, password):
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(input_pdf)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
pdf_writer.encrypt(user_pwd=password, owner_pwd=None, use_128bit=True)
with open(output_pdf, 'wb') as out:
pdf_writer.write(out)
def _insert_page_to_pdf(original: BinaryIO, page: PageObject,
page_index: int) -> PdfFileWriter:
input = PdfFileReader(original)
output = PdfFileWriter()
for i in range(input.getNumPages()):
if i != page_index:
p = input.getPage(i)
output.addPage(p)
else:
output.addPage(page)
return output
def merge_pdfs(paths, output):
pdf_writer = PdfFileWriter()
for path in paths:
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
# Add each page to the writer object
pdf_writer.addPage(pdf_reader.getPage(page))
# Write out the merged PDF
with open(output, 'wb') as out:
pdf_writer.write(out)
def split_to_single_pages(path, name_of_split):
""" Splits one document into single pages
"""
pdf = PdfFileReader(path)
for page in range(pdf.getNumPages()):
pdf_writer = PdfFileWriter()
pdf_writer.addPage(pdf.getPage(page))
output = f'{name_of_split}{page}.pdf'
with open(output, 'wb') as output_pdf:
pdf_writer.write(output_pdf)
def split_pdf(input_path, page_ranges, output_name):
for page_range in page_ranges:
input_pdf = PdfFileReader(input_path)
pdf_writer = PdfFileWriter()
start, stop = format_range(page_range)
for page in range(start, stop):
pdf_writer.addPage(input_pdf.getPage(page))
output = f"{output_name}_p{page_range}.pdf"
with open(output, 'wb') as output_pdf:
pdf_writer.write(output_pdf)
def remove_page(pdf_path, page_numbers):
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(pdf_path, 'rb')
i = 0
for page in [
pdf_reader.getPage(i) for i in range(pdf_reader.getNumPages())
]:
if i in page_numbers:
pdf_writer.addPage(page)
i += 1
with open('Resultant_PDF_After_Extraction.pdf', 'wb') as fh:
pdf_writer.write(fh)
