def get_metadata(file, key):
with open(file, 'rb') as pdf:
pdf_reader = PdfFileReader(pdf)
metadata = pdf_reader.getDocumentInfo()
print(metadata)
property = metadata.get('/' + key, 'Key Error')
return property
def test_merge_pdf_output(self):
image_paths = [
'tests/pdf_samples/jpeg_w_350.jpg',
'tests/pdf_samples/pdf_sample_A Sample PDF_loremIpsum_pages_01.pdf',
'tests/pdf_samples/pdf_sample_b_pages_01.pdf',
'tests/pdf_samples/pdf_sample_dummy_w3c_pages_01.pdf',
'tests/pdf_samples/pdf_sample_googledocs_image_pages_02.pdf',
## the next PDF fail to read - invalid literal for int() with base 10: b'F-1.4' !!!
# 'tests/pdf_samples/pdf_sample_googlesheet_pages_02.pdf',
'tests/pdf_samples/pdf_sample_libreoffice_exported_ISO19005_pages_02.pdf',
'tests/pdf_samples/pdf_sample_libreoffice_exported_format_FDF_pages_02.pdf',
'tests/pdf_samples/pdf_sample_libreoffice_exported_hibrid_format_pages_02.pdf',
'tests/pdf_samples/pdf_sample_libreoffice_exported_not_hybrid_ISO19005_pages_02.pdf',
'tests/pdf_samples/pdf_sample_pages_01.pdf',
('tests/pdf_samples/pdf_sample_readthedocs_pdf_networkdays_pages_019.pdf', (0, 2)),
'tests/pdf_samples/pdf_sample_text_edit_macos_pages_01.pdf',
'tests/pdf_samples/pdf_sample_wikimedia_org_pages_01.pdf',
'tests/pdf_samples/sample_pdf_commandline_xhtml2pdf_generated_pages_01.pdf',
'tests/pdf_samples/issue_repo_pypdf4.pdf',
'tests/pdf_samples/issue_repo_pypdf4_test.pdf',
]
m = MergeToPdf(paths_list=image_paths, output_file_path='test_merged_pdf.pdf')
m.merge_pdfs()
with open('test_merged_pdf.pdf', "rb") as outputfile:
generated_pdf = PdfFileReader(outputfile)
pages = generated_pdf.getNumPages()
self.assertEqual(pages, 23)
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 pdf_meta(filename):
with open(filename,'rb') as pdf:
pdfFile = PdfFileReader(pdf)
doc = pdfFile.getDocumentInfo()
print(f'[***] PDF MetaData: {str(filename)}')
for item in doc:
print(f'[++] {item} : {doc[item]}')
def extract_information(self, pdf_path, link):
with open(pdf_path, 'rb') as f:
pdf = PdfFileReader(f)
information = pdf.getDocumentInfo()
number_of_pages = pdf.getNumPages()
try:
readable1 = extract_date(
information.getText("/CreationDate").split('-'))
readable2 = extract_date(
information.getText("/ModDate").split('-'))
except:
readable1 = None
readable2 = None
info = {
"author": information.author,
"creator": information.creator,
"producer": information.producer,
"subject": information.subject,
"title": information.title,
"creation_date": readable1,
"modification_date": readable2,
"number_of_pages": number_of_pages,
"download_link": link
}
return pdf_path, info
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 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 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 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 imprimir_metadata(nombreArchivo):
with open(nombreArchivo, 'rb') as pdf:
pdf_file = PdfFileReader(pdf)
doc_info = pdf_file.getDocumentInfo()
print(f'[*] MetaData PDF para el archivo: {str(nombreArchivo)}')
for meta_item in doc_info:
print(f'[+] {meta_item}: {doc_info[meta_item]}')
def pdf_to_txt(file):
text = ''
pdfReader = PdfFileReader(file)
for i in range(pdfReader.numPages):
page = pdfReader.getPage(i)
text += page.extractText()
return text.lower()
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 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 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 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)
async def add_watermark(file_path,stage,fileno):
"""把水印添加到pdf中"""
#print('文件开始...' + str(datetime.now()))
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
#create_watermark(page,stage,fileno)
mark = create_watermark(page, stage, fileno)
#mark=await asyncio.get_event_loop().run_in_executor(None, create_watermark, page, stage, fileno)
# 读入水印pdf文件
#mark='d:/mark.pdf'
pdf_output = await asyncio.get_event_loop().run_in_executor(None, merge, pdf_input, mark)
#pdf_output = merge(file_path, mark)
# 加密码
pdf_output.encrypt(user_pwd='', owner_pwd='12345',use_128bit=True)
pdf_output.addMetadata(pdf_info)
# 可以更改一些属性值
#pdf_output.addMetadata(info)
#savepdf(pdf_output, file_path)
await asyncio.get_event_loop().run_in_executor(None, savepdf, pdf_output, file_path)
def print_meta(filename):
with open(filename, 'rb') as pdf:
pdf_file = PdfFileReader(pdf)
doc_info = pdf_file.getDocumentInfo()
print(f'[*] PDF MetaData For: {str(filename)}')
for meta_item in doc_info:
print(f'[+] {meta_item}: {doc_info[meta_item]}')
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 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 make_booklet(input_name, output_name, blanks=0):
reader = PdfFileReader(open(input_name, "rb"))
pages = [reader.getPage(p) for p in range(0, reader.getNumPages())]
for i in range(0, blanks):
pages.insert(0, None)
sheets = build_booklet(pages)
writer = PdfFileWriter()
p0 = reader.getPage(0)
input_width = p0.mediaBox.getWidth()
output_width = input_width * 2
input_height = p0.mediaBox.getHeight()
output_height = input_height
page_size = (output_width, output_height)
# We want to group fronts and backs together.
for sheet in sheets:
add_double_page(writer, page_size, sheet.back)
for sheet in sheets:
add_double_page(writer, page_size, sheet.front)
writer.write(open(output_name, "wb"))
print_instructions(sheets)
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 generate_pdf(template_name, request, contexte, extra_pdf_files=None):
template = get_template(template_name)
contexte.update({
'MEDIA_ROOT': settings.MEDIA_ROOT,
'cdate': now(),
'user': request.user
})
html = template.render(contexte)
try:
result = BytesIO()
pisa_status = pisa.CreatePDF(html, result)
if not pisa_status.err:
if extra_pdf_files:
from PyPDF4 import PdfFileWriter, PdfFileReader
output = PdfFileWriter()
append_pdf(PdfFileReader(result), output)
result = BytesIO()
for pdf_file in extra_pdf_files:
try:
append_pdf(PdfFileReader(pdf_file), output)
except Exception:
return render(request, "pdf_error.html", {
'pdf': pdf_file,
'error': traceback.format_exc()
})
output.write(result)
return http.HttpResponse(result.getvalue(),
content_type='application/pdf')
except Exception as e:
logger = logging.getLogger(__name__)
logger.exception(e)
return http.HttpResponse('Gremlins ate your pdf! %s' % cgi.escape(html))
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 get_info(input_file: str):
"""
Extracting the file info
"""
# If PDF is encrypted the file metadata cannot be extracted
with open(input_file, 'rb') as pdf_file:
pdf_reader = PdfFileReader(pdf_file, strict=False)
output = {
"File": input_file,
"Encrypted": ("True" if pdf_reader.isEncrypted else "False")
}
if not pdf_reader.isEncrypted:
info = pdf_reader.getDocumentInfo()
num_pages = pdf_reader.getNumPages()
output["Author"] = info.author
output["Creator"] = info.creator
output["Producer"] = info.producer
output["Subject"] = info.subject
output["Title"] = info.title
output["Number of pages"] = num_pages
# To Display collected metadata
print(
"## File Information ##################################################"
)
print("\n".join("{}:{}".format(i, j) for i, j in output.items()))
print(
"######################################################################"
)
return True, output
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 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 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 on_file_selected(self):
if self.file_selector.getpath():
pdf_reader = PdfFileReader(self.file_selector.getpath())
if pdf_reader.isEncrypted and not decrypt(pdf_reader,
MESSAGE_TITLE):
self.page_count_text.set("")
self.file_selector.clear()
else:
self.page_count_text.set(pdf_reader.getNumPages())
def extract(fileobj):
pfr = PdfFileReader(fileobj, strict=False)
text = "" if fmt == "string" else []
for pg in range(pfr.getNumPages()):
if fmt == "string":
text += pfr.getPage(pg).extractText()
else:
text.append(pfr.getPage(pg).extractText())
return text
