def __init__(self, id: int):
self.report_model = Report.objects.get(report_id=id)
self.pdf_writer = PyPDF2.PdfFileWriter()
import PyPDF2, os
#it can only extract text from pdf and not other data
#and have limited set of actions
pdf1File = open('meetingminutes.pdf', 'rb') #open in read binary
reader1 = PyPDF2.PdfFileReader(pdf1File) #reading first pdf
pdf2File = open('meetingminutes2.pdf', 'rb')
reader2 = PyPDF2.PdfFileReader(pdf2File) #reading second pdf
writer = PyPDF2.PdfFileWriter(
) #writer variable for the pdf which is created by python only
for page_num in range(reader1.numPages): #going through each page
page = reader1.getPage(page_num) #getting page
writer.addPage(page) #writing to new pdf
for page_num in range(reader2.numPages): #taking second pdf's all pages
page = reader2.getPage(page_num) #getting each page
writer.addPage(page) #writing(appending) to the new(created) pdf
outputfile = open('CombinedPDFs.pdf', 'wb') #write binary
writer.write(outputfile)
outputfile.close()
pdf1File.close()
pdf2File.close()
def __init__(self, in_file: str, out_file: str):
self.__reader = PyPDF2.PdfFileReader(in_file, strict=False)
self.__writer = PyPDF2.PdfFileWriter()
self.__writer.cloneReaderDocumentRoot(self.__reader)
self.out_file = out_file
def add_files_to_pdf(
self,
files: list = None,
target_document: str = None,
) -> None:
"""Add images and/or pdfs to new PDF document
Image formats supported are JPEG, PNG and GIF.
The file can be added with extra properties by
denoting `:` at the end of the filename.add()
Supported extra properties are:
- for PDF, the page numbers to be included in the new PDF document
- for images, the position of the image in the new PDF document
**Examples**
**Robot Framework**
.. code-block:: robotframework
***Settings***
Library RPA.PDF
***Tasks***
Add files to pdf
${files}= Create List
... ${TESTDATA_DIR}${/}invoice.pdf
... ${TESTDATA_DIR}${/}approved.png:center
... ${TESTDATA_DIR}${/}robot.pdf:1
... ${TESTDATA_DIR}${/}approved.png:x=0,y=0
... ${TESTDATA_DIR}${/}robot.pdf:2-10,15
... ${TESTDATA_DIR}${/}approved.png
Add Files To PDF ${files} newdoc.pdf
**Python**
.. code-block:: python
from RPA.PDF import PDF
pdf = PDF()
list_of_files = [
'invoice.pdf',
'approved.png:center',
'robot.pdf:1',
'approved.png:x=0,y=0',
]
def example_keyword():
pdf.add_files_to_pdf(
files=list_of_files,
target_document="output/output.pdf"
)
:param files: list of filepaths to add into PDF (can be either images or PDFs)
:param target_document: filepath of target PDF
"""
writer = PyPDF2.PdfFileWriter()
for f in files:
file_to_add = Path(f)
namesplit = file_to_add.name.rsplit(":", 1)
basename = namesplit[0]
parameters = namesplit[1] if len(namesplit) == 2 else None
file_to_add = file_to_add.parent / basename
image_filetype = imghdr.what(str(file_to_add))
self.logger.info("File %s type: %s" %
(str(file_to_add), image_filetype))
if basename.endswith(".pdf"):
reader = PyPDF2.PdfFileReader(str(file_to_add), strict=False)
pagecount = reader.getNumPages()
pages = self._get_pages(pagecount, parameters)
for n in pages:
try:
page = reader.getPage(n - 1)
writer.addPage(page)
except IndexError:
self.logger.warning("File %s does not have page %d" %
(file_to_add, n))
elif image_filetype in ["png", "jpg", "jpeg", "gif"]:
temp_pdf = os.path.join(tempfile.gettempdir(), "temp.pdf")
pdf = FPDF()
pdf.set_margin(0)
pdf.add_page()
x, y, width, height = self._get_image_coordinates(
str(file_to_add), parameters)
pdf.image(name=file_to_add, x=x, y=y, w=width, h=height)
pdf.output(name=temp_pdf)
reader = PyPDF2.PdfFileReader(temp_pdf)
writer.addPage(reader.getPage(0))
with open(target_document, "wb") as f:
writer.write(f)
import PyPDF2
import os
import sys
if len(sys.argv) != 4:
raise RuntimeError('Usage {} watermark.pdf source.pdf output.pdf'.format(
sys.argv[0]))
watermark_path = sys.argv[1]
if not os.path.isfile(watermark_path):
raise RuntimeError('Watermark file {} not found'.format(watermark_path))
watermark = PyPDF2.PdfFileReader(open(watermark_path, 'rb'))
source_path = sys.argv[2]
if not os.path.isfile(source_path):
raise RuntimeError('Source file {} not found'.format(source_path))
source = PyPDF2.PdfFileReader(open(source_path, 'rb'))
watermark_page = watermark.getPage(0)
pdf_output = PyPDF2.PdfFileWriter()
for pageNum in range(0, source.numPages):
pageObj = source.getPage(pageNum)
pageObj.mergePage(watermark_page)
pdf_output.addPage(pageObj)
output_file = open(sys.argv[3], 'wb')
pdf_output.write(output_file)
output_file.close()
def exportPdf(fin, abpath_out, annotations):
'''Export PDF with annotations.
Args:
fin (str): abspath to input PDF file.
abpath_out (str): abspath to output PDF file.
annotations (dict): annotation info. See import_mendeley.py
getHighlights() for more info.
'''
try:
inpdf = PyPDF2.PdfFileReader(open(fin, 'rb'))
if inpdf.isEncrypted:
# PyPDF2 seems to think some files are encrypted even
# if they are not. We just ignore the encryption.
# This seems to work for the one file where I saw this issue
#inpdf._override_encryption = True
#inpdf._flatten()
# UPDATE: trying to decrypt takes a lot of time,
# as this rarely happens to academic docs I'm skipping this
# and simply treat as fail
#raise Exception("Skip encrypt")
return
except IOError:
LOGGER.warning('Could not open pdf file %s' %fin)
# retain meta data
meta = inpdf.getDocumentInfo()
outpdf = PyPDF2.PdfFileWriter()
outpdf.addMetadata(meta)
highlights=annotations.get('highlights',None)
if highlights is None:
hlpages=[]
else:
hlpages=list(highlights.keys())
hlpages.sort()
notes=annotations.get('notes',None)
if notes is None:
ntpages=[]
else:
ntpages=list(notes.keys())
ntpages.sort()
#----------------Loop through pages----------------
pages=range(1,inpdf.getNumPages()+1)
for pii in pages:
inpg = inpdf.getPage(pii-1)
#----------------Process highlights----------------
if pii in hlpages:
for hjj in highlights[pii]:
# Changes suggested by matteosecli: add author of highlight:
anno = pdfannotation.createHighlight(hjj["rect"],
author=hjj['author'],
cdate=hjj["cdate"], color=hjj['color'])
inpg=pdfannotation.addAnnotation(inpg,outpdf,anno)
#------------------Process notes------------------
if pii in ntpages:
for njj in notes[pii]:
note = pdfannotation.createNote(njj["rect"], \
contents=njj["content"], author=njj["author"],\
cdate=njj["cdate"])
inpg=pdfannotation.addAnnotation(inpg,outpdf,note)
outpdf.addPage(inpg)
#-----------------------Save-----------------------
if os.path.isfile(abpath_out):
os.remove(abpath_out)
with open(abpath_out, mode='wb') as fout:
outpdf.write(fout)
LOGGER.debug('Exported annotated pdf.')
return
def rotate_page(
self,
pages: ListOrString,
source_path: str = None,
output_path: str = None,
clockwise: bool = True,
angle: int = 90,
) -> None:
"""Rotate pages in source PDF document and save to target PDF document.
If no source path given, assumes a PDF is already opened.
**Examples**
**Robot Framework**
.. code-block:: robotframework
***Settings***
Library RPA.PDF
***Tasks***
Example Keyword
Rotate Page
... source_path=/tmp/sample.pdf
... output_path=/tmp/output.pdf
... pages=5
**Python**
.. code-block:: python
from RPA.PDF import PDF
pdf = PDF()
def rotate_page():
pages = pdf.rotate_page(
source_path="/tmp/sample.pdf",
output_path="/tmp/output.pdf",
pages=5
)
:param pages: page numbers to extract from PDF (numbers start from 0).
:param source_path: filepath to the source pdf.
:param output_path: filepath to the target pdf, stored by default
to `output_directory`.
:param clockwise: directorion that page will be rotated to, default True.
:param angle: number of degrees to rotate, default 90.
"""
# TODO: don't save to a new file every time
self.switch_to_pdf(source_path)
reader = self.ctx.active_pdf_document.reader
writer = PyPDF2.PdfFileWriter()
output_filepath = Path(
output_path) if output_path else self.default_output
pages = self._get_page_numbers(pages, reader)
for page in range(reader.getNumPages()):
source_page = reader.getPage(int(page))
if page in pages:
if clockwise:
source_page.rotateClockwise(int(angle))
else:
source_page.rotateCounterClockwise(int(angle))
else:
source_page = reader.getPage(int(page))
writer.addPage(source_page)
with open(str(output_filepath), "wb") as f:
writer.write(f)
pdf_reader.getIsEncrypted() # False
pdf_reader.getNumPages() # It will return number of pages in pdf # 3
page1 = pdf_reader.getPage(0)
page1.extractText()
page2 = pdf_reader.getPage(1)
page2.extractText()
# Append Write or Merge PDf
pdf_writer = pdf.PdfFileWriter()
pdf_writer.addPage(page1)
pdf_writer.addPage(page2)
output = open('E:\Projects\Extract Text From PDF File\Pages.pdf','wb')
pdf_writer.write(output)
output.close()
def pdf_replace(request):
if request.method == 'POST':
# 如果用户通过POST提交
form = PdfReplaceForm(request.POST, request.FILES)
if form.is_valid():
# 获取需要插入的PDF页面文件1
f1 = form.cleaned_data['file1']
# 获取需要被替换的文件2
f2 = form.cleaned_data['file2']
# 获取替换页码数
page = form.cleaned_data['page']
# 获取文件2总页数
pdfFileObj = PyPDF2.PdfFileReader(f2)
total_page = pdfFileObj.getNumPages()
# 获取文件2第一部分-人为可读页码
page_start = 1
page_end = page - 1
pdfOutputFile1 = open(os.path.join('media', 'part_1.pdf'), 'wb+')
# 利用PyPDF2创建新的Pdf Writer
pdfWriter = PyPDF2.PdfFileWriter()
for page_num in range(page_start, page_end + 1):
# pdf文档页码对象编码是从0开始，所以减一
page_index = int(page_num) - 1
# 利用PyPDF2提取页码对象
pageObj = pdfFileObj.getPage(page_index) # 从0编码
# 添加已读取的页面对象
pdfWriter.addPage(pageObj)
pdfWriter.write(pdfOutputFile1)
pdfOutputFile1.close()
# 获取文件2第2部分-人为可读页码
page_start = page + 1
page_end = total_page
pdfOutputFile2 = open(os.path.join('media', 'part_2.pdf'), 'wb+')
# 利用PyPDF2创建新的Pdf Writer
pdfWriter = PyPDF2.PdfFileWriter()
for page_num in range(page_start, page_end + 1):
# pdf文档页码对象编码是从0开始，所以减一
page_index = int(page_num) - 1
# 利用PyPDF2提取页码对象
pageObj = pdfFileObj.getPage(page_index) # 从0编码
# 添加已读取的页面对象
pdfWriter.addPage(pageObj)
pdfWriter.write(pdfOutputFile2)
pdfOutputFile2.close()
f2_part_1 = open(os.path.join('media', 'part_1.pdf'), 'rb+')
f2_part_2 = open(os.path.join('media', 'part_2.pdf'), 'rb+')
# 创建PDF文件合并对象，添加合并文件
pdfMerger = PyPDF2.PdfFileMerger()
pdfMerger.append(PyPDF2.PdfFileReader(f2_part_1))
pdfMerger.append(PyPDF2.PdfFileReader(f1))
pdfMerger.append(PyPDF2.PdfFileReader(f2_part_2))
# 将合并文件对象写入到replaced_file.pdf
with open(os.path.join('media', 'replaced_file.pdf'),
'wb') as pdfOutputFile:
pdfMerger.write(pdfOutputFile)
# 打开合并的replaced_file.pdf，通过HttpResponse输出
response = FileResponse(
open(os.path.join('media', 'replaced_file.pdf'), 'rb'))
response['content_type'] = "application/octet-stream"
response[
'Content-Disposition'] = 'attachment; filename="replaced_file.pdf"'
return response
else:
# 如果通过POST提交，但表单未通过验证
form = PdfReplaceForm()
else:
# 如果用户没有通过POST，提交生成空表单
form = PdfReplaceForm()
return render(request, 'pdf/pdf_replace.html', {'form': form})
): # Loop, for each page of the input pdf
page = input_reader.getPage(
page_num
) # Creating the Page Object for each page of the input pdf
page.mergePage(
watermark_page
) # Merging pages using the method of the Page Object
writer_object.addPage(
page
) # Passing the merged page to the writer object with addPage method
with open(
'super_watermarked.pdf', 'wb'
) as result_file: # Creating the new archive, with merged page
writer_object.write(
result_file
) # Writing each merged page into new archive
# watermark('super.pdf', 'wtr.pdf.pdf')
template_pdf = PyPDF2.PdfFileReader(open('super.pdf', 'rb'))
watermark_pdf = PyPDF2.PdfFileReader(open('wtr.pdf.pdf', 'rb'))
writer_object = PyPDF2.PdfFileWriter()
for i in range(template_pdf.numPages):
page = template_pdf.getPage(i)
page.mergePage(watermark_pdf.getPage(0))
writer_object.addPage(page)
with open('watermarked_output.pdf', 'wb') as file:
writer_object.write(file)
import PyPDF2 as ppdf
pdffile1 = open('meetingminutes1.pdf', 'rb')
reader1 = ppdf.PdfFileReader(pdffile1)
#print(reader.numPages)
#page=reader.getPage(0);
#print(page.extractText())
pdffile2 = open('meetingminutes2.pdf', 'rb')
reader2 = ppdf.PdfFileReader(pdffile2)
writer = ppdf.PdfFileWriter()
for p1 in range(reader1.numPages):
if p1 % 2:
page = reader1.getPage(p1 - 1)
else:
page = reader1.getPage(p1)
writer.addPage(page)
for p2 in range(reader2.numPages):
page = reader2.getPage(p2)
writer.addPage(page)
outputfile = open('combined.pdf', 'wb')
writer.write(outputfile)
pdffile1.close()
pdffile2.close()
def split_pdf_file(self):
if not self.pdf_name.text():
error_msg = QtWidgets.QMessageBox(self)
error_msg.setIcon(QtWidgets.QMessageBox.Warning)
error_msg.setText('For processing please choose pdf-file!')
error_msg.setWindowTitle('Error split pdf-file')
error_msg.exec_()
return
if not self.export_directory.text():
error_msg = QtWidgets.QMessageBox(self)
error_msg.setIcon(QtWidgets.QMessageBox.Warning)
error_msg.setText('For processing please choose export directory!')
error_msg.setWindowTitle('Error split pdf-file')
error_msg.exec_()
return
self.progressBar.show()
self.label_help.hide()
self.label_qty.show()
try:
pdfFileObj = open(self.pdf_name.text(), 'rb')
except Exception:
error_msg = QtWidgets.QMessageBox(self.centralwidget)
error_msg.setIcon(QtWidgets.QMessageBox.Warning)
error_msg.setText('Error open pdf-file!')
error_msg.setWindowTitle('Error split pdf-file')
error_msg.exec_()
return
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
self.progressBar.setRange(0, pdfReader.numPages - 1)
maxVal = self.progressBar.maximum()
writer = PyPDF2.PdfFileWriter()
qty_suppl = 0
for i in range(0, pdfReader.numPages):
self.progressBar.setValue(i + (maxVal - i) / 100)
QtWidgets.QApplication.processEvents()
pageObj = pdfReader.getPage(i)
check_text = pageObj.extractText().split()
if len(check_text) > 5 and check_text[1] == '10.11.98':
if i == 0:
suppl_no = list(
filter(lambda f: len(f) == 10 and f[:2] == '26',
check_text))[0][-5:]
writer.addPage(pdfReader.getPage(i))
else:
output_file = '\\Reconciliation_act~Acc_act~60~' + suppl_no + '~' + datetime.date.today(
).strftime('%Y%m%d') + '.pdf'
try:
with open(self.export_directory.text() + output_file,
'wb') as outfile:
writer.write(outfile)
qty_suppl += 1
self.label_qty.setText('Processed: ' +
str(qty_suppl) +
' supplier(s)')
QtWidgets.QApplication.processEvents()
except Exception:
error_msg = QtWidgets.QMessageBox(self.centralwidget)
error_msg.setIcon(QtWidgets.QMessageBox.Warning)
error_msg.setText('Error save pdf-file!')
error_msg.setWindowTitle('Error split pdf-file')
error_msg.exec_()
return
outfile.close()
suppl_no = list(
filter(lambda f: len(f) == 10 and f[:2] == '26',
check_text))[0][-5:]
writer = PyPDF2.PdfFileWriter()
writer.addPage(pdfReader.getPage(i))
else:
if len(check_text) > 5:
writer.addPage(pdfReader.getPage(i))
output_file = '\\Reconciliation_act~Acc_act~60~' + suppl_no + '~' + datetime.date.today(
).strftime('%Y%m%d') + '.pdf'
try:
with open(self.export_directory.text() + output_file,
'wb') as outfile:
writer.write(outfile)
outfile.close()
qty_suppl += 1
self.label_qty.setText('Processed: ' + str(qty_suppl) +
' supplier(s)')
except Exception:
error_msg = QtWidgets.QMessageBox(self.centralwidget)
error_msg.setIcon(QtWidgets.QMessageBox.Warning)
error_msg.setText('Error save pdf-file!')
error_msg.setWindowTitle('Error split pdf-file')
error_msg.exec_()
return
success_msg = QtWidgets.QMessageBox(self)
success_msg.setIcon(QtWidgets.QMessageBox.Information)
success_msg.setText('Processed: ' + str(qty_suppl) + ' supplier(s)')
QtWidgets.QApplication.processEvents()
success_msg.setWindowTitle('Success split pdf-file')
success_msg.exec_()
self.progressBar.hide()
self.label_help.show()
def lambda_handler(event, context):
# Get the object from the event and show its content type
bucket = event['Records'][0]['s3']['bucket']['name']
key = urllib.parse.unquote_plus(event['Records'][0]['s3']['object']['key'],
encoding='utf-8')
print(bucket, key)
try:
# バケツの取得
response = s3.get_object(Bucket=bucket, Key=key)
# レスポンスの内容の確認
if response['ContentType'] != 'application/zip' and response[
'ContentType'] != 'application/x-zip-compressed' and response[
'ContentType'] != 'binary/octet-stream':
return 'Unsupported extension. : ' + response['ContentType']
# src/yyyymmddhhmmssfff/filename.zip
keyItems = key.split('/')
createDate = keyItems[1]
zipname = keyItems[2]
# 拡張をpdfに変更
name, ext = getNameAndExtention(zipname)
# ワークフォルダと格納パスの作成
global basedir
pdfname = name + '.pdf' # pdfのファイル名
zipPath = os.path.join(basedir, createDate + "_" + zipname) # zipの保存名
imgPath = os.path.join(basedir, 'img', createDate, name) # imgの解凍先
pdfPath = os.path.join(basedir, createDate + "_" + pdfname) # pdfの保存名
pdfkey = '/'.join(['dst', createDate, pdfname]) # pdfの保存key
os.makedirs(imgPath, exist_ok=True)
print(zipPath)
print(imgPath)
print(pdfPath)
# S3から/tmpにダウンロード
s3_client.download_file(bucket, key, zipPath)
# 解凍処理
unzip(zipPath, imgPath, ext)
# 画像を検索
imgList = []
searchImg(imgList, imgPath)
# imageをPDFに置き換え
pdflist = []
changeImg2Pdf(imgList, pdflist)
# PDFの読み書き
pdfWriter = PyPDF2.PdfFileWriter()
margePdf(pdflist, pdfWriter)
writePdf(pdfWriter, pdfPath)
# S3にPDFをアップロード
s3_client.upload_file(pdfPath, bucket, pdfkey)
return 'success!!!'
except Exception as e:
print(e)
print(
'Error getting object {} from bucket {}. Make sure they exist and your bucket is in the same region as this function.'
.format(key, bucket))
raise e
file1 = open(file_path, 'rb')
read1 = PyPDF2.PdfFileReader(file1)
page1 = read1.getPage(0)
#page.rotateClockwise(90)
#pdf = PdfFileReader(file('Java Printing.pdf'))
page = read1.getPage(0).mediaBox
if page.getUpperRight_x() - page.getUpperLeft_x() > page.getUpperRight_y(
) - page.getLowerRight_y():
print('Landscape')
else:
print('Portrait')
page1.rotateClockwise(90)
# save (rotated) page
file2 = PyPDF2.PdfFileWriter()
file2.addPage(page1)
result = open('Balances.pdf', 'wb')
file2.write(result)
result.close()
file1.close()
# read from pdf
fp = open('Balances.pdf', 'rb')
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
rsrcmgr = PDFResourceManager()
laparams = LAParams()
def send_public_report(rating_decision_obj):
"""
Download public report from AWS S3 and send to issuer.
:param RatingDecision: rating decision object
"""
target_file = None
# Send this file to the issuer
# Fetch uploaded files from AWS S3
document = get_public_report(rating_decision_obj)
try:
legal_name = rating_decision_obj.issuer.legal_name
legal_name = str(
unicodedata.normalize('NFKD',
legal_name).encode('ASCII',
'ignore').decode('utf-8'))
target_file = (legal_name + ' draft report' + ' (' +
datetime.datetime.today().strftime('%Y-%m-%d, %H%M') +
").pdf")
filepath = AWS_ANALYTICAL_MEDIA_LOCATION + '/' + str(document.upload)
download_file(filepath, target_file)
# Password protect file
path, filename = os.path.split(target_file)
output_file = os.path.join(path, "temp_" + filename)
output = PyPDF2.PdfFileWriter()
input_stream = PyPDF2.PdfFileReader(open(target_file, "rb"))
for i in range(0, input_stream.getNumPages()):
output.addPage(input_stream.getPage(i))
outputStream = open(output_file, "wb")
user_password = urandom(16).hex()[:5]
# Set user and owner password to pdf file
output.encrypt(user_pwd=user_password,
owner_pwd='owner_pass',
use_128bit=True)
output.write(outputStream)
outputStream.close()
# Rename temporary output file with original filename, this
# will automatically delete temporary file
os.rename(output_file, target_file)
attachments = [] # start with an empty list
# add the attachment to the list
attachments.append(target_file)
contact_list = list(
RatingDecisionInsiderLink.objects.filter(
rating_decision=rating_decision_obj))
to_list = []
for row in contact_list:
to_list.append(row.insider.email)
# Send email with link to admin control to editor
send_email.delay(
header=ISSUER_HEADER,
body=ISSUER_EMAIL %
(rating_decision_obj.issuer.analyst.primary_analyst.first_name),
to=to_list,
from_sender=None,
cc=rating_decision_obj.issuer.analyst.primary_analyst.email,
attachments=attachments)
# Send email with password to primary analyst
send_email.delay(
header=ISSUER_EMAIL_HEADER_PASSWORD,
body=ISSUER_EMAIL_BODY_PASSWORD.format(
target_file, user_password,
rating_decision_obj.issuer.analyst.primary_analyst.first_name),
to=to_list,
from_sender=None,
cc=rating_decision_obj.issuer.analyst.primary_analyst.email,
)
# Delete file
later = datetime.datetime.utcnow() + timedelta(minutes=10)
files = [os.path.abspath(target_file)]
delete_files_task.apply_async(files, eta=later)
except AnalyticalDocument.DoesNotExist:
pass
import PyPDF2
with open('super.pdf', 'rb') as file:
reader = PyPDF2.PdfFileReader(file)
print(reader.numPages)
with open('wtr.pdf', 'rb') as file_wtm:
watermark = PyPDF2.PdfFileReader(file_wtm)
lst = []
for page in range(0, reader.numPages):
n_page = reader.getPage(page)
n_page_watermark = watermark.getPage(0)
n_page.mergePage(n_page_watermark)
lst.append(n_page)
pdf_writer = PyPDF2.PdfFileWriter()
for i in lst:
pdf_writer.addPage(i)
with open('output.pdf', 'wb') as output_file:
pdf_writer.write(output_file)
#Or this way --> more elegant way :)
template = PyPDF2.PdfFileReader(open('super.pdf', 'rb'))
watermark2 = PyPDF2.PdfFileReader(open('wtr.pdf', 'rb'))
output = PyPDF2.PdfFileWriter()
for i in range(template.getNumPages()):
page = template.getPage(i)
然后从已有的文档中拷贝内容到新文件中
有关PDF文件操作一般遵循以下步骤：
1.打开一个或者多个已有的PDF文件，得到PdfFileReader对象
2.创建一个新的PdfFileWriter对象
3.将页面从PdfFileReader对象拷贝到PdfFileWriter对象
4.最后利用PdfFileWriter对象的write()写入新创建的PDF文件
'''
minutesFile = open('meetingminutes.pdf', 'rb')
pdfReader = PyPDF2.PdfFileReader(minutesFile) # 创建PdfFileReader对象
minutesFirstPage = pdfReader.getPage(0)
pdfWatermarkReader = PyPDF2.PdfFileReader(open('watermark.pdf',
'rb')) # 创建PdfFileReader对象
minutesFirstPage.mergePage(pdfWatermarkReader.getPage(0))
pdfWriter = PyPDF2.PdfFileWriter() # 创建PdfFileWriter对象
pdfWriter.addPage(minutesFirstPage)
for pageNum in range(1, pdfReader.numPages):
pageObj = pdfReader.getPage(pageNum)
pdfWriter.addPage(pageObj)
resultPdfFile = open('watermarkedCover.pdf', 'wb')
pdfWriter.write(resultPdfFile) # 创建新的PDF文件，并将PdfFileWriter内容写进该文件
minutesFile.close()
resultPdfFile.close()
import PyPDF2 as pdf
import os
SONGS_PATH = "C:/Users/tomas/zpevnik"
paths = sorted(os.listdir(SONGS_PATH))
paths.insert(39, paths.pop()) # hack: dá Čechomor na správné místo v abecedě
files = [open(os.path.join(SONGS_PATH, path), "rb") for path in paths]
output = pdf.PdfFileWriter()
for i, (file, f) in enumerate(zip(paths, files)):
print(f"Working on {i}: ", end=" ")
page = pdf.PdfFileReader(f)
output.addPage(page.getPage(0))
page_name = os.path.splitext(os.path.basename(file))[0]
print(page_name)
output.addBookmark(page_name, i)
with open("out.pdf", "wb") as f:
output.write(f)
def extract_pages_from_pdf(
self,
source_path: str = None,
output_path: str = None,
pages: ListOrString = None,
) -> None:
"""Extract pages from source PDF and save to a new PDF document.
Page numbers start from 1.
If no source path given, assumes a PDF is already opened.
**Examples**
**Robot Framework**
.. code-block:: robotframework
***Settings***
Library RPA.PDF
***Tasks***
Example Keyword
${pages}= Extract Pages From PDF
... source_path=/tmp/sample.pdf
... output_path=/tmp/output.pdf
... pages=5
**Python**
.. code-block:: python
from RPA.PDF import PDF
pdf = PDF()
def example_keyword():
pages = pdf.extract_pages_from_pdf(
source_path="/tmp/sample.pdf",
output_path="/tmp/output.pdf",
pages=5
)
:param source_path: filepath to the source pdf.
:param output_path: filepath to the target pdf, stored by default
in `output_directory`.
:param pages: page numbers to extract from PDF (numbers start from 0)
if None then extracts all pages.
"""
self.switch_to_pdf(source_path)
reader = self.ctx.active_pdf_document.reader
writer = PyPDF2.PdfFileWriter()
output_filepath = Path(
output_path) if output_path else self.default_output
pages = self._get_page_numbers(pages, reader)
for pagenum in pages:
writer.addPage(reader.getPage(int(pagenum) - 1))
with open(str(output_filepath), "wb") as f:
writer.write(f)
def make_writer(pdf):
with open(pdf, 'rb') as f:
r = PyPDF2.PdfFileReader(f)
w = PyPDF2.PdfFileWriter()
w.appendPagesFromReader(r)
return w
def add_watermark_image_to_pdf(
self,
image_path: str,
output_path: str,
source_path: str = None,
coverage: float = 0.2,
) -> None:
"""Add image to PDF which can be new or existing PDF.
If no source path given, assumes a PDF is already opened.
**Examples**
**Robot Framework**
.. code-block:: robotframework
***Settings***
Library RPA.PDF
***Tasks***
Example Keyword
Add Watermark Image To PDF
... image_path=approved.png
... source_path=/tmp/sample.pdf
... output_path=output/output.pdf
**Python**
.. code-block:: python
from RPA.PDF import PDF
pdf = PDF()
def example_keyword():
pdf.add_watermark_image_to_pdf(
image_path="approved.png"
source_path="/tmp/sample.pdf"
output_path="output/output.pdf"
)
:param image_path: filepath to image file to add into PDF
:param source: filepath to source, if not given add image to currently
active PDF
:param output_path: filepath of target PDF
:param coverage: how the watermark image should be scaled on page,
defaults to 0.2
"""
self.switch_to_pdf(source_path)
temp_pdf = os.path.join(tempfile.gettempdir(), "temp.pdf")
writer = PyPDF2.PdfFileWriter()
pdf = FPDF()
pdf.add_page()
reader = self.ctx.active_pdf_document.reader
mediabox = reader.getPage(0).mediaBox
im = Image.open(image_path)
max_width = int(float(mediabox.getWidth()) * coverage)
max_height = int(float(mediabox.getHeight()) * coverage)
width, height = self.fit_dimensions_to_box(*im.size, max_width,
max_height)
pdf.image(name=image_path, x=40, y=60, w=width, h=height)
pdf.output(name=temp_pdf)
img = PyPDF2.PdfFileReader(temp_pdf)
watermark = img.getPage(0)
for n in range(reader.getNumPages()):
page = reader.getPage(n)
page.mergePage(watermark)
writer.addPage(page)
with open(output_path, "wb") as f:
writer.write(f)
import os
import PyPDF2
import glob
# todo learn gitIgnore
filePaths = glob.glob("Data/*.pdf")
with open("Password", mode="r", encoding="utf-8") as f:
password = f.read().replace("\n", "")
for i in filePaths:
pdf = PyPDF2.PdfFileReader(i)
pdf.decrypt(password)
dst_pdf = PyPDF2.PdfFileWriter()
dst_pdf.cloneReaderDocumentRoot(pdf)
with open(i, mode="wb") as f:
dst_pdf.write(f)
# ch18_8.py
import PyPDF2, os, re
try:
for dirName, sub_dirNames, fileNames in os.walk(
'F:\\Book\\電腦書\\Python入門\\範例檔案\\ch18'):
for fn in fileNames:
txt = re.search(r'\w*\.pdf', fn, re.IGNORECASE)
if txt != None:
pdfFn = txt.group()
pdfObj = open(pdfFn, 'rb')
pdfRd = PyPDF2.PdfFileReader(pdfObj)
pdfWr = PyPDF2.PdfFileWriter() # 新的PDF物件
for pageNum in range(pdfRd.numPages):
pdfWr.addPage(pdfRd.getPage(pageNum)) # 一次將一頁放入新的PDF物件
pdfWr.encrypt('python') # 執行加密
refn = re.search(r'\w+[^.]', pdfFn, re.IGNORECASE)
encryptPdf = refn.group()
encryptPdf = open(encryptPdf + '_encryt.pdf',
'wb') # 開啟二進位檔案供寫入
pdfWr.write(encryptPdf) # 執行寫入
print(pdfFn + '寫入成功')
encryptPdf.close()
except FileNotFoundError as e:
print(e)
finally:
print('程式結束!!')
import PyPDF2
import sys
import os
template = sys.argv[1]
watermark = sys.argv[2]
template1 = PyPDF2.PdfFileReader(open(template, 'rb')) #creates a file reader
watermark1 = PyPDF2.PdfFileReader(open(watermark, 'rb'))
output = PyPDF2.PdfFileWriter() #creates a write object
for i in range(template1.getNumPages()):#getNumPages gives how many pages the template file has
page = template1.getPage(i) #take one page at a time
page.mergePage(watermark1.getPage(0)) #watermark file has only one page
output.addPage(page)
with open('watermarked_output2.pdf', 'wb') as file:
output.write(file)
pdfFile = open('file.pdf', 'rb') # must open in read binary mode
reader = PyPDF2.PdfFileReader(pdfFile)
print(reader.numPages) # number of pages in file
page = reader.getPage(0) # gets specific page
print(page.extractText())
for pageNum in range(reader.numPages):
print(reader.getPage(pageNum).extractText())
# can add remove and reorder pages can not edit text
pdf1 = open('file1', 'rb')
pdf2 = open('file2', 'rb')
reader1 = PyPDF2.PdfFileReader(pdf1)
reader2 = PyPDF2.PdfFileReader(pdf2)
writer = PyPDF2.PdfFileWriter() # blank pdf in memory
for pageNum in range(reader1.numPages):
page = reader1.getPage(pageNum)
writer.addPage(page)
for pageNum in range(reader2.numPages):
page = reader2.getPage(pageNum)
writer.addPage(page)
outputFile = open('combinedPdf.pdf', 'wb')
writer.write(outputFile)
outputFile.close()
pdf1.close()
pdf2.close()
def exportPdf(fin, outdir, annotations, verbose):
'''Export PDF with annotations.
<fin>: string, absolute path to input PDF file.
<outdir>: string, absolute path to the output directory.
<annotations>: FileAnno obj.
Update time: 2016-02-19 14:32:56.
'''
#---------------Skip unlinked files---------------
assert annotations.hasfile, 'no file of %s' % fin
#if not annotations.hasfile:
#return
try:
inpdf = PyPDF2.PdfFileReader(open(fin, 'rb'))
if inpdf.isEncrypted:
# PyPDF2 seems to think some files are encrypted even
# if they are not. We just ignore the encryption.
# This seems to work for the one file where I saw this issue
#inpdf._override_encryption = True
#inpdf._flatten()
# UPDATE: trying to decrypt takes a lot of time,
# as this rarely happens to academic docs I'm skipping this
# and simply treat as fail
raise Exception("Skip encrypt")
except IOError:
print('Could not find pdf file %s' % fin)
# retain meta data
meta = inpdf.getDocumentInfo()
outpdf = PyPDF2.PdfFileWriter()
outpdf.addMetadata(meta)
#----------------Loop through pages----------------
pages = range(1, inpdf.getNumPages() + 1)
for pii in pages:
inpg = inpdf.getPage(pii - 1)
#----------------Process highlights----------------
if pii in annotations.hlpages:
for hjj in annotations.highlights[pii]:
# Changes suggested by matteosecli: add author of highlight:
anno = pdfannotation.createHighlight(hjj["rect"],
author=hjj['author'],
cdate=hjj["cdate"],
color=hjj['color'])
inpg = pdfannotation.addAnnotation(inpg, outpdf, anno)
#------------------Process notes------------------
if pii in annotations.ntpages:
for njj in annotations.notes[pii]:
note = pdfannotation.createNote(njj["rect"], \
contents=njj["content"], author=njj["author"],\
cdate=njj["cdate"])
inpg = pdfannotation.addAnnotation(inpg, outpdf, note)
outpdf.addPage(inpg)
# this is a fix provided by rongmu regarding issue #22:
# https://github.com/Xunius/Menotexport/issues/22
# As I'm not giving it tests I'll put it inside a try
# fix start ----------------------------------{{{
# Copy the root (document catalog) except for /Pages
# PDF Reference, Sixth Edition, version 1.7, p.137
# https://www.adobe.com/devnet/pdf/pdf_reference_archive.html
try:
for k, v in inpdf.trailer["/Root"].items():
if k.getObject() != "/Pages":
outpdf._root_object.update({k: v})
except:
pass
# fix end ----------------------------------}}}
#-----------------------Save-----------------------
filename = annotations.filename
if not os.path.isdir(outdir):
os.makedirs(outdir)
abpath_out = os.path.join(outdir, filename)
if os.path.isfile(abpath_out):
os.remove(abpath_out)
with open(abpath_out, mode='wb') as fout:
outpdf.write(fout)
return
pdf_path = "./PDF/"
#os.chdir(pdf_path)
#Get the name of the parent pdf files from user
#This file will be demerged into 2 files
parent_pdf = getFileNameFromUser("Give parent PDF name with .pdf extn",
pdf_path)
#Create file objects for both the files
pdfFileObj = open(os.path.join(pdf_path + parent_pdf), "rb")
#Pass the file objects to the file reader
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
#create a Pdf writer object
pdfWriter1 = PyPDF2.PdfFileWriter()
pdfWriter2 = PyPDF2.PdfFileWriter()
#Add individual pages from pdf files to writer object
addPageToWriter(pdfReader, pdfWriter1, 0, pdfReader.numPages / 2)
addPageToWriter(pdfReader, pdfWriter2, pdfReader.numPages / 2,
pdfReader.numPages)
pdfOutputFileObj1 = open(
os.path.join(pdf_path + getFinalPdfNameFromUser()), "wb")
pdfOutputFileObj2 = open(
os.path.join(pdf_path + getFinalPdfNameFromUser()), "wb")
print(".. Demerging parent pdf file....")
pdfWriter1.write(pdfOutputFileObj1)
pdfWriter2.write(pdfOutputFileObj2)
print("... done...")
import PyPDF2 as p
template = p.PdfFileReader(open('merged_pdf.pdf', 'rb'))
water = p.PdfFileReader(open('pdf3.pdf', 'rb'))
output = p.PdfFileWriter()
for i in range(template.getNumPages()):
page = template.getPage(i)
page.mergePage(water.getPage(0))
output.addPage(page)
with open('watermarkedPdf.pdf', 'wb') as file:
output.write(file)
fileList.append(pdfFileObj)
# Create PdfFileReader objects from PDF file list
readerList = []
for pdfFile in fileList:
pdfReader = PyPDF2.PdfFileReader(pdfFile)
readerList.append(pdfReader)
totalPages = 0
for pr in readerList:
print(pr.numPages)
totalPages += pr.numPages
print("total pages:", totalPages)
# combine read PDF files
pdfWriter = PyPDF2.PdfFileWriter()
for pr in readerList:
for pageNum in range(pr.numPages):
pageObj = pr.getPage(pageNum)
pdfWriter.addPage(pageObj)
# write to a new PDF file
if os.path.isfile(mergedFile + ".pdf"):
print('File already exists, specify another filename')
else:
pdfOutputFile = open(mergedFile + ".pdf", 'wb')
pdfWriter.write(pdfOutputFile)
pdfOutputFile.close()
# Close all read files
for pdfFile in fileList:
import PyPDF2
pdf1 = open('JadaDixon_rates_of_reaction_lab.pdf', 'rb')
pdf2 = open('JadaDixon_reaction_rate_p_and_d_.pdf', 'rb')
pdf3 = open('JadaDixon_Redox_Lab_Template.pdf', 'rb')
pdf4 = open('JadaDixonchemistry.pdf', 'rb')
pdf5 = open('jadadixonenergeticslab.pdf', 'rb')
pdf6 = open('JadaDixonSBaLab2.pdf', 'rb')
pdf7 = open('Chemistry_P_and_D__Jada_Dixon.pdf', 'rb')
pdf1reader = PyPDF2.PdfFileReader(pdf1)
pdf2reader = PyPDF2.PdfFileReader(pdf2)
pdf3reader = PyPDF2.PdfFileReader(pdf3)
pdf4reader = PyPDF2.PdfFileReader(pdf4)
pdf5reader = PyPDF2.PdfFileReader(pdf5)
pdf6reader = PyPDF2.PdfFileReader(pdf6)
pdf7reader = PyPDF2.PdfFileReader(pdf7)
pdfwrite = PyPDF2.PdfFileWriter()
for i in range(pdf1reader.numPages):
pageO = pdf1reader.getPage(i)
pdfWRITE
