def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/SplitAllPages/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# loop through all the pages
pdf_page = 1
total_size = pdf.getPages().size()
while pdf_page <= total_size:
# create a new Document object
new_document = Document()
# get the page at particular index of Page Collection
new_document.getPages().add(pdf.getPages().get_Item(pdf_page))
# save the newly generated PDF file
new_document.save(dataDir + "page_#{pdf_page}.pdf")
pdf_page+=1
print "Split process completed successfully!"
def __init__(self):
dataDir = Settings.dataDir + "WorkingWithText/ExtractTextFromAllPages/"
# Open the target document
pdf = Document(dataDir + "input1.pdf")
# create TextAbsorber object to extract text
text_absorber = TextAbsorber()
# accept the absorber for all the pages
pdf.getPages().accept(text_absorber)
# In order to extract text from specific page of document, we need to specify the particular page using its index against accept(..) method.
# accept the absorber for particular PDF page
# pdfDocument.getPages().get_Item(1).accept(textAbsorber)
# get the extracted text
extracted_text = text_absorber.getText()
# create a writer and open the file
writer = FileWriter(File(dataDir + "extracted_text.out.txt"))
writer.write(extracted_text)
# write a line of text to the file
# tw.WriteLine(extractedText)
# close the stream
writer.close()
print "Text extracted successfully. Check output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithText/ExtractTextFromAllPages/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# create TextAbsorber object to extract text
text_absorber = TextAbsorber()
# accept the absorber for all the pages
pdf.getPages().accept(text_absorber)
# In order to extract text from specific page of document, we need to specify the particular page using its index against accept(..) method.
# accept the absorber for particular PDF page
# pdfDocument.getPages().get_Item(1).accept(textAbsorber)
#get the extracted text
extracted_text = text_absorber.getText()
# create a writer and open the file
writer = FileWriter(File(dataDir + "extracted_text.out.txt"))
writer.write(extracted_text)
# write a line of text to the file
# tw.WriteLine(extractedText)
# close the stream
writer.close()
print "Text extracted successfully. Check output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/SplitAllPages/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# loop through all the pages
pdf_page = 1
total_size = pdf.getPages().size()
while pdf_page <= total_size:
# create a new Document object
new_document = Document()
# get the page at particular index of Page Collection
new_document.getPages().add(pdf.getPages().get_Item(pdf_page))
# save the newly generated PDF file
new_document.save(dataDir + "page_#{pdf_page}.pdf")
pdf_page += 1
print "Split process completed successfully!"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/DeletePage/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# delete a particular page
pdf.getPages().delete(2)
# save the newly generated PDF file
pdf.save(dataDir + "output.pdf")
print "Page deleted successfully!"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/DeletePage/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# delete a particular page
pdf.getPages().delete(2)
# save the newly generated PDF file
pdf.save(dataDir + "output.pdf")
print "Page deleted successfully!"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/InsertEmptyPageAtEndOfFile/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# insert a empty page in a PDF
pdf.getPages().add()
# Save the concatenated output file (the target document)
pdf.save(dataDir + "output.pdf")
print "Empty page added successfully!"
def __init__(self):
dataDir = Settings.dataDir + "WorkingWithText/AddHtml/"
# Instantiate Document object
doc = Document()
# Add a page to pages collection of PDF file
page = doc.getPages().add()
# Instantiate HtmlFragment with HTML contents
title = HtmlFragment("<fontsize=10><b><i>Table</i></b></fontsize>")
# set MarginInfo for margin details
margin = MarginInfo()
margin.setBottom(10)
margin.setTop(200)
# Set margin information
title.setMargin(margin)
# Add HTML Fragment to paragraphs collection of page
page.getParagraphs().add(title)
# Save PDF file
doc.save(dataDir + "html.output.pdf")
print "HTML added successfully"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithText/AddText/'
# Instantiate Document object
doc = Document(dataDir + 'input1.pdf')
# get particular page
pdf_page = doc.getPages().get_Item(1)
# create text fragment
text_fragment = TextFragment("main text")
text_fragment.setPosition(Position(100, 600))
font_repository = FontRepository()
# set text properties
text_fragment.getTextState().setFont(
font_repository.findFont("Verdana"))
text_fragment.getTextState().setFontSize(14)
# create TextBuilder object
text_builder = TextBuilder(pdf_page)
# append the text fragment to the PDF page
text_builder.appendText(text_fragment)
# Save PDF file
doc.save(dataDir + "Text_Added.pdf")
print "Text added successfully"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithText/AddHtml/'
# Instantiate Document object
doc = Document()
# Add a page to pages collection of PDF file
page = doc.getPages().add()
# Instantiate HtmlFragment with HTML contents
title = HtmlFragment("<fontsize=10><b><i>Table</i></b></fontsize>")
# set MarginInfo for margin details
margin = MarginInfo()
margin.setBottom(10)
margin.setTop(200)
# Set margin information
title.setMargin(margin)
# Add HTML Fragment to paragraphs collection of page
page.getParagraphs().add(title)
# Save PDF file
doc.save(dataDir + "html.output.pdf")
print "HTML added successfully"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithText/AddText/'
# Instantiate Document object
doc = Document(dataDir + 'input1.pdf')
# get particular page
pdf_page = doc.getPages().get_Item(1)
# create text fragment
text_fragment = TextFragment("main text")
text_fragment.setPosition(Position(100, 600))
font_repository = FontRepository()
# set text properties
text_fragment.getTextState().setFont(font_repository.findFont("Verdana"))
text_fragment.getTextState().setFontSize(14)
# create TextBuilder object
text_builder = TextBuilder(pdf_page)
# append the text fragment to the PDF page
text_builder.appendText(text_fragment)
# Save PDF file
doc.save(dataDir + "Text_Added.pdf")
print "Text added successfully"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/ConcatenatePdfFiles/'
# Open the target document
pdf1 = Document(dataDir + 'input1.pdf')
# Open the source document
pdf2 = Document(dataDir + 'input2.pdf')
# Add the pages of the source document to the target document
pdf1.getPages().add(pdf2.getPages())
# Save the concatenated output file (the target document)
pdf1.save(dataDir + "Concatenate_output.pdf")
print "New document has been saved, please check the output file"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/ConcatenatePdfFiles/'
# Open the target document
pdf1 = Document(dataDir + 'input1.pdf')
# Open the source document
pdf2 = Document(dataDir + 'input2.pdf')
# Add the pages of the source document to the target document
pdf1.getPages().add(pdf2.getPages())
# Save the concatenated output file (the target document)
pdf1.save(dataDir + "Concatenate_output.pdf")
print "New document has been saved, please check the output file"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/GetPage/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# get the page at particular index of Page Collection
pdf_page = pdf.getPages().get_Item(1)
# create a Document object
new_document = Document()
# add page to pages collection of document object
new_document.getPages().add(pdf_page)
# save the newly generated PDF file
new_document.save(dataDir + "output.pdf")
print "Process completed successfully!"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/GetNumberOfPages/'
# Create PDF document
pdf = Document(dataDir + 'input1.pdf')
page_count = pdf.getPages().size()
print "Page Count:"
print page_count
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/GetNumberOfPages/'
# Create PDF document
pdf = Document(dataDir + 'input1.pdf')
page_count = pdf.getPages().size()
print "Page Count:"
print page_count
def __init__(self):
dataDir = Settings.dataDir + "WorkingWithDocumentObject/AddJavascript/"
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Adding JavaScript at Document Level
# Instantiate JavascriptAction with desried JavaScript statement
javaScript = JavascriptAction("this.print({bUI:true,bSilent:false,bShrinkToFit:true})")
# Assign JavascriptAction object to desired action of Document
doc.setOpenAction(javaScript)
# Adding JavaScript at Page Level
doc.getPages().get_Item(2).getActions().setOnOpen(JavascriptAction("app.alert('page 2 is opened')"))
doc.getPages().get_Item(2).getActions().setOnClose(JavascriptAction("app.alert('page 2 is closed')"))
# Save PDF Document
doc.save(dataDir + "JavaScript-Added.pdf")
print "Added JavaScript Successfully, please check the output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/AddJavascript/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Adding JavaScript at Document Level
# Instantiate JavascriptAction with desried JavaScript statement
javaScript = JavascriptAction(
"this.print({bUI:true,bSilent:false,bShrinkToFit:true})")
# Assign JavascriptAction object to desired action of Document
doc.setOpenAction(javaScript)
# Adding JavaScript at Page Level
doc.getPages().get_Item(2).getActions().setOnOpen(
JavascriptAction("app.alert('page 2 is opened')"))
doc.getPages().get_Item(2).getActions().setOnClose(
JavascriptAction("app.alert('page 2 is closed')"))
# Save PDF Document
doc.save(dataDir + "JavaScript-Added.pdf")
print "Added JavaScript Successfully, please check the output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/UpdatePageDimensions/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# get page collection
page_collection = pdf.getPages()
# get particular page
pdf_page = page_collection.get_Item(1)
# set the page size as A4 (11.7 x 8.3 in) and in Aspose.Pdf, 1 inch = 72 points
# so A4 dimensions in points will be (842.4, 597.6)
pdf_page.setPageSize(597.6,842.4)
# save the newly generated PDF file
pdf.save(dataDir + "output.pdf")
print "Dimensions updated successfully!"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/GetPageProperties/'
# Create PDF document
pdf_document = Document(dataDir + 'input1.pdf');
# get page collection
page_collection =pdf_document.getPages();
# get particular page
pdf_page =page_collection.get_Item(1);
#get page properties
print "ArtBox : Height = "
print pdf_page.getArtBox().getHeight()
print ", Width = "
print pdf_page.getArtBox().getWidth()
print ", LLX = "
print pdf_page.getArtBox().getLLX()
print ", LLY = "
print pdf_page.getArtBox().getLLY()
print ", URX = "
print pdf_page.getArtBox().getURX()
print ", URY = "
print pdf_page.getArtBox().getURY()
print "BleedBox : Height = "
print pdf_page.getBleedBox().getHeight()
print ", Width = "
print pdf_page.getBleedBox().getWidth()
print ", LLX = "
print pdf_page.getBleedBox().getLLX()
print ", LLY = "
print pdf_page.getBleedBox().getLLY()
print ", URX = "
print pdf_page.getBleedBox().getURX()
print ", URY = "
print pdf_page.getBleedBox().getURY()
print "CropBox : Height = "
print pdf_page.getCropBox().getHeight()
print ", Width = "
print pdf_page.getCropBox().getWidth()
print ", LLX = "
print pdf_page.getCropBox().getLLX()
print ", LLY = "
print pdf_page.getCropBox().getLLY()
print ", URX = "
print pdf_page.getCropBox().getURX()
print ", URY = "
print pdf_page.getCropBox().getURY()
print "MediaBox : Height = "
print pdf_page.getMediaBox().getHeight()
print ", Width = "
print pdf_page.getMediaBox().getWidth()
print ", LLX = "
print pdf_page.getMediaBox().getLLX()
print ", LLY = "
print pdf_page.getMediaBox().getLLY()
print ", URX = "
print pdf_page.getMediaBox().getURX()
print ", URY = "
print pdf_page.getMediaBox().getURY()
print "TrimBox : Height = "
print pdf_page.getTrimBox().getHeight()
print ", Width = "
print pdf_page.getTrimBox().getWidth()
print ", LLX = "
print pdf_page.getTrimBox().getLLX()
print ", LLY = "
print pdf_page.getTrimBox()
print getLLY()
print ", URX = "
print pdf_page.getTrimBox().getURX()
print ", URY = "
print pdf_page.getTrimBox().getURY()
print "Rect : Height = "
print pdf_page.getRect().getHeight()
print ", Width = "
print pdf_page.getRect().getWidth()
print ", LLX = "
print pdf_page.getRect().getLLX()
print ", LLY = "
print pdf_page.getRect().getLLY()
print ", URX = "
print pdf_page.getRect().getURX()
print ", URY = " +pdf_page.getRect().getURY()
print "Page Number :"
print pdf_page.getNumber()
print "Rotate :"
print pdf_page.getRotate()
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithPages/GetPageProperties/'
# Create PDF document
pdf_document = Document(dataDir + 'input1.pdf')
# get page collection
page_collection = pdf_document.getPages()
# get particular page
pdf_page = page_collection.get_Item(1)
#get page properties
print "ArtBox : Height = "
print pdf_page.getArtBox().getHeight()
print ", Width = "
print pdf_page.getArtBox().getWidth()
print ", LLX = "
print pdf_page.getArtBox().getLLX()
print ", LLY = "
print pdf_page.getArtBox().getLLY()
print ", URX = "
print pdf_page.getArtBox().getURX()
print ", URY = "
print pdf_page.getArtBox().getURY()
print "BleedBox : Height = "
print pdf_page.getBleedBox().getHeight()
print ", Width = "
print pdf_page.getBleedBox().getWidth()
print ", LLX = "
print pdf_page.getBleedBox().getLLX()
print ", LLY = "
print pdf_page.getBleedBox().getLLY()
print ", URX = "
print pdf_page.getBleedBox().getURX()
print ", URY = "
print pdf_page.getBleedBox().getURY()
print "CropBox : Height = "
print pdf_page.getCropBox().getHeight()
print ", Width = "
print pdf_page.getCropBox().getWidth()
print ", LLX = "
print pdf_page.getCropBox().getLLX()
print ", LLY = "
print pdf_page.getCropBox().getLLY()
print ", URX = "
print pdf_page.getCropBox().getURX()
print ", URY = "
print pdf_page.getCropBox().getURY()
print "MediaBox : Height = "
print pdf_page.getMediaBox().getHeight()
print ", Width = "
print pdf_page.getMediaBox().getWidth()
print ", LLX = "
print pdf_page.getMediaBox().getLLX()
print ", LLY = "
print pdf_page.getMediaBox().getLLY()
print ", URX = "
print pdf_page.getMediaBox().getURX()
print ", URY = "
print pdf_page.getMediaBox().getURY()
print "TrimBox : Height = "
print pdf_page.getTrimBox().getHeight()
print ", Width = "
print pdf_page.getTrimBox().getWidth()
print ", LLX = "
print pdf_page.getTrimBox().getLLX()
print ", LLY = "
print pdf_page.getTrimBox()
print getLLY()
print ", URX = "
print pdf_page.getTrimBox().getURX()
print ", URY = "
print pdf_page.getTrimBox().getURY()
print "Rect : Height = "
print pdf_page.getRect().getHeight()
print ", Width = "
print pdf_page.getRect().getWidth()
print ", LLX = "
print pdf_page.getRect().getLLX()
print ", LLY = "
print pdf_page.getRect().getLLY()
print ", URX = "
print pdf_page.getRect().getURX()
print ", URY = " + pdf_page.getRect().getURY()
print "Page Number :"
print pdf_page.getNumber()
print "Rotate :"
print pdf_page.getRotate()
