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/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 + '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 + 'WorkingWithDocumentConversion/PdfToDoc/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# Save the concatenated output file (the target document)
pdf.save(dataDir + "output.doc")
print "Document has been converted 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/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 + 'WorkingWithDocumentConversion/PdfToExcel/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# Instantiate ExcelSave Option object
excelsave = ExcelSaveOptions()
# Save the output to XLS format
pdf.save(dataDir + "Converted_Excel.xls", excelsave)
print "Document has been converted successfully"
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/GetXMPMetadata/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Get properties
print "xmp:CreateDate: "
print doc.getMetadata().get_Item("xmp:CreateDate")
print "xmp:Nickname: "
print doc.getMetadata().get_Item("xmp:Nickname")
print "xmp:CustomProperty: "
print doc.getMetadata().get_Item("xmp:CustomProperty")
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithDocumentConversion/SvgToPdf/'
# Instantiate LoadOption object using SVG load option
options = SvgLoadOptions()
# Create document object
pdf = Document(dataDir + 'Example.svg', options)
# Save the output to XLS format
pdf.save(dataDir + "SVG.pdf")
print "Document has been converted successfully"
def optimize_web(dataDir):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/Optimize/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Optimize for web
doc.optimize()
#Save output document
doc.save(dataDir + "Optimized_Web.pdf")
print "Optimized PDF for the Web, please check output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/GetDocumentWindow/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Get different document properties
# Position of document's window - Default: false
print "CenterWindow :- "
print doc.getCenterWindow()
# Predominant reading order; determine the position of page
# when displayed side by side - Default: L2R
print "Direction :- "
print doc.getDirection()
# Whether window's title bar should display document title.
# If false, title bar displays PDF file name - Default: false
print "DisplayDocTitle :- "
print doc.getDisplayDocTitle()
#Whether to resize the document's window to fit the size of
#first displayed page - Default: false
print "FitWindow :- "
print doc.getFitWindow()
# Whether to hide menu bar of the viewer application - Default: false
print "HideMenuBar :-"
print doc.getHideMenubar()
# Whether to hide tool bar of the viewer application - Default: false
print "HideToolBar :-"
print doc.getHideToolBar()
# Whether to hide UI elements like scroll bars
# and leaving only the page contents displayed - Default: false
print "HideWindowUI :-"
print doc.getHideWindowUI()
# The document's page mode. How to display document on exiting full-screen mode.
print "NonFullScreenPageMode :-"
print doc.getNonFullScreenPageMode()
# The page layout i.e. single page, one column
print "PageLayout :-"
print doc.getPageLayout()
#How the document should display when opened.
print "pageMode :-"
print doc.getPageMode()
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 + '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 + 'WorkingWithDocumentConversion/PdfToSvg/'
# Open the target document
pdf = Document(dataDir + 'input1.pdf')
# instantiate an object of SvgSaveOptions
save_options = SvgSaveOptions()
# do not compress SVG image to Zip archive
save_options.CompressOutputToZipArchive = False
# Save the output to XLS format
pdf.save(dataDir + "Output.svg", save_options)
print "Document has been converted successfully"
def optimize_web(dataDir):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/SetExpiration/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
javascript = JavascriptAction(
"var year=2014;" "var month=4;" "today = new Date();"
"today = new Date(today.getFullYear(), today.getMonth());"
"expiry = new Date(year, month);"
"if (today.getTime() > expiry.getTime())"
"app.alert('The file is expired. You need a new one.');"
)
doc.setOpenAction(javascript)
# save update document with information
doc.save(dataDir + "set_expiration.pdf")
print "Update document information, please check output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/SetPdfFileInfo/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Get document information
doc_info = doc.getInfo()
doc_info.setAuthor("Aspose.Pdf for java")
doc_info.setCreationDate(Date())
doc_info.setKeywords("Aspose.Pdf, DOM, API")
doc_info.setModDate(Date())
doc_info.setSubject("PDF Information")
doc_info.setTitle("Setting PDF Document Information")
# save update document with information
doc.save(dataDir + "Updated_Information.pdf")
print "Update document information, please check output file."
def __init__(self):
dataDir = Settings.dataDir + 'WorkingWithDocumentObject/GetPdfFileInfo/'
# Open a pdf document.
doc = Document(dataDir + "input1.pdf")
# Get document information
doc_info = doc.getInfo()
# Show document information
print "Author:"
print doc_info.getAuthor()
print "Creation Date:"
print doc_info.getCreationDate()
print "Keywords:"
print doc_info.getKeywords()
print "Modify Date:"
print doc_info.getModDate()
print "Subject:"
print doc_info.getSubject()
print "Title:"
print doc_info.getTitle()
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/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()
