def copy_page(page):
newpage = PageObject(page.pdf)
newpage.update(page)
# Copy Rectangles to be manipulatable
for attr in PAGE_BOXES:
if page.has_key(attr):
newpage[NameObject(attr)] = RectangleObject(list(page[attr]))
return newpage
def copy_page(page):
newpage = PageObject(page.pdf)
newpage.update(page)
# Copy Rectangles to be manipulatable
for attr in PAGE_BOXES:
if page.has_key(attr):
newpage[NameObject(attr)] = RectangleObject(list(page[attr]))
return newpage
def slice(self, ifile, ofile=None, marginv=0, marginh=0, columnwidth=0, centerwidth=0, scale=0.9):
output = PdfFileWriter()
input = PdfFileReader(file(ifile, "rb"))
# print the title of document1.pdf
print "title = %s" % (input.getDocumentInfo().title)
print "Processing page: "
for i in xrange(input.getNumPages()):
print i+1
# add left column as page
page = PageObject.createBlankPage(input)
page.mergePage(input.getPage(i))
if columnwidth != 0 and centerwidth != 0:
page.mediaBox.upperRight = (
page.mediaBox.getUpperLeft_x() + marginh + columnwidth,
page.mediaBox.getUpperRight_y() - marginv
)
else:
page.mediaBox.upperRight = (
page.mediaBox.getUpperRight_x() / 2,
page.mediaBox.getUpperRight_y() - marginv
)
page.mediaBox.lowerLeft = (
page.mediaBox.getLowerLeft_x() + marginh,
page.mediaBox.getLowerLeft_y() + marginv,
)
page.scale(scale, scale)
output.addPage(page)
# add right column as page
page = PageObject.createBlankPage(input)
page.mergePage(input.getPage(i))
if columnwidth != 0 and centerwidth != 0:
page.mediaBox.lowerLeft = (
page.mediaBox.getLowerLeft_x() + marginh + columnwidth + centerwidth,
page.mediaBox.getLowerLeft_y() + marginv,
)
else:
page.mediaBox.lowerLeft = (
page.mediaBox.getUpperRight_x() / 2,
page.mediaBox.getLowerLeft_y() + marginv,
)
page.mediaBox.upperRight = (
page.mediaBox.getUpperRight_x() - marginh,
page.mediaBox.getUpperRight_y() - marginv
)
page.scale(scale, scale)
output.addPage(page)
# finally, write "output"
if ofile is not None:
outputStream = file(ofile, "wb")
else:
outputStream = file(PdfSlicer.getOutName(ifile), "wb")
output.write(outputStream)
outputStream.close()
def generate_files(self, pages, front_side_pages, back_side_pages):
"""
scale each two pages to fit into one sheet, construct the document
and write out two files: the front side and the back side files.
"""
front_output = PdfFileWriter()
back_output = PdfFileWriter()
size = 841 / 2
num_pages = pages.getNumPages()
for index, page in enumerate(front_side_pages):
#(w, h) = page_model.mediaBox.upperRight
page_model = PageObject.createBlankPage(width=841, height=595)
page_model.mergeScaledTranslatedPage(pages.getPage(page[0]), tx=0, ty=0, scale=0.7)
page_model.mergeScaledTranslatedPage(pages.getPage(page[1]), tx=size, ty=0, scale=0.7)
front_output.addPage(page_model)
ProgressStatus.message = "Processing front pages ... (%s of %s)" % (index, num_pages / 4)
ProgressStatus.percentage = float(index) / float(pages.getNumPages() / 4) * 50
if self.exiting: return
for index, page in enumerate(back_side_pages):
page_model = PageObject.createBlankPage(width=841, height=595)
page_model.mergeScaledTranslatedPage(pages.getPage(page[0]), tx=0, ty=0, scale=0.7)
page_model.mergeScaledTranslatedPage(pages.getPage(page[1]), tx=size, ty=0, scale=0.7)
back_output.addPage(page_model)
ProgressStatus.message = "Processing back pages ... (%s of %s)" % (index, num_pages / 4)
ProgressStatus.percentage = float(index) / float(pages.getNumPages() / 4) * 50 + 50
if self.exiting: return
with file(path.join(self.job.directory, "(front_side_pages) " + path.basename(self.job.pdf_file)), "wb") as stream:
ProgressStatus.message = "Writing files..."
front_output.write(stream)
with file(path.join(self.job.directory, "(back_side_pages) " + path.basename(self.job.pdf_file)), "wb") as stream:
ProgressStatus.message = "Writing files..."
back_output.write(stream)
ProgressStatus.message = "Finished"
ProgressStatus.percentage = 100
def replace_text(cls, page, text, replace):
# HACK
from pyPdf.pdf import ContentStream, PageObject
from pyPdf.generic import TextStringObject, NameObject
content = ContentStream(page["/Contents"].getObject(), page.pdf)
for idx in range(len(content.operations)):
operands, operator = content.operations[idx]
if operator == 'Tj':
operands[0] = TextStringObject(operands[0].replace(
text, replace))
new_page = PageObject.createBlankPage(page.pdf)
new_page.mergePage(page)
new_page[NameObject('/Contents')] = content
return new_page
def replace_text(cls, page, text, replace):
# HACK
from pyPdf.pdf import ContentStream, PageObject
from pyPdf.generic import TextStringObject, NameObject
content = ContentStream(page["/Contents"].getObject(), page.pdf)
for idx in range(len(content.operations)):
operands, operator = content.operations[idx]
if operator == 'Tj':
operands[0] = TextStringObject(operands[0].replace(text,
replace))
new_page = PageObject.createBlankPage(page.pdf)
new_page.mergePage(page)
new_page[NameObject('/Contents')] = content
return new_page
def n_pages_on_one(pages, pages_sheet):
width = float(pages[0].mediaBox.getWidth())
height = float(pages[0].mediaBox.getHeight())
# Calculate placement parameters
rotation, scaling, cell_x_count, cell_y_count = _get_optimal_placement(
width, height, pages_sheet)
# Get placement matrix, ajust to rotation
if rotation:
# From down to up, left to right
# Also ajust to "one-off issue"
placement = list(product(range(1, cell_x_count+1),
range(cell_y_count-1, -1, -1)))
else:
# From left to right, up to down
placement = map(lambda (x, y): (y, x),
list(product(range(cell_y_count),
range(cell_x_count))))
new_pages = []
# Merge pages
for new_page_idx in range(int(math.ceil(1. * len(pages) / pages_sheet))):
offset = new_page_idx * pages_sheet
# Start from blank page
new_page = PageObject.createBlankPage(None, width, height)
# Get `pages_sheet` number of pages and merge together
for idx, page in enumerate(pages[offset:offset+pages_sheet]):
x, y = placement[idx]
# Get coordinates
w = width * x / cell_x_count
h = height * (y+1) / cell_y_count
# TODO align page so that it takes the center of its cell
new_page.mergeRotatedScaledTranslatedPage(page,
rotation, scaling,
w, height-h)
new_pages.append(new_page)
return new_pages
def analyze_webletter(self, pdf_letter):
"""
Look if the web letter has a minimum of 2 page.
If not add one blank page.
"""
pdf = PdfFileReader(BytesIO(pdf_letter))
if pdf.numPages < 2:
final_pdf = PdfFileWriter()
final_pdf.addPage(pdf.getPage(0))
width = float(pdf.getPage(0).mediaBox.getWidth())
height = float(pdf.getPage(0).mediaBox.getHeight())
new_page = PageObject.createBlankPage(None, width, height)
final_pdf.addPage(new_page)
output_stream = BytesIO()
final_pdf.write(output_stream)
output_stream.seek(0)
pdf_letter = output_stream.read()
output_stream.close()
return pdf_letter
def analyze_webletter(self, pdf_letter):
"""
Look if the web letter has a minimum of 2 page.
If not add one blank page.
"""
pdf = PdfFileReader(BytesIO(pdf_letter))
if pdf.numPages < 2:
final_pdf = PdfFileWriter()
final_pdf.addPage(pdf.getPage(0))
width = float(pdf.getPage(0).mediaBox.getWidth())
height = float(pdf.getPage(0).mediaBox.getHeight())
new_page = PageObject.createBlankPage(None, width, height)
final_pdf.addPage(new_page)
output_stream = BytesIO()
final_pdf.write(output_stream)
output_stream.seek(0)
pdf_letter = output_stream.read()
output_stream.close()
return pdf_letter
def generate_files(self, pages, front_side_pages, back_side_pages):
"""
scale each two pages to fit into one sheet, construct the document
and write out two files: the front side and the back side files.
"""
front_output = PdfFileWriter()
back_output = PdfFileWriter()
size = 841 / 2
num_pages = pages.getNumPages()
for index, page in enumerate(front_side_pages):
#(w, h) = page_model.mediaBox.upperRight
page_model = PageObject.createBlankPage(width=841, height=595)
page_model.mergeScaledTranslatedPage(pages.getPage(page[0]),
tx=0,
ty=0,
scale=0.7)
page_model.mergeScaledTranslatedPage(pages.getPage(page[1]),
tx=size,
ty=0,
scale=0.7)
front_output.addPage(page_model)
ProgressStatus.message = "Processing front pages ... (%s of %s)" % (
index, num_pages / 4)
ProgressStatus.percentage = float(index) / float(
pages.getNumPages() / 4) * 50
if self.exiting: return
for index, page in enumerate(back_side_pages):
page_model = PageObject.createBlankPage(width=841, height=595)
page_model.mergeScaledTranslatedPage(pages.getPage(page[0]),
tx=0,
ty=0,
scale=0.7)
page_model.mergeScaledTranslatedPage(pages.getPage(page[1]),
tx=size,
ty=0,
scale=0.7)
back_output.addPage(page_model)
ProgressStatus.message = "Processing back pages ... (%s of %s)" % (
index, num_pages / 4)
ProgressStatus.percentage = float(index) / float(
pages.getNumPages() / 4) * 50 + 50
if self.exiting: return
with file(
path.join(
self.job.directory,
"(front_side_pages) " + path.basename(self.job.pdf_file)),
"wb") as stream:
ProgressStatus.message = "Writing files..."
front_output.write(stream)
with file(
path.join(
self.job.directory,
"(back_side_pages) " + path.basename(self.job.pdf_file)),
"wb") as stream:
ProgressStatus.message = "Writing files..."
back_output.write(stream)
ProgressStatus.message = "Finished"
ProgressStatus.percentage = 100
def copyPage(page):
newpage = PageObject(page.pdf)
newpage.update(page)
newpage[NameObject("/CropBox")] = RectangleObject(page.cropBox)
return newpage
#!/usr/bin/env python
from pyPdf import PdfFileWriter, PdfFileReader
from pyPdf.pdf import PageObject
input1 = PdfFileReader(open('page1.pdf', 'rb'))
page1 = input1.getPage(0)
width, height = (page1.mediaBox.getWidth(), page1.mediaBox.getHeight())
output = PdfFileWriter()
for i in range(10):
page = PageObject.createBlankPage(None, width, height)
page.mergeScaledTranslatedPage(page1, 0.5, 0, 0)
page.mergeScaledTranslatedPage(page1, 0.5, width/2, height/2)
page.mergeScaledTranslatedPage(page1, 0.5, 0, height/2)
page.mergeScaledTranslatedPage(page1, 0.5, width/2, 0)
output.addPage(page)
outputStream = open('output.pdf', 'wb')
output.write(outputStream)
outputStream.close()
def copyPage(page):
newpage = PageObject(page.pdf)
newpage.update(page)
newpage[NameObject("/CropBox")] = RectangleObject(page.cropBox)
return newpage
