def __call__(self, data, attachments=[], pages=None):
self.rendered = {}
for field, ctx in self.fields.items():
if "template" not in ctx:
continue
self.context = ctx
kwargs = self.template_args(data)
template = self.context["template"]
try:
rendered_field = template.render(**kwargs)
except Exception as err:
logger.error("%s: %s %s", field, template, err)
else:
# Skip the field if it is already rendered by filter
if field not in self.rendered:
self.rendered[field] = rendered_field
filled = PdfFileReader(self.exec_pdftk(self.rendered))
for pagenumber, watermark in self.watermarks:
page = filled.getPage(pagenumber)
page.mergePage(watermark)
output = PdfFileWriter()
pages = pages or xrange(filled.getNumPages())
for p in pages:
output.addPage(filled.getPage(p))
for attachment in attachments:
output.addBlankPage().mergePage(attachment.pdf())
return output
def test_two_on_one_page(self):
# Build a document with two pages
pdf = PdfFileReader(self.get_pdf_stream())
output = PdfFileWriter()
output.addPage(pdf.getPage(0))
output.addPage(pdf.getPage(0))
assert output.getNumPages() == 2
assert output.getPage(0).extractText().count('Test') == 1
buf = StringIO()
output.write(buf)
buf.seek(0)
rv = self.app.get('/')
self.assertEquals(rv.status_code, 200)
rv = self.app.post('/handleform',
data={'file': (buf, 'test.pdf')})
rv = self.combine_and_download(pages_sheet='2')
pdf_download = PdfFileReader(StringIO(rv.data))
self.assertEquals(pdf_download.getPage(0).extractText().count('Test'),
2)
self.assertEquals(pdf_download.getNumPages(), 1)
self.clean_up()
def renderToPdf(envLL, filename, sizex, sizey):
"""Renders the specified Box2d and zoom level as a PDF"""
basefilename = os.path.splitext(filename)[0]
mergedpdf = None
for mapname in MAPNIK_LAYERS:
print 'Rendering', mapname
# Render layer PDF.
localfilename = basefilename + '_' + mapname + '.pdf';
file = open(localfilename, 'wb')
surface = cairo.PDFSurface(file.name, sizex, sizey)
envMerc = LLToMerc(envLL)
map = mapnik.Map(sizex, sizey)
mapnik.load_map(map, mapname + ".xml")
map.zoom_to_box(envMerc)
mapnik.render(map, surface)
surface.finish()
file.close()
# Merge with master.
if not mergedpdf:
mergedpdf = PdfFileWriter()
localpdf = PdfFileReader(open(localfilename, "rb"))
page = localpdf.getPage(0)
mergedpdf.addPage(page)
else:
localpdf = PdfFileReader(open(localfilename, "rb"))
page.mergePage(localpdf.getPage(0))
output = open(filename, 'wb')
mergedpdf.write(output)
output.close()
def test_concat_pdf_files( self ):
try:
os.unlink( r"docs/c.pdf" )
except:
pass
self.assertTrue( True )
input_a = PdfFileReader( file( r"docs/a.pdf", 'rb' ) )
input_b = PdfFileReader( file( r"docs/b.pdf", 'rb' ) )
output = PdfFileWriter()
for x in range( 0, input_a.getNumPages() ):
output.addPage( input_a.getPage( x ) )
for x in range( 0, input_b.getNumPages() ):
output.addPage( input_b.getPage( x ) )
outputStream = file( r"docs/c.pdf", 'wb' )
output.write( outputStream )
outputStream.close()
count = input_a.getNumPages() + input_b.getNumPages()
check = PdfFileReader( file( r"docs/c.pdf", 'rb' ) )
self.assertEqual( count, check.getNumPages() )
os.unlink( r"docs/c.pdf" )
def addPdfOverlay(self, pdf_doc, overlay_doc, output_doc, repeatOverlay=False): ''' Essentially merging two PDF documents. pdf_doc: (string) Path to PDF document. overlay_doc: (string) Path to PDF overlay document to overlay pdf_doc. repeatOverlay: (boolean) If set to True, page 1 of the overlay document is repeated for each page of the pdf_doc. (default: False) ''' pdf = PdfFileReader(file(pdf_doc, "rb")) pdf_overlay = PdfFileReader(file(overlay_doc, "rb")) page_cnt = pdf.numPages if repeatOverlay: overlay_pages = [pdf_overlay.getPage(0) for n in range(page_cnt)] else: overlay_pages = pdf_overlay.pages outputWriter = PdfFileWriter() for n in range(page_cnt): pg = pdf.getPage(n) pg.mergePage(overlay_pages[n]) outputWriter.addPage(pg) # Output outputStream = file(output_doc, "wb") outputWriter.write(outputStream) # Close streams outputStream.close() pdf.stream.close() pdf_overlay.stream.close()
def save_ready_template(request, id):
person_print = FIO.objects.get(id=id)
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.drawString(284, 579, "{} {}".format(person_print.name, person_print.surname))
can.showPage()
can.drawString(260, 494, "{} {}".format(person_print.name, person_print.surname))
can.showPage()
can.save()
# move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# read your existing PDF
existing_pdf = PdfFileReader(file("/Users/danilakimov/Desktop/template1.pdf", "rb"))
output = PdfFileWriter()
# add the "watermark" (which is the new pdf) on the existing page
page = existing_pdf.getPage(0)
page.mergePage(new_pdf.getPage(0))
output.addPage(page)
page = existing_pdf.getPage(1)
page.mergePage(new_pdf.getPage(1))
output.addPage(page)
# finally, write "output" to a real file
outputStream = file("/Users/danilakimov/Desktop/readytemplate.pdf", "wb")
output.write(outputStream)
outputStream.close()
return render(request, 'template_page.html', {'person_template': person_print})
def merge(fppath, bppath, outputpath, no_delete, fed_backwards):
fpfile = PdfFileReader(open(fppath))
bpfile = PdfFileReader(open(bppath))
outputfile = PdfFileWriter()
outputpages = []
for i in range(fpfile.getNumPages()):
backpages = True
try:
outputpages.append(fpfile.getPage(i))
if backpages:
if fed_backwards:
outputpages.append(bpfile.getPage(bpfile.getNumPages() - i - 1))
else:
outputpages.append(bpfile.getPage(i))
except IndexError:
backpages = False
if not no_delete:
outputpages = [page for page in outputpages if page.extractText() != '']
[outputfile.addPage(page) for page in outputpages]
outputfile.write(open(os.path.expanduser(outputpath), 'w'))
def rewrite(self, context, font={'name': 'Times-Roman', 'size': 11}):
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.setFont(font['name'], font['size'])
for i in context:
can.drawString(i['x'], i['y'], i['value'])
can.save()
# move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# read your existing PDF
existing_pdf = PdfFileReader(file(self.path, "rb"))
output = PdfFileWriter()
# merge the new file with the existing
page = existing_pdf.getPage(0)
page.mergePage(new_pdf.getPage(0))
output.addPage(page)
# finally, write "output" to a real file
outputStream = file(self.destination, "wb")
output.write(outputStream)
outputStream.close()
return True
def pdf_watermark_fast_first_page(self, pathname, Wm_f, wt1='',**kwargs):
try :
url_watermark=kwargs['url_wtm']
except:pass
from pyPdf import PdfFileWriter, PdfFileReader
import StringIO
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.drawString(10, 100, url_watermark)
can.save()
#move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# read your existing PDF
existing_pdf = PdfFileReader(file(pathname, "rb"))
output = PdfFileWriter()
# add the "watermark" (which is the new pdf) on the existing page
page = existing_pdf.getPage(0)
page.mergePage(new_pdf.getPage(0))
output.addPage(page)
# finally, write "output" to a real file
outputStream = file(Wm_f, "wb")
# import sys;sys.setrecursionlimit(11500)
output.write(outputStream)
outputStream.close()
return Wm_f
def add_guides(self):
pdf_in = PdfFileReader(open('sig.pdf', 'rb'))
pdf_out = PdfFileWriter()
for i in xrange(pdf_in.getNumPages()):
page = pdf_in.getPage(i)
if not i:
guides = StringIO()
if self.args.longarm:
create_pdf(
guides, a4lwidth_pt, a4lheight_pt, generate_longarm())
else:
if self.args.a5:
w, h = a5width_pt, a5height_pt
else:
w, h = a4lwidth_pt, a4lheight_pt
create_pdf(guides, w, h, generate_shortarm(
self.args.a5, bool(self.args.signature)))
pdf_guides = PdfFileReader(guides)
page.mergePage(pdf_guides.getPage(0))
pdf_out.addPage(page)
pdf_out.write(open('sigs.pdf', 'wb'))
def duplicated_pdf(stream):
"""Creates a duplicated pdf, from html stream (A.K.A. StringIO)"""
o_text = "<center><h3>-- Original --</h3></center>"
c_text = "<center><h3>-- Duplicado --</h3></center>"
pdf_conv = html_to_pdf.HTMLToPDFConverter()
original = PdfFileReader(StringIO(pdf_conv.convert(stream, o_text, o_text)))
stream.seek(0)
copy = PdfFileReader(StringIO(pdf_conv.convert(stream, c_text, c_text)))
out = PdfFileWriter()
for n in xrange(0, original.getNumPages()):
out.addPage(original.getPage(n))
for n in xrange(0, copy.getNumPages()):
out.addPage(copy.getPage(n))
encoded_pdf = StringIO()
out.write(encoded_pdf)
encoded_pdf.seek(0)
encoded_pdf = encoded_pdf.read()
return encoded_pdf
def pdf(coursesid,examsid):
''' Creates a blank PDF of this exam '''
# TODO: Obviously fix this up to generate actual PDFs; this is just a proof of concept
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from pyPdf import PdfFileWriter, PdfFileReader
from io import BytesIO
output = BytesIO()
p = canvas.Canvas(output, pagesize=letter)
p.drawString(100, 100, 'Hello')
p.save()
output.seek(0)
new_pdf = PdfFileReader(output)
existing_pdf = PdfFileReader(open('/home/treece/src/web/bubbleck/res/Template.pdf', 'rb'))
out = PdfFileWriter()
page = existing_pdf.getPage(0)
page.mergePage(new_pdf.getPage(0))
out.addPage(page)
a = BytesIO()
pdf_out = out.write(a)
response = make_response(pdf_out)
response.headers['Content-Disposition'] = "filename='sakulaci.pdf"
response.mimetype = 'application/pdf'
return response
class Packet(object):
def __init__(self, results_pdf):
self.results_pdf = PdfFileReader(open(results_pdf, "rb"))
self.num_pages = self.results_pdf.getNumPages()
self.result_list = self.result_string.split('\n')
self.entry_start = 0
@property
def num_rounds(self):
first_entry = self.results_pdf.getPage(0).extractText().split('\n')[0]
i = len(first_entry)-1
while i >= 0:
if first_entry[i] in digits:
return int(first_entry[i])
i-=1
@property
def result_string(self):
result_string = ""
for i in range(0, self.num_pages):
result_string+=self.results_pdf.getPage(i).extractText()
return result_string
def next_entry(self):
school_code = school_codes(self.result_list[self.entry_start])
start, end = self.entry_start+1, self.entry_start+self.num_rounds+2
rest = self.result_list[start:end]
self.entry_start+=self.num_rounds+2
return [school_code] + rest
def add_footer_pdf(in_fname, op_fname, imgPath): from pyPdf import PdfFileWriter, PdfFileReader from reportlab.pdfgen import canvas from StringIO import StringIO output = PdfFileWriter() # Using ReportLab to insert image into PDF imgTemp1 = StringIO() imgDoc1 = canvas.Canvas(imgTemp1) # Draw image on Canvas and save PDF in buffer imgDoc1.drawImage(imgPath, 210, 20, 155, 35) imgDoc1.save() overlay1 = PdfFileReader(StringIO(imgTemp1.getvalue())).getPage(0) in_file = PdfFileReader(file(in_fname,"rb")) n_pg = in_file.getNumPages() - 1 page = in_file.getPage(0) output.addPage(page) # Use PyPDF to merge the image-PDF into the template for i in range(n_pg): page = in_file.getPage(i+1) page.mergePage(overlay1) output.addPage(page) #Save the result outputStream = file(op_fname,"w") output.write(outputStream) outputStream.close()
def make_Cert(code, redeem_for):
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.setFont('Helvetica', 32)
can.drawString(280,540, code)
can.setFont('Helvetica', 32)
can.drawString(220,300, redeem_for)
can.save()
#move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# read your existing PDF
existing_pdf = PdfFileReader(file("cert.pdf", "rb"))
output = PdfFileWriter()
# add the "watermark" (which is the new pdf) on the existing page
page = existing_pdf.getPage(0)
page.mergePage(new_pdf.getPage(0))
output.addPage(page)
# finally, write "output" to a real file
outputStream = file(redeem_for.replace(" ", "_") + "_cert.pdf", "wb")
output.write(outputStream)
outputStream.close()
def render(self):
output = PdfFileWriter()
base1 = "%s/lib/%s" % (path.dirname(__file__), "kfza_base.pdf")
base1 = open(base1, 'rb')
b1_pdf = PdfFileReader(base1)
wm = b1_pdf.getPage(0)
p1 = PdfFileReader(self.generate_page_one())
page1 = p1.getPage(0)
page1.mergePage(wm)
output.addPage(page1)
bpdf = "%s/lib/%s" % (path.dirname(__file__), self.base_pdf)
with open(bpdf, 'rb') as pdf:
pf = PdfFileReader(pdf)
if pf.isEncrypted:
pf.decrypt('')
for page in range(pf.getNumPages()):
output.addPage(pf.getPage(page))
if self.context.course.extra_questions:
b1_pdf = PdfFileReader(base1)
wm = b1_pdf.getPage(0)
p1 = PdfFileReader(self.generate_page_one())
page1 = p1.getPage(1)
page1.mergePage(wm)
output.addPage(page1)
ntf = TemporaryFile()
output.write(ntf)
ntf.seek(0)
base1.close()
return ntf
def generate(donor):
os.system('mkdir -p output')
donor_url = donor.replace(' ','%20')
page1 = 'output/%s1' % (donor.replace(' ','-').lower())
page2 = 'output/%s2' % (donor.replace(' ','-').lower())
combined = 'output/%s.pdf' % (donor.replace(' ','-').lower())
if os.path.exists(combined): return
os.system('cp "%s" "%s.svg"' % (page1_svg, page1))
os.system('sed "s|/France/|/%s/|" "%s" > "%s.svg"' % (donor_url, page1_svg, page1))
os.system('inkscape --file="%s.svg" --verb=za.co.widgetlabs.update --verb=FileSave --verb=FileQuit 2> /dev/null' % (page1))
os.system('inkscape --file="%s.svg" --export-pdf="%s.pdf" 2> /dev/null' % (page1, page1))
os.system('cp "%s" "%s.svg"' % (page2_svg, page2))
os.system('sed "s|/France/|/%s/|" "%s" > "%s.svg"' % (donor_url, page2_svg, page2))
os.system('inkscape --file="%s.svg" --verb=za.co.widgetlabs.update --verb=FileSave --verb=FileQuit 2> /dev/null' % (page2))
os.system('inkscape --file="%s.svg" --export-pdf="%s.pdf" ' % (page2, page2))
# Merge pages
input1 = PdfFileReader(file('%s.pdf' % (page1), 'rb'))
input2 = PdfFileReader(file('%s.pdf' % (page2), 'rb'))
output = PdfFileWriter()
output.addPage(input1.getPage(0))
output.addPage(input2.getPage(0))
outputStream = file(combined, 'wb')
output.write(outputStream)
outputStream.close()
sleep(2)
def reshuffle(output_directory, input_file, filename):
output_pdf = PdfFileWriter()
with open(input_file, 'rb') as readfile:
input_pdf = PdfFileReader(readfile)
total_pages = input_pdf.getNumPages()
if total_pages == 7:
print filename,
if "hardest_jet_phi_all_linear" in filename or "hardest_jet_eta_all_linear" in filename or "hardest_jet_pT_all_linear" in filename or "hardest_jet_pT_jec_all_linear" in filename or "area" in filename or "jec" in filename or "pfc_neutral_0_100_pT" in filename or "pfc_charged_0_100_pT" in filename or "pfc_neutral_0_5_pT" in filename or "pfc_charged_0_5_pT" in filename:
output_pdf.addPage(input_pdf.getPage(4))
output_pdf.addPage(input_pdf.getPage(5))
output_pdf.addPage(input_pdf.getPage(6))
print "85"
else:
output_pdf.addPage(input_pdf.getPage(5))
output_pdf.addPage(input_pdf.getPage(4))
output_pdf.addPage(input_pdf.getPage(6))
print "150"
for i in range(0, 4):
output_pdf.addPage(input_pdf.getPage(i))
with open(output_directory + filename, "wb") as writefile:
output_pdf.write(writefile)
def add_terms_and_conditions(self, ids, original_report_pdf,
original_report):
terms_and_conditions_decoded = False
default_terms_and_conditions_decoded = False
user = self.env['res.users'].browse(self._uid)
# todo change user language to report language (client language)
language_field = original_report.terms_conditions_language_field
model = original_report.model
object = self.env[model].browse(ids)
localdict = {'o': object}
eval('document_language = o.%s' % language_field, localdict,
mode="exec", nocopy=True)
document_language = localdict.get('document_language',
self._context.get('lang'))
company = object.company_id
# todo check language
terms_and_conditions_list = company.terms_and_conditions
for terms_and_conditions in terms_and_conditions_list:
if terms_and_conditions.language == document_language:
terms_and_conditions_decoded =\
base64.decodestring(terms_and_conditions.datas)
if terms_and_conditions.language == 'default':
default_terms_and_conditions_decoded = \
base64.decodestring(terms_and_conditions.datas)
if not terms_and_conditions_decoded:
terms_and_conditions_decoded = \
default_terms_and_conditions_decoded or False
if terms_and_conditions_decoded:
writer = PdfFileWriter()
stream_original_report = StringIO(original_report_pdf)
reader_original_report = PdfFileReader(stream_original_report)
stream_terms_and_conditions = StringIO(terms_and_conditions_decoded)
reader_terms_and_conditions = PdfFileReader(
stream_terms_and_conditions)
for page in range(0, reader_original_report.getNumPages()):
writer.addPage(reader_original_report.getPage(page))
for page in range(0, reader_terms_and_conditions.getNumPages()):
writer.addPage(reader_terms_and_conditions.getPage(page))
stream_to_write = StringIO()
writer.write(stream_to_write)
combined_pdf = stream_to_write.getvalue()
return combined_pdf
else:
return original_report_pdf
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 pdf2text(source_pdf,target_pages): pdf = PdfFileReader(file(source_pdf, "rb")) text_string = '' try: #loop over pages for page in target_pages: text_string += pdf.getPage(int(page-1)).extractText() except: #just one page text_string += pdf.getPage(int(target_pages-1)).extractText() return text_string
def test_watermark(self):
# Make sure our Test string is available in the original document
pdf = PdfFileReader(self.get_pdf_stream())
assert 'Test' in pdf.getPage(0).extractText()
assert 'TEST_WATERMARK' not in pdf.getPage(0).extractText()
rv = self.combine_and_download(text_overlay='TEST_WATERMARK')
pdf_download = PdfFileReader(StringIO(rv.data))
self.assert_('Test' in pdf_download.getPage(0).extractText())
self.assert_('TEST_WATERMARK' in pdf_download.getPage(0).extractText())
self.clean_up()
def merge_pdf(url_list):
# Download each PDF and merge them into one giant PDF, post this giant PDF to anonfiles.com, add URL to scraperwiki database
output = PdfFileWriter()
for url in url_list:
if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/083.pdf":
url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/83.pdf"
url[1] = "83.pdf"
if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/039.pdf":
url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/39.pdf"
url[1] = "39.pdf"
if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/021.pdf":
url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/21.pdf"
url[1] = "21.pdf"
if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/016S.pdf":
url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/16S.pdf"
url[1] = "16S.pdf"
if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/015.pdf":
url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/15.pdf"
url[1] = "15.pdf"
pdf_file = os.system("wget %s" % url[0])
input1 = PdfFileReader(file('/tmp/%s' % url[1], "rb"))
numPages = input1.getNumPages()
print "number of pages = %s" % (numPages)
page1 = input1.getPage(0)
page2 = input1.getPage(1)
output.addPage(page1)
output.addPage(page2)
if numPages == 3:
page3 = input1.getPage(2)
output.addPage(page3)
final_page_count = output.getNumPages()
print "Number of Pages in Final = %s" % (final_page_count)
outputStream = file("/tmp/bus.pdf", "wb")
output.write(outputStream)
outputStream.close()
reply = os.system('curl -kF "[email protected];filename=bus.pdf" https://anonfiles.com/api/hotlink -o "reply.txt"')
with open('reply.txt', 'r') as f:
read_data = f.read()
data_dict = {
'Title':'Link to COTA Bus Schedule',
'URL':read_data,
}
scraperwiki.sqlite.save(unique_keys=['Title', 'URL'], data=data_dict)
def run(self):
def getSrcDim(srcPage):
return (float(srcPage.mediaBox.getWidth()),
float(srcPage.mediaBox.getHeight()))
def getDestDim():
if self.opts.orientation == const.PORTRAIT:
return self.opts.size
elif self.opts.orientation == const.LANDSCAPE:
return (self.opts.size[1], self.opts.size[0])
def getScale(srcPage):
destWidth, destHeight = getDestDim()
return (getSrcDim(srcPage)[const.WIDTH]/float(destWidth))
def getScaledDestDim(srcPage):
return [x * int(getScale(srcPage)) for x in getDestDim()]
reader = PdfFileReader(file(self.infile, "rb"))
writer = PdfFileWriter(
documentInfo=reader.getDocumentInfo(), authors=["Vimala"])
#self.opts.count
srcPage = reader.getPage(0)
height = getSrcDim(srcPage)[const.HEIGHT]
totalHeight = self.opts.count * height
destPage = writer.addBlankPage(*getScaledDestDim(srcPage))
print totalHeight
fitScale = getScaledDestDim(srcPage)[const.HEIGHT] / float(totalHeight)
print fitScale
srcPage.scale(fitScale, fitScale)
#scale = getScale(srcPage)
#srcPage.scale(scale, scale)
destPage.mergeTranslatedPage(srcPage, 0, height * 2 - .2 * height)
srcPage = reader.getPage(1)
srcPage.scale(fitScale, fitScale)
destPage.mergeTranslatedPage(srcPage, 0, height - .1 * height)
srcPage = reader.getPage(3)
srcPage.scale(fitScale, fitScale)
destPage.mergeTranslatedPage(srcPage, 0, 0)
#import pdb;pdb.set_trace()
writer.write(open(self.outfile, "wb"))
def doc_overlay(request, document_uuid, lot_number, qrcode=True):
report = Report.objects.get(lot_number=lot_number)
document = Document.objects.get(uuid=document_uuid)
response = HttpResponse(content_type='application/pdf')
response['Content-Disposition'] = 'filename="inspection_report.pdf"'
outputPDF = PdfFileWriter()
packet = StringIO()
# read your existing PDF
f = urlopen(Request(document.file.url)).read()
mem = StringIO(f)
existing_pdf = PdfFileReader(mem)
pages = existing_pdf.getNumPages()
first_page = existing_pdf.getPage(0)
width = float(first_page.mediaBox.getWidth())
height = float(first_page.mediaBox.getHeight())
# create a new PDF with Reportlab
p = canvas.Canvas(packet, pagesize=letter)
#p.setFillColorRGB(255,255,255)
#p.rect(0*mm, 271*mm, 205*mm, 12*mm, fill=1, stroke=0)
p.setFillColorRGB(0,0,0)
p.setFont("Helvetica", 7)
p.drawCentredString(width/2.0,height-9.0, "%s LOT # %s / %s (doc# %s)" %
(settings.PDF_COMPANY_SHORT_NAME,
report.lot_number, str(report.created_at.date()), document.uuid))
barcode = createBarcodeDrawing('QR', value="%s%s" % (request.META['HTTP_HOST'], report.get_absolute_url()))
barcode.drawOn(p,175*mm, 10*mm)
p.save()
#move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# add the "watermark" (which is the new pdf) on the existing page
for x in range(0,pages):
page = existing_pdf.getPage(x)
page.mergePage(new_pdf.getPage(0))
outputPDF.addPage(page)
# finally, write "output" to a real file
outputPDF.write(response)
#f.close()
action.send(request.user, verb="viewed document", action_object=document, target=report)
return response
def ProcessPDF ( filename, largeformatsize ):
"""
Open a PDF to perform a page count and check for corrupt files
Count small pages and large pages as defined above.
"""
pdf_count = {
"npages":0,
"nlargepages":0,
"nsmallpages":0,
}
try:
#Open file
filestream = file(filename, "rb")
#load into pypdf
pdfFile = PdfFileReader(filestream)
#First access into pdf contents
# Raises decryption/security exceptions here
npages = pdfFile.getNumPages()
except IOError:
err = '<{}> :: Could not open file. Check permissions?'.format(filename)
return False, err
except Exception as e:
err = '<{}> :: {}'.format(filename, e)
return False, err
for ii in range(npages):
pdf_count["npages"] += 1
'''
Calculate page dimensions and pricing category
Dimensions are returned by pyPDF in Points (72 points = 1 inch)
See:
http://en.wikipedia.org/wiki/Point_(typography)
http://en.wikipedia.org/wiki/Paper_size
'''
width = (pdfFile.getPage(ii).artBox.getUpperRight_x()/72 -
pdfFile.getPage(ii).artBox.getLowerLeft_x()/72)
height = (pdfFile.getPage(ii).artBox.getUpperRight_y()/72 -
pdfFile.getPage(ii).artBox.getLowerLeft_y()/72)
if (width * height) > largeformatsize:
pdf_count["nlargepages"] += 1
else:
pdf_count["nsmallpages"] += 1
return True, pdf_count
def pdf(request, region, name, period_name):
"""Generate and return a PDF for the given tax form."""
company = request.company
form = registry.get_form(region, name)
period = get_period(period_name, None)
if form is None or period is None:
raise Http404
filing = form.tally(company, period)
c = canvas.Canvas("hello.pdf")
for spec in form.pdf_fields:
x, y, name = spec[:3]
value = getattr(filing.pages[0], name, None)
if value is None:
value = u''
if isinstance(value, Decimal):
dollars, cents = unicode(value).split('.')
c.drawString(x - 8 - c.stringWidth(dollars), y, dollars)
c.drawString(x + 4, y, cents)
elif len(spec) > 3:
value = unicode(value)
step = spec[3]
for i, char in enumerate(value):
c.drawString(x + i * step, y, char)
else:
value = unicode(value)
c.drawString(x, y, value)
c.showPage()
datadir = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'data')
pdfpath = os.path.join(datadir, form.filename)
taxform = PdfFileReader(file(pdfpath, 'rb'))
rendering = PdfFileReader(StringIO(c.getpdfdata()))
output = PdfFileWriter()
watermark = rendering.getPage(0)
page1 = taxform.getPage(0)
page1.mergePage(watermark)
output.addPage(page1)
pdfdata = StringIO()
output.write(pdfdata)
return HttpResponse(pdfdata.getvalue(), content_type='application/pdf')
def AddWatermark(self,watermark,filein,fileout):
#Use reportlab to create a PDF that will be used
#as a watermark on another PDF.
c= canvas.Canvas("temp_watermark.pdf")
c.setFont("Courier", 60)
#This next setting with make the text of our
#watermark gray, nice touch for a watermark.
c.setFillGray(0.5,0.5)
#Set up our watermark document. Our watermark
#will be rotated 45 degrees from the direction
#of our underlying document.
c.saveState()
c.translate(500,100)
c.rotate(45)
c.drawCentredString(0, 0, "A WATERMARK!")
c.drawCentredString(0, 300, "A WATERMARK!")
c.drawCentredString(0, 600, "A WATERMARK!")
c.restoreState()
c.save()
#Read in the PDF that will have the PDF applied to it.
output = PdfFileWriter()
input1 = PdfFileReader(file(filein, "rb"))
#Just to demo this function from pyPdf.
#If the PDF has a title, this will print it out.
print "title = %s" % (input1.getDocumentInfo().title)
#Open up the orgininal PDF.
page1 = input1.getPage(0)
#Read in the file created above by ReportLab for our watermark.
twatermark = PdfFileReader(file("temp_watermark.pdf", "rb"))
#Apply the watermark by merging the two PDF files.
page1.mergePage(twatermark.getPage(0))
#Send the resultant PDF to the output stream.
output.addPage(page1)
#Just to demo this function from pyPdf.
#Return the number of pages in the watermarked PDF.
print "watermarked_pdf.pdf has %s pages." % input1.getNumPages()
#write the output of our new, watermarked PDF.
outputStream = file(fileout, "wb")
output.write(outputStream)
outputStream.close()
os.remove("temp_watermark.pdf")
os.remove(filein)
def main(argv = None):
"""
funcao para pegar uma pagina de um pdf
argumentos:
nome_do_arquivo_de_entrada nome_do_arquivo_de_saida numero_da_pagina_inicial [numero_da_pagina_final]
"""
if argv is None:
argv = sys.argv[1:]
output = PdfFileWriter()
input = PdfFileReader(file(argv[0],"rb"))
output.addPage(input.getPage(int(argv[2])))
if len(argv) >= 4:
for i in range(int(argv[2])+1,int(argv[3])+1):
output.addPage(input.getPage(i))
output.write(file(argv[1],"wb"))
def Merge():
from pyPdf import PdfFileWriter, PdfFileReader
output_pdf = PdfFileWriter()
with open(r'input.pdf', 'rb') as readfile:
input_pdf = PdfFileReader(readfile)
total_pages = input_pdf.getNumPages()
for page in xrange(total_pages - 1, -1, -2):
print page
page1 = input_pdf.getPage(page)
page2 = input_pdf.getPage(page-1)
page1.mergePage(page2)
output_pdf.addPage(page1)
with open(r'output.pdf', "wb") as writefile:
output_pdf.write(writefile)
def download_pdf(url):
writer = PdfFileWriter()
code = requests.get(url, stream=True).status_code
if code != 404:
remoteFile = urlopen(Request(url)).read()
memoryFile = StringIO(remoteFile)
pdfFile = PdfFileReader(memoryFile)
for pageNum in xrange(pdfFile.getNumPages()):
currentPage = pdfFile.getPage(pageNum)
#currentPage.mergePage(watermark.getPage(0))
writer.addPage(currentPage)
outputStream = open('pdf_folder/%s'%basename(url),"wb")
writer.write(outputStream)
outputStream.close()
return (True)
else:
return (False)
def getDocData(Fdoc):
from pyPdf import PdfFileReader
import codecs
f = PdfFileReader(file(Fdoc, "rb"))
pages = f.getNumPages()
pages = int(pages - 1)
name = Fdoc.replace("input_PDF", "output_text")[:-4] + ".txt"
#I want to replace test 2 with something dynamic so I am not writing over my files
g = codecs.open(name, encoding='utf-8', mode='wb')
#looping through the pages and putting the contents in to a text document
l = 0
for t in range(0, pages):
while l <= pages:
pg = f.getPage(l)
pgtxt = pg.extractText()
l = l + 1
g.write(pgtxt)
def split_pages(input_filename, prefix=None):
"""
Splits up a PDF file into single page PDF files. Returns
path string where resulting PDF files are
located. It is the caller's responsibility to clean the disk when
the files are no longer necessary. The best way to do it is to
call result.rmtree()
"""
output_dir = None
try:
if prefix is None:
# create a temporary directory
output_dir = mkdtemp('donomo')
prefix = os.path.join(output_dir, 'page-')
# open PDF
pdf_input = PdfFileReader(file(input_filename, 'rb'))
# iterate over pages in the input PDF
for i in xrange(pdf_input.getNumPages()):
# get n-th page
page = pdf_input.getPage(i)
# create a one-page pdf writer
pdf_output = PdfFileWriter()
pdf_output.addPage(page)
# save it in a new file
page_filename = '%s%03d.pdf' % (prefix, i)
page_filestream = file(page_filename, "wb")
pdf_output.write(page_filestream)
page_filestream.close()
# return the directory name to the caller
return os.path.dirname(prefix)
except Exception, e:
logging.error(str(e))
# delete a temporary directory along with all its contents
if output_dir:
rmtree(output_dir)
raise
def createForm(info):
luokka = info['Luokka']
if info['Koiran sukupuoli'] == 'uros':
info['Uros'] = 'x'
elif info['Koiran sukupuoli'] == 'narttu':
info['Narttu'] = 'x'
packet = StringIO.StringIO()
c = canvas.Canvas(packet, pagesize=A4)
for k in info.keys():
if k in placements[luokka].keys():
x, y = placements[luokka][k]
y = y + offsets[luokka]
text = info[k]
c.drawString(x * cm, y * cm, text)
c.save()
packet.seek(0)
new_pdf = PdfFileReader(packet)
output = PdfFileWriter()
output.addPage(new_pdf.getPage(0))
outputStream = file("/tmp/stamp.pdf", "wb")
output.write(outputStream)
outputStream.close()
try:
os.mkdir("esitaytetyt")
except:
pass
print " ".join([
'pdftk',
"pohjat/%s.pdf" % luokka, 'stamp', '/tmp/stamp.pdf', 'output',
'esitaytetyt/%s.pdf' % info['Rekisterinumero'].replace('/', '-')
])
call([
'pdftk',
"pohjat/%s.pdf" % luokka, 'stamp', '/tmp/stamp.pdf', 'output',
'esitaytetyt/%s.pdf' % info['Rekisterinumero'].replace('/', '-')
])
def add_omr_marks(self, pdf_data, is_latest_document):
# Documentation
# http://meteorite.unm.edu/site_media/pdf/reportlab-userguide.pdf
# https://pythonhosted.org/PyPDF2/PdfFileReader.html
# https://stackoverflow.com/a/17538003
# https://gist.github.com/kzim44/5023021
# https://www.blog.pythonlibrary.org/2013/07/16/
# pypdf-how-to-write-a-pdf-to-memory/
self.ensure_one()
pdf_buffer = StringIO.StringIO()
pdf_buffer.write(pdf_data)
existing_pdf = PdfFileReader(pdf_buffer)
output = PdfFileWriter()
total_pages = existing_pdf.getNumPages()
def lastpair(a):
b = a - 1
if self.omr_single_sided or b % 2 == 0:
return b
return lastpair(b)
# print latest omr mark on latest pair page (recto)
latest_omr_page = lastpair(total_pages)
for page_number in range(total_pages):
page = existing_pdf.getPage(page_number)
# only print omr marks on pair pages (recto)
if self.omr_single_sided or page_number % 2 is 0:
is_latest_page = is_latest_document and \
page_number == latest_omr_page
marks = self._compute_marks(is_latest_page)
omr_layer = self._build_omr_layer(marks)
page.mergePage(omr_layer)
output.addPage(page)
out_buffer = StringIO.StringIO()
output.write(out_buffer)
return out_buffer.getvalue()
def pdf2Text(pdf):
from pyPdf import PdfFileWriter, PdfFileReader
with open("/tmp/temp_crawler.pdf", "wb") as file_pdf:
file_pdf.write(pdf)
try:
pdf = PdfFileReader(file("/tmp/temp_crawler.pdf", "rb"))
content = ""
for i in range(0, pdf.getNumPages()):
content += pdf.getPage(i).extractText() + "\n"
content = u" ".join(content.replace(u"\xa0", u" ").strip().split())
except Exception:
print "[ Error con el PDF ]"
return " "
return unidecode(content)
def _merge_pdf(self, documents):
"""Merge PDF files into one.
:param documents: list of path of pdf files
:returns: path of the merged pdf
"""
writer = PdfFileWriter()
streams = [
] # We have to close the streams *after* PdfFilWriter's call to write()
for document in documents:
pdfreport = file(document, 'rb')
streams.append(pdfreport)
reader = PdfFileReader(pdfreport)
for page in range(0, reader.getNumPages()):
writer.addPage(reader.getPage(page))
merged_file_fd, merged_file_path = tempfile.mkstemp(
suffix='.pdf', prefix='report.merged.tmp.')
with closing(os.fdopen(merged_file_fd, 'w')) as merged_file:
writer.write(merged_file)
for stream in streams:
stream.close()
return merged_file_path
def remove_pages(pdf_file, max_pages=1):
output = PdfFileWriter()
with open(pdf_file, 'r') as pdf:
input = PdfFileReader(pdf)
total_pages = input.getNumPages()
for i in xrange(max_pages):
if i >= total_pages:
break
p = input.getPage(i)
output.addPage(p)
with open(pdf_file + '.tmp', 'w') as pdf:
output.write(pdf)
os.remove(pdf_file)
os.rename(pdf_file + '.tmp', pdf_file)
return pdf_file
def create_source_pdf(self, cr, uid, ids, data, report_xml, context=None):
results = self._create_source(cr, uid, ids, data, report_xml, context)
if results and len(results) == 1:
return results[0]
if results:
if deferred:
deferred.set_status(_('Concatenating single documents'))
not_pdf = filter(lambda r: r[1] != 'pdf', results)
if not_pdf:
raise osv.except_osv(_('Error!'),
_('Unsupported combination of formats!'))
#if results[0][1]=='pdf':
output = PdfFileWriter()
for r in results:
reader = PdfFileReader(StringIO(r[0]))
for page in range(reader.getNumPages()):
output.addPage(reader.getPage(page))
s = StringIO()
output.write(s)
return s.getvalue(), results[0][1]
return self.create_single_pdf(cr, uid, ids, data, report_xml, context)
def kesit(dosya_yolu , sayfa1 , sayfa2=0):
"""pdf dosyasının sayfa1'den sayfa2'ye kadar olan kısmını alır
sayfa2 verilmesse sayfa1'den sonuna kadar alır
"""
try:
kaynak = PdfFileReader(open(dosya_yolu, "rb"))
islem = PdfFileWriter()
if sayfa1<0:
(-1)*sayfa1
if sayfa2==0:
sayfa2=kaynak.getNumPages()
if sayfa2<=sayfa1:
sayfa2=sayfa1+1
hedef = open("data.pdf", "wb")
for i in range(int(sayfa1),int(sayfa2)):
islem.addPage(kaynak.getPage(i))
islem.write(hedef)
hedef.close()
print "»» pdf oluşturuldu"
except:
print "»» pdf oluşturulamadı"
def genfile(srcfile, desfile, startpage, endpage):
"""
根据startpage跟endpage做pdf文件切分
:param srcfile:
:param desfile:
:param startpage:
:param endpage:
:return:
"""
output = PdfFileWriter()
src = PdfFileReader(file(srcfile, "rb"))
(filepath, filename) = os.path.split(desfile)
if not os.path.exists(filepath):
os.makedirs(filepath)
des = file(desfile, "wb")
for i in range(startpage - 1, endpage):
output.addPage(src.getPage(i))
output.write(des)
des.close()
del src
del des
def fisk_pdf(pdffile, directory):
name = pdffile[:-4]
g = open(os.path.join(directory, name, name + ".md"), "w")
print("# Notes on: ", file = g)
input = PdfFileReader(file(pdffile, "rb"))
print("Number of pages %s" % input.getNumPages())
j = 0
for p in [input.getPage(i) for i in range(0,input.getNumPages())]:
j = j + 1
output = PdfFileWriter()
output.addPage(p)
print("### Page " + str(j), file = g)
imagefile = os.path.join(directory, name, "images", "file_" + str(j) + ".pdf")
imagefilePNG = os.path.join(directory, name, "images", "file_" + str(j) + ".png")
f = open(imagefile, "w")
output.write(f)
f.close()
textfile = os.path.join(directory, name, "texts", "file_" + str(j) + ".txt")
textfileASCII = os.path.join(directory, name, "texts", "file_" + str(j) + "_ascii.txt")
cmd = "pdftotext " + imagefile + " " + textfile # extracts text from the pdffile
os.system(cmd)
cmd = "iconv -c -f utf8 -t ascii " + textfile + " > " + textfileASCII
# ./texts/file_" + str(j) + ".txt" + " > ./texts/file_" + str(j) + "_ascii.txt"
os.system(cmd)
cmd = "convert -density 100 " + imagefile + " -quality 100 " + imagefilePNG
os.system(cmd)
print("![](./images/file_" + str(j) + ".png)", file = g)
print("", file = g)
print("### Text from page " + str(j), file = g)
t = open(os.path.join(directory, name, "texts", "file_" + str(j) + "_ascii.txt"), "r")
txt = t.read()
txt = txt.replace('\n', ' ').replace('\r', '').replace(' ', '')
n = 80
chunks = [txt[i:i+n] for i in range(0, len(txt), n)]
for c in chunks:
print(" " + c, file = g)
print("", file = g)
print("### Notes on page " + str(j), file = g)
g.close()
def Split(d):
args = d["args"]
if len(args) < 2:
Error("split needs at least two arguments")
prefix, count = args[0], d["-n"]
for filename in args[1:]:
reader = PdfFileReader(open(filename, "rb"))
numpages = reader.getNumPages()
# Get a format string that allows the integer numbers to have
# leading zeros so that they will sort in natural order.
lt = int(ceil(log10(numpages)))
assert lt > 0
fmt = "%%0%dd" % lt
for i in range(reader.getNumPages()):
output_file = prefix + (fmt % count) + ".pdf"
writer = GetOutputWriter(output_file, d)
output_stream = open(output_file, "wb")
page = reader.getPage(i)
Sentinel(d)
writer.addPage(page)
writer.write(open(output_file, "wb"))
count += 1
def test1(self):
"Test generating several 'n-up' docs, n = (m**2) / 2..."
for path0 in ("samples/test-a4-l.pdf", "samples/test-a4-p.pdf"):
for n in (2, 8, 18):
outName = os.path.splitext(path0)[0] + "-%dup.pdf" % n
path1 = os.path.join(".", outName)
generateNup(path0, n, path1, verbose=False) # , dirs="UL")
# assert output has correct number of pages
input = PdfFileReader(file(path0, "rb"))
np0 = input.getNumPages()
input = PdfFileReader(file(path1, "rb"))
np1 = input.getNumPages()
self.assertEqual(np1, math.ceil(np0 / float(n)))
# assert output page(s) has/have correct text content
for pn in range(np1):
page = input.getPage(pn)
text = page.extractText().split()
exp = group([str(num) for num in range(np0)], n)[pn]
self.assertEqual(text, exp)
def append_file(out, input_file_name):
print("Open %s" % input_file_name)
input1 = PdfFileReader(file(input_file_name, "rb"))
page = input1.getPage(0)
upperleft_x = page.mediaBox.getUpperLeft_x()
upperleft_y = page.mediaBox.getUpperLeft_y()
upperright_x = page.mediaBox.getUpperRight_x()
upperright_y = page.mediaBox.getUpperRight_y()
# print(page.mediaBox)
# print(page.mediaBox.getUpperLeft_x())
# print(page.mediaBox.getUpperLeft_y())
# print(page.mediaBox.getUpperRight_x())
# print(page.mediaBox.getUpperRight_y())
# print(page.mediaBox.lowerLeft)
# print(page.mediaBox.upperLeft)
# print(page.mediaBox.lowerRight)
# print(page.mediaBox.upperRight)
if backpage:
# устанавливаем зону обрезки по оборотной стороне уведомления
page.mediaBox.upperRight = (
float(page.mediaBox.getUpperRight_x()),
float(page.mediaBox.getUpperRight_y()) -
(float(page.mediaBox.getUpperLeft_y()) * 0.325))
page.mediaBox.lowerRight = (
float(page.mediaBox.getLowerRight_x()) * 0.7,
float(page.mediaBox.getUpperRight_y()) -
(float(page.mediaBox.getUpperLeft_y()) * 0.48))
else:
# устанавливаем зону обрезки по основной стороне уведомления
page.mediaBox.lowerRight = (
float(page.mediaBox.getLowerRight_x()) * 0.7,
float(page.mediaBox.getUpperLeft_y()) -
(float(page.mediaBox.getUpperLeft_y()) * 0.325))
#print(page.mediaBox)
out.addPage(page)
print('Croped and added to output file')
def test_rotation_different_to_unrotated(self):
# Make sure our Test string is available in the original document
pdf = PdfFileReader(self.get_pdf_stream())
assert 'Test' in pdf.getPage(0).extractText()
rv = self.app.get('/')
self.assertEquals(rv.status_code, 200)
rv = self.app.post('/handleform',
data={'file': (self.get_pdf_stream(), 'test.pdf')})
# Start build without rotation
rv = self.combine_and_download()
content_no_rotation = rv.data
# Start build with rotation
rv = self.combine_and_download(rotate='180')
content = rv.data
self.assert_(content_no_rotation != content)
self.clean_up()
def _combine_pdf_files(self, tmp_folder_name, output_report):
output_path = tmp_folder_name + output_report
output_temp_path = tmp_folder_name + 'temp.pdf'
cmd = """gs -q -dNOPAUSE -sDEVICE=pdfwrite -sOUTPUTFILE=%s \
-dBATCH %s*water*.pdf""" % (output_temp_path, tmp_folder_name)
os.system(cmd)
# remove the last empty page
input_stream = PdfFileReader(file(output_temp_path, 'rb'))
output_stream = PdfFileWriter()
pagenum = input_stream.getNumPages()
for i in range(pagenum - 1):
page = input_stream.getPage(i)
output_stream.addPage(page)
out_stream = file(output_path, 'wb')
try:
output_stream.write(out_stream)
finally:
out_stream.close()
def parse_pdf(self, pdfname):
if not os.path.exists(pdfname):
print 'Missing API documentation, downloading from: %s' % pdfurl
urllib.urlretrieve(pdfurl, pdfname)
print 'Compiling API methods...'
apidoc = PdfFileReader(file(pdfname, 'rb'))
for p in range(0, apidoc.getNumPages()):
doc = apidoc.getPage(p).extractText()
mCall = re.search(r'<methodCall>.+</methodCall>', doc)
mResp = re.search(r'<methodResponse>.+</methodResponse>', doc)
section = None
if mCall:
xml = mCall.group()
method = re.search(r'<methodName>(UDNS_\w+)</methodName>', xml)
if not method:
continue
section = method.group(1)
if re.search(r'[Cc]onnect', section):
continue # exclude connection-related methods
if section not in self.config._sections:
self.config.add_section(section)
patt = re.compile(
r'<value><([^\s]+)>([^\s]+)</([^\s]+)></value>')
match = re.findall(patt, xml)
order = []
for m in match:
key = '%s+%s' % m[0:2]
self.config.set(section, key, m[2])
order.append(key)
if order:
self.config.set(section, 'order', ','.join(order))
if section and re.search(r'<fault>', doc):
self.config.set(section, 'fault', True)
if section and mResp:
xml = mResp.group()
record = re.search(r'<array>\s*<data>\s*<value>\s*<([_\w]+)>',
xml)
if record:
self.config.set(section, 'array', record.group(1))
def print_danfe(inv):
str_pdf = ""
paths = []
if inv.nfe_version == '1.10':
from pysped.nfe.leiaute import ProcNFe_110
procnfe = ProcNFe_110()
elif inv.nfe_version == '2.00':
from pysped.nfe.leiaute import ProcNFe_200
procnfe = ProcNFe_200()
elif inv.nfe_version == '3.10':
from pysped.nfe.leiaute import ProcNFe_310
procnfe = ProcNFe_310()
file_xml = monta_caminho_nfe(inv.company_id, inv.nfe_access_key)
if inv.state not in ('open', 'paid', 'sefaz_cancelled'):
file_xml = os.path.join(file_xml, 'tmp/')
procnfe.xml = os.path.join(file_xml, inv.nfe_access_key + '-nfe.xml')
danfe = DANFE()
danfe.logo = add_backgound_to_logo_image(inv.company_id)
danfe.NFe = procnfe.NFe
danfe.leiaute_logo_vertical = inv.company_id.nfe_logo_vertical
danfe.protNFe = procnfe.protNFe
danfe.caminho = "/tmp/"
danfe.gerar_danfe()
paths.append(danfe.caminho + danfe.NFe.chave + '.pdf')
output = PdfFileWriter()
s = StringIO()
for path in paths:
pdf = PdfFileReader(file(path, "rb"))
for i in range(pdf.getNumPages()):
output.addPage(pdf.getPage(i))
output.write(s)
str_pdf = s.getvalue()
s.close()
return str_pdf
def pdf_watermark_fast(self, pathname, Wm_f, wt1='', **kwargs):
try:
url_watermark = kwargs['url_wtm']
except:
pass
from pyPdf import PdfFileWriter, PdfFileReader
# fo=os.getcwd()
# CurrentDir=os.path.dirname(os.path.realpath(__file__))
import watter_marker
url_watermark2 = url_watermark.replace(".", "_")
url_watermark2 = url_watermark2.replace("://", "__")
# CurrentDir=os.path.dirname(os.path.realpath(__file__)).replace('\\','/')
if wt1 == '':
if not os.path.isfile(self.Watermarked_PDF_Dir + "/" +
"watermarker_slow" + url_watermark2 +
".pdf"):
wt1 = self.watermark_file(self.Watermarked_PDF_Dir + "/" +
"watermarker_slow" + url_watermark2 +
".pdf",
url_watermark,
center_text=False)
else:
wt1 = self.Watermarked_PDF_Dir + "/" + "watermarker_fast.pdf"
if True:
watermark1 = PdfFileReader(file(wt1, 'rb'))
else:
wt1 = self.watermark_file(self.Watermarked_PDF_Dir + "/" +
"watermarker_slow" + url_watermark2 +
".pdf",
url_watermark,
center_text=False)
watermark1 = PdfFileReader(file(wt1, 'rb'))
wtt = watermark1.getPage(0)
watter_marker.op_w_input(pathname, wt1, Wm_f)
# Wm_f is full address
return Wm_f
def collate(self, remove_temp=True, remove_sources=False):
from pyPdf import PdfFileWriter, PdfFileReader
from svglib.svglib import svg2rlg
from reportlab.graphics import renderPDF
# Make temporary folder
dest_dir, _ = os.path.split(self.dest)
if not os.path.exists(dest_dir):
raise RuntimeError, "output place %s d.n.e." % dest_dir
temp_dir = dest_dir + '/tmp'
if not os.path.exists(temp_dir):
os.mkdir(temp_dir)
# Fix SVG windows for PDFing
temp_page = [
'%s/page%i.tmp' % (temp_dir, i) for i, _ in enumerate(self.sources)
]
for s, d in zip(self.sources, temp_page):
hack_svg_viewbox(s, d)
# Generate single PDF pages
for s in temp_page:
drawing = svg2rlg(s)
renderPDF.drawToFile(drawing, s, autoSize=1)
# Concatenate the PDF pages into a single document
output = PdfFileWriter()
for s in temp_page:
i = PdfFileReader(open(s, 'rb'))
output.addPage(i.getPage(0))
del i
fout = file(self.dest, 'wb')
output.write(fout)
fout.close()
# Remove the temporary folder
if remove_temp:
shutil.rmtree(temp_dir)
# Remove the source images
if remove_sources:
map(os.remove, self.sources)
return True
def createForm(dogs, filename):
packet = StringIO.StringIO()
c = canvas.Canvas(packet, pagesize=A4)
extraoffset = {'Luokka': 0}
for i, info in enumerate(dogs):
for k in info.keys():
if k in placements.keys():
if k in extraoffset:
extra = extraoffset[k]
else:
extra = 0
x, y = placements[k]
text = info[k]
c.drawString(extra + x*cm, yoffset[i]*cm + y*cm, text)
if i == 5:
c.showPage()
extraoffset['Luokka'] = 0.3*cm
if len(dogs) < 7:
c.showPage()
c.save()
packet.seek(0)
new_pdf = PdfFileReader(packet)
output = PdfFileWriter()
output.addPage(new_pdf.getPage(0))
output.addPage(new_pdf.getPage(1))
outputStream = file("/tmp/stamp.pdf", "wb")
output.write(outputStream)
outputStream.close()
try:
os.mkdir("esitaytetyt")
except:
pass
call(['pdftk', 'pohjat/koepoytakirja.pdf', 'multistamp', '/tmp/stamp.pdf', 'output', 'esitaytetyt/%s' % filename])
def writePDF(linkPaths):
if "<type 'list'>" != str(type(linkPaths)):
print "Invalid parameter passed.\n"
return
l = len(linkPaths)
output = PdfFileWriter()
for i in range(0,l):
input1 = PdfFileReader(file("./Tmp/" + str(i+1) + ".pdf", "rb"))
output.addPage(input1.getPage(0))
print("Generating newspaper...\n")
dateObject = datetime.now()
fileName = dateObject.strftime("%Y%m%d")
fileName = "GDN " + fileName + ".pdf"
outputStream = file(fileName, "wb")
output.write(outputStream)
outputStream.close()
return
def merge_pdf(lpdf):
"""
Merge all PDF in the list and return the content as a File Object
:param lpdf: List of PDF as File Object
:type lpdf: list
:return: return a file object
:rtype: File Object
"""
fo_pdf = StringIO()
ret = PdfFileWriter()
for current_pdf in lpdf:
if current_pdf is None:
continue
# We ensure we start at the begining of the file
current_pdf.seek(0)
tmp_pdf = PdfFileReader(current_pdf)
for page in range(tmp_pdf.getNumPages()):
ret.addPage(tmp_pdf.getPage(page))
# We store the content of the merge into a file object
ret.write(fo_pdf)
return fo_pdf
def cropNzoom(inputFile, pageNumber, zoomFactor):
print "Cropping and scaling pdf"
pageNumber = pageNumber - 1
outputFile = inputFile[:inputFile.rindex('.')] + '_' + str(pageNumber +
1) + 'test.pdf'
output = PdfFileWriter()
input1 = PdfFileReader(file(inputFile, "rb"))
page = input1.getPage(pageNumber)
page.scaleBy(zoomFactor)
output.addPage(page)
print "Saving cropped pdf as: " + outputFile[outputFile.rindex('\\') + 1:]
outputStream = file(outputFile, "wb")
output.write(outputStream)
outputStream.close()
return outputFile
def main(output_file, input_files):
print "concat all files:"
output = PdfFileWriter()
total_pages = 0
for f in input_files:
# expect filename as "*.pdf"
if f[-4:] != ".pdf":
print "skipped file: ", f
continue
else:
input = PdfFileReader(file(f, 'rb'))
num_pages = input.getNumPages()
total_pages += num_pages
print f, "->", str(num_pages) + "pages"
for i in xrange(0, num_pages):
output.addPage(input.getPage(i))
outputStream = file(output_file, 'wb')
output.write(outputStream)
print str(total_pages) + "pages written"
outputStream.close()
def create(self, cr, uid, ids, datas, context=None):
self.pool = pooler.get_pool(cr.dbname)
checkoutType = self.pool.get('plm.checkout')
output = PdfFileWriter()
children = []
packed = []
checkouts = checkoutType.browse(cr, uid, ids)
for checkout in checkouts:
document = checkout.documentid
if document.printout:
if not document.id in packed:
input1 = PdfFileReader(
StringIO.StringIO(
base64.decodestring(document.printout)))
output.addPage(input1.getPage(0))
packed.append(document.id)
pdf_string = StringIO.StringIO()
output.write(pdf_string)
self.obj = external_pdf(pdf_string.getvalue())
self.obj.render()
pdf_string.close()
return (self.obj.pdf, 'pdf')
def crop_image(box, pdf_page, filename, count):
print "BOX"
print box
with open(filename + "_data/" + pdf_page, "rb") as in_f:
input1 = PdfFileReader(in_f)
output = PdfFileWriter()
page = input1.getPage(0)
x0 = float(box[0])
y0 = pdf_metadata.page_height - float(box[1])
x1 = float(box[2])
y1 = pdf_metadata.page_height - float(box[3])
page.trimBox.lowerLeft = (x0, y1)
page.trimBox.upperRight = (x1, y0)
page.cropBox.lowerLeft = (x0, y1)
page.cropBox.upperRight = (x1, y0)
output.addPage(page)
with open("OCR_DATASET/" + filename + "_me_" + str(count),
"wb") as out_f:
output.write(out_f)
def get_pdf_pagesize(fn, page=0):
f = open(fn, "rb")
pdf = PdfFileReader(f)
p = pdf.getPage(page)
f.close()
x0 = x1 = y0 = y1 = 0.0
for k in [
'/TrimBox',
'/CropBox',
'/MediaBox',
'/ArtBox',
]:
try:
_dim = p[k]
except:
continue
_x0, _y0, _x1, _y1 = map(float, _dim)
y0 = min(y0, _y0)
y1 = max(y1, _y1)
x0 = min(x0, _x0)
x1 = max(x1, _x1)
width = x1 - x0
height = y1 - y0
return (width, height)
def MergePDF(filepath,outfile):
output=PdfFileWriter()
outputPages=0
pdf_fileName=getFileName(filepath)
print '总的',pdf_fileName
for each in pdf_fileName:
if '.DS_Store' in each:
continue
# print '看看',os.path.dirname(each),'+', os.path.splitext(each.replace(os.path.dirname(each),''))
#
print '单的',each
# 读取源pdf文件
input = PdfFileReader(file(each, "rb"))
# print 'input：',input
# 如果pdf文件已经加密，必须首先解密才能使用pyPdf
if input.isEncrypted == True:
print 'input.isEncrypted',input.isEncrypted
input.decrypt("map")
# 获得源pdf文件中页面总数
pageCount = input.getNumPages()
outputPages += pageCount
print pageCount
# 分别将page添加到输出output中
for iPage in range(0, pageCount):
output.addPage(input.getPage(iPage))
print "All Pages Number:"+str(outputPages)
# 最后写pdf文件
outputStream=file(filepath+outfile,"wb")
output.write(outputStream)
outputStream.close()
print "finished"