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 crop(filein): output = PdfFileWriter() input1 = PdfFileReader(file(filein, "rb")) input2 = PdfFileReader(file(filein, "rb")) # print the title of the document print "title = %s" % (input1.getDocumentInfo().title) n = input1.getNumPages() # loop over pages for i in range(n): # p = input1.getPage(i) # print p.cropBox # p.mediaBox.upperRight = ( # p.mediaBox.getUpperRight_x() / 2, # p.mediaBox.getUpperRight_y() / 2 # ) w, h = 359, 269 slide1 = input1.getPage(i) rect = lambda x, y: generic.RectangleObject([x, y, x+w, y+h]) slide1.mediaBox = rect(117, 462) output.addPage(slide1) slide2 = input2.getPage(i) slide2.mediaBox = rect(117, 111) output.addPage(slide2) # write output fileout = "%s-cropped%s" % os.path.splitext(filein) outputStream = file(fileout, "wb") output.write(outputStream) outputStream.close() # print some information n2 = output.getNumPages() print "%s has %s pages." % (filein, n) print "%s has %s pages." % (fileout, n2)
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 compact(filein):
output = PdfFileWriter()
input1 = PdfFileReader(file(filein, "rb"))
# print the title of the document
print "title = %s" % (input1.getDocumentInfo().title)
n = input1.getNumPages()
# loop over pages
for i in range(1, n):
curr = input1.getPage(i)
prev = input1.getPage(i - 1)
currTxt = curr.extractText()[:-3]
prevTxt = prev.extractText()[:-3]
if currTxt.find(prevTxt) == 0: # prevTxt is prefix of currTxt
pass # the current page is an extension to the previous one -> continue
else:
output.addPage(
prev) # current page is something new -> save latest old one
output.addPage(input1.getPage(n - 1)) # add last page
# write output
fileout = "%s-compact%s" % os.path.splitext(filein)
outputStream = file(fileout, "wb")
output.write(outputStream)
outputStream.close()
# print some information
n2 = output.getNumPages()
print "%s has %s pages." % (filein, n)
print "%s has %s pages." % (fileout, n2)
print "-> removed %s pages\n" % (n - n2)
def consume_files(filelist):
i = 0
while (len(filelist) > 0):
output = PdfFileWriter()
merge_pages_better(output, filelist)
outputstream = file(PREFIX_STR+str(i)+'.pdf', 'wb')
print "%s%d.pdf has %d pages" % (PREFIX_STR, i, output.getNumPages())
i = i + 1
output.write(outputstream)
outputstream.close()
return 1
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 splitPDF(inputpdf, output_fn, start, end):
""" from the input pdf creates a new pdf file with the name output_fn
containing only the pages of the pdf from start to end
"""
outputpdf = PdfFileWriter()
print 'added pages ',
for i in xrange(start, end):
outputpdf.addPage(inputpdf.getPage(i))
print str(i) + ',',
print 'finished. printed', outputpdf.getNumPages(), 'pages'
outstream = file(output_fn, 'wb')
outputpdf.write(outstream)
outstream.close()
def merge_pdfs(output_name, files):
""" Merges files in the order given. Make sure to sort first."""
output = PdfFileWriter()
for f in files:
try:
i = PdfFileReader(file(f, "rb"))
except IOError as e:
print(e)
except PdfReadError as e:
print(e)
else:
for p in i.pages:
output.addPage(p)
if output.getNumPages():
ostream = file(output_name, "wb")
output.write(ostream)
ostream.close()
def test_page_ranges(self):
rv = self.app.get('/')
self.assertEquals(rv.status_code, 200)
pdf = PdfFileReader(self.get_pdf_stream())
# Build a document with twenty pages
output = PdfFileWriter()
page = pdf.getPage(0)
for i in range(1, 21):
new_page = CombineTestCase.replace_text(page, 'Test',
'Test %d' % i)
output.addPage(new_page)
assert output.getNumPages() == 20
buf = StringIO()
output.write(buf)
buf.seek(0)
rv = self.app.post('/handleform',
data={'file': (buf, 'test.pdf')},
follow_redirects=True)
ids = self.extract_ids_from_main_page(rv.data)
pages_kw = 'pages_%d' % ids[0]
rv = self.combine_and_download(**{pages_kw: '-5, 10, 12-14, 18-'})
pdf_download = PdfFileReader(StringIO(rv.data))
# Test ranges
ranges = [1, 2, 3, 4, 5, 10, 12, 13, 14, 18, 19, 20]
self.assert_(
all((('Test %d' % page) in pdf_download.getPage(i).extractText())
for i, page in enumerate(ranges)))
self.assertEquals(pdf_download.getNumPages(), len(ranges))
self.clean_up()
def test_page_ranges(self):
rv = self.app.get('/')
self.assertEquals(rv.status_code, 200)
pdf = PdfFileReader(self.get_pdf_stream())
# Build a document with twenty pages
output = PdfFileWriter()
page = pdf.getPage(0)
for i in range(1, 21):
new_page = CombineTestCase.replace_text(page, 'Test', 'Test %d' % i)
output.addPage(new_page)
assert output.getNumPages() == 20
buf = StringIO()
output.write(buf)
buf.seek(0)
rv = self.app.post('/handleform',
data={'file': (buf, 'test.pdf')},
follow_redirects=True)
ids = self.extract_ids_from_main_page(rv.data)
pages_kw = 'pages_%d' % ids[0]
rv = self.combine_and_download(**{pages_kw: '-5, 10, 12-14, 18-'})
pdf_download = PdfFileReader(StringIO(rv.data))
# Test ranges
ranges = [1, 2, 3, 4, 5, 10, 12, 13, 14, 18, 19, 20]
self.assert_(all(
(('Test %d' % page) in pdf_download.getPage(i).extractText())
for i, page in enumerate(ranges)))
self.assertEquals(pdf_download.getNumPages(), len(ranges))
self.clean_up()
batchnames.append("batch"+str(i)+".pdf")
# Loop through HouseDistricts
for i in range(1,100):
output = PdfFileWriter()
outputfilename = "pdfs/HD"+str(i)+".pdf"
for b in batchnames:
input_pdf = PdfFileReader(file("pdfs/"+b, "rb"))
with open('csvs/district_data.csv', 'rb') as csvfile:
district_reader = csv.reader(csvfile, delimiter=',', quotechar='"')
for row in district_reader:
if row[0] == b:
if row[9]== str(i):
output.addPage(input_pdf.getPage(int(row[1])-1))
if output.getNumPages() >0:
outputStream = file(outputfilename, "wb")
output.write(outputStream)
outputStream.close()
print "There are %s form letters from %s " % (output.getNumPages(), outputfilename)
# Loop through SenateDistricts
for i in range(1,34):
output = PdfFileWriter()
outputfilename = "pdfs/SD"+str(i)+".pdf"
for b in batchnames:
input_pdf = PdfFileReader(file("pdfs/"+b, "rb"))
with open('csvs/district_data.csv', 'rb') as csvfile:
district_reader = csv.reader(csvfile, delimiter=',', quotechar='"')
for row in district_reader:
# This is the pyPdf library. Install with: $ pip install pyPdf
from pyPdf import PdfFileWriter, PdfFileReader
# Open a writer object
output = PdfFileWriter()
# Load the pdf file(s) you want to input pages from
input1 = PdfFileReader(file("test.pdf", "rb"))
# Add some pages from your source/input files to the writer object
output.addPage(input1.getPage(8))
output.addPage(input1.getPage(15))
# For kicks, print the number of pages added to the console
print "number of pages is: %s " % output.getNumPages()
# Explain the kind of file this will be when outputted
outputStream = file("assembled_pdf.pdf", "wb")
# Write the actual output file
output.write(outputStream)
# Close the output file
outputStream.close()
for x in range(len(INPUT)) :
hackfile = 'editionHack/hack{0}.pdf'.format(x+OFFSET)
goodfile = 'editionHack/'+INPUT[x]+".pdf"
output = PdfFileWriter()
input1 = PdfFileReader(file(goodfile, "rb"))
page1 = input1.getPage(0)
watermark = PdfFileReader(file(hackfile, "rb"))
page1.mergePage(watermark.getPage(0))
output.addPage(page1)
outputStream = file("editionHack/finalPage{0}.pdf".format(x+OFFSET), "wb")
print "finalPage{0}.pdf".format(x+OFFSET)
output.write(outputStream)
outputStream.close()
output = PdfFileWriter()
for x in range(3,11) :
input1 = PdfFileReader(file('editionHack/finalPage{0}.pdf'.format(x), "rb"))
output.addPage(input1.getPage(0))
input1 = PdfFileReader(file('sitOzfarsWysr_a4.pdf', "rb"))
for x in range(input1.getNumPages()) :
output.addPage(input1.getPage(x))
if output.getNumPages() % 2 == 1 :
input1 = PdfFileReader(file('editionHack/blankPage.pdf', "rb"))
output.addPage(input1.getPage(0))
outputStream = file("editionHack/sowInterior.pdf".format(x), "wb")
output.write(outputStream)
outputStream.close()
})
# Add It
output._addObject(properties)
# Add back the one we deleted first
output._addObject(item)
address = PdfFileReader(file("input\\address\\"+fname, "rb"))
location = PdfFileReader(file("input\\location\\"+fname, "rb"))
print "Location Pages:", location.numPages
print "Address Pages:", address.numPages
if location.numPages > 1 :
print "Location has more than 1 page, exiting..."
sys.exit()
page = location.getPage(0)
for i in xrange(address.numPages):
#print ".",
output.addPage(address.getPage(i))
output.addPage(page)
# output should be double address
print "Output Pages:", output.getNumPages()
#if output.getNumPages() == (address.numPages *2):
if output.getNumPages() > 0:
outStream = file("output\\"+fname, "wb")
output.write(outStream)
outStream.close()
print "Generation Complete"
for fn in fnames:
for k in range(len(fn)):
if len(out_name) - 1 < k:
out_name.append([])
if out_name[k].count(fn[k]) < 1:
out_name[k].append(fn[k])
#out_name[k].sort()
#out_name[k].reverse();
for k in range(len(out_name)):
if k == 0:
out_name[k] = [datetime.date.today().strftime('%y%m%d')]
out_name[k] = '_'.join(out_name[k])
# собираем из отфильтрованных частей конечное имя файла
postfix = '_crop'
if backpage:
postfix = '_backpage'
out_name = ('_'.join(out_name) + postfix)[0:251] + '.pdf'
print('')
print(out_name)
print("has %s pages" % output.getNumPages())
print('Saving...')
outputStream = file(out_name, "wb")
output.write(outputStream)
outputStream.close()
print('Done')
def _dpd_label_get(self, cr, uid, picking, test=False, context=None):
carrier = picking.carrier_id
if not carrier or carrier.api != "dpd":
raise Warning(_("Invalid carrier type!"))
profile = carrier.dpd_profile_id
if not profile:
raise Warning(_("No DPD Profile defined!"))
# check test profile
if test:
profile = carrier.dpd_test_profile_id
if not profile:
return True
# check packages
pack_op_obj = self.pool["stock.pack.operation"]
package_count = 0
package_count_all = True
# check operation for package count
for operation in picking.pack_operation_ids:
if operation.qty_done:
# check if all operation have a package count
# if not add one package for itself
if not operation.package_count:
if package_count_all:
package_count_all = False
package_count += 1
else:
# add packages
package_count += operation.package_count
if not package_count:
package_count = 1
partner = picking.partner_id
client = self._dpd_client_get(context)
tracking_refs = []
carrier_errors = []
label_pdf = PdfFileWriter()
carrier_label_name = None
try:
for packageNo in range(0, package_count):
parts = {}
parts["username"] = profile.user
parts["password"] = md5(profile.password).hexdigest()
parts["mandant"] = profile.client
parts["kdnr"] = partner.ref or ""
name = partner.name.strip()
bezugsp = partner.street2 and partner.street2.strip() or ""
parent_partner = partner.parent_id
if not partner.mail_without_company and parent_partner:
name = parent_partner.name
bezugsp = partner.name.strip()
zusatz = ""
if len(name) > 48:
shortName = name[:48]
lastSpacePos = shortName.rfind(" ")
if lastSpacePos > 30:
lastSpacePos += 1
zusatz = name[lastSpacePos:lastSpacePos + 32]
name = shortName[:lastSpacePos]
else:
zusatz = name[48:80]
name = shortName
parts["name"] = name
parts["zusatz"] = zusatz
parts["anschrift"] = partner.street and partner.street.strip(
) or ""
parts["plz"] = partner.zip and partner.zip.strip() or ""
parts["ort"] = partner.city and partner.city.strip() or ""
parts[
"land"] = partner.country_id and partner.country_id.code or "AT"
parts["bezugsp"] = bezugsp
parts["tel"] = partner.phone or partner.mobile or ""
parts["mail"] = partner.email or ""
parts["liefernr"] = picking.name or ""
parts["pakettyp"] = carrier.dpd_type or "DPD"
parts["gewicht"] = "1000"
weight = picking.carrier_weight or picking.weight or 0.0
if weight:
uom_obj = self.pool["product.uom"]
uom_id = uom_obj.search_id(
cr, uid, [("category_id", "=",
picking.weight_uom_id.category_id.id), '|',
("name", "=", "g"), ("code", "=", "g")])
uom = uom_obj.browse(cr, uid, uom_id, context=context)
if not uom:
raise Warning(_("No unit gramm found!"))
parts["gewicht"] = str(
int(
uom_obj._compute_qty(cr, uid,
picking.weight_uom_id.id,
weight, uom.id)))
parts["vdat"] = ""
produkt1 = carrier.dpd_product1
if not produkt1:
produkt1 = "KP"
if weight > 3:
produkt1 = "NP"
parts["produkt1"] = produkt1
parts["produkt2"] = []
parts["produkt3"] = []
parts["produkt4"] = []
parts["produkt5"] = ""
parts["produkt6"] = []
parts["produkt7"] = ""
msgSoapOut = client.service.getLabel(**parts)
picking_obj = self.pool["stock.picking"]
# save pdf
label_url = msgSoapOut.label
if label_url:
carrier_label_name = label_url.split("/")[-1]
label_file = urllib2.urlopen(label_url)
try:
# add page
label_pdf.addPage(
PdfFileReader(StringIO(
label_file.read())).getPage(0))
finally:
label_file.close()
# evaluate error
err_code = msgSoapOut.err_code
if err_code:
carrier_error = err_code
foundError = False
for err, err_message in self._dpd_errors:
if err in err_code:
carrier_error = err_message
foundError = True
if not foundError:
h = HTMLParser()
carrier_error = h.unescape(carrier_error)
_logger.error(carrier_error)
carrier_errors.append(carrier_error)
else:
# store ref
tracking_refs.append(msgSoapOut.paknr)
# build label
carrier_label = None
if label_pdf.getNumPages() > 0:
bufPdf = StringIO()
try:
label_pdf.write(bufPdf)
carrier_label = base64.encodestring(bufPdf.getvalue())
finally:
bufPdf.close()
status = None
carrier_tracking_ref = None
if not carrier_errors and not test:
status = "created"
if not test:
carrier_tracking_ref = ", ".join(tracking_refs)
# write data
picking_obj.write(cr,
uid,
picking.id, {
"carrier_label_name": carrier_label_name,
"carrier_label": carrier_label,
"carrier_error": "\n".join(carrier_errors),
"carrier_tracking_ref": carrier_tracking_ref,
"carrier_status": status,
"number_of_packages": package_count
},
context=context)
except Exception, e:
self._dpd_error(e)
raise e
# This is the pyPdf library. Install with: $ pip install pyPdf
from pyPdf import PdfFileWriter, PdfFileReader
# Open a writer object
output = PdfFileWriter()
# Load the pdf file(s) you want to input pages from
input1 = PdfFileReader(file("test.pdf", "rb"))
# Add some pages from your source/input files to the writer object
output.addPage(input1.getPage(8))
output.addPage(input1.getPage(15))
# For kicks, print the number of pages added to the console
print "number of pages is: %s " % output.getNumPages()
# Explain the kind of file this will be when outputted
outputStream = file("assembled_pdf.pdf", "wb")
# Write the actual output file
output.write(outputStream)
# Close the output file
outputStream.close()
from pyPdf import PdfFileWriter, PdfFileReader
import glob
output = PdfFileWriter()
files = glob.glob(r'./*.pdf')
for stuff in list(sorted(files)):
input = PdfFileReader(file(str(stuff), "rb"))
print "processing %s " % (stuff)
output.addPage(input.getPage(0))
print "output has %s pages." % output.getNumPages()
outputStream = file("out.pdf", 'wb')
output.write(outputStream)
outputStream.close()
page2 = output_pdf.addBlankPage(x/2, y)
page2.mergeTranslatedPage(p, -x/2, 0)
split_count = split_count + 1
else:
# Portrait, fine on its own
output_pdf.addPage(p)
progress.animate(amount=i)
progress.animate(amount=pages)
print 'Total pages: %d -> %d ' % (
pages,
output_pdf.getNumPages()
)
if split_count:
print '/-{ %d }-\\ double spreads split apart' % split_count
print 'Writing... here is a bird to keep you company'
def write_file():
# Write the file
output_file = file(input_base + '.split' + input_ext, "wb")
output_pdf.write(output_file)
output_file.close()
t = threading.Thread(target=write_file)
t.start()
