def get(self):
url = self.request.get('url')
if not url:
url = ""
page = self.request.get('pg')
if not page:
page = 'all'
else:
page = int(page)-1
u = urllib2.urlopen(urllib2.unquote(url))
output = StringIO.StringIO()
output.write(u.read())
p = PdfFileReader(output)
pages = p.getNumPages()
title = p.getDocumentInfo().title
if page == "all":
content=""
for i in range(0, pages):
# Extract text from page and add to content
content += "<page number='%d'><![CDATA[%s]]></page>\n" % (i+1, p.getPage(i).extractText())
else:
content = "<page number='%d'><![CDATA[%s]]></page>\n" % (page+1, p.getPage(page).extractText())
output.close()
result = "<?xml version='1.0' encoding='UTF-8'?>\n<document url='%s' title='%s'>%s</document>" % (url, title, content)
self.response.headers['Content-type'] = 'application/xml'
self.response.out.write(result)
def get_pdf(self, text, use_design=False):
"""
Given the text, produces an A4 blank PDF with the text put in the
position given by the tranlsation box.
:param text: Text to put inside a translation box
:param use_design: Set to true to use a design in the background
:return: Rendered PDF
:rtype: pypdf.PdfFileReader if use_design is False or PdfFileWriter
"""
self.ensure_one()
packet = StringIO.StringIO()
can = Canvas(packet, bottomup=0)
text_wrap = self._wrap_text(text, can._fontname, can._fontsize)
top = self.top * inch
left = self.left * inch
for line in text_wrap[:self.nb_lines + 1]:
can.drawString(left, top, line)
top += can._leading
can.save()
# Move to the beginning of the StringIO buffer
packet.seek(0)
remaining = ''
if len(text_wrap) > self.nb_lines:
remaining = ' '.join(text_wrap[self.nb_lines + 1:])
out_pdf = PdfFileReader(packet)
if use_design:
design_pdf_path = self.env['ir.config_parameter'].get_param(
'sbc_compassion.composition_design')
if design_pdf_path:
design_pdf = PdfFileReader(file(design_pdf_path, 'rb'))
page = design_pdf.getPage(0)
page.mergePage(out_pdf.getPage(0))
out_pdf = PdfFileWriter()
out_pdf.addPage(page)
return out_pdf, remaining
def create(self, vals):
""" Create a message for sending the CommKit after be translated on
the local translate plaform.
"""
if vals.get('direction') == "Beneficiary To Supporter":
correspondence = super(Correspondence, self).create(vals)
else:
sponsorship = self.env['recurring.contract'].browse(
vals['sponsorship_id'])
original_lang = self.env['res.lang.compassion'].browse(
vals.get('original_language_id'))
# TODO Remove this fix when HAITI case is resolved
# For now, we switch French to Creole for avoiding translation
if 'HA' in sponsorship.child_id.local_id:
french = self.env.ref(
'child_compassion.lang_compassion_french')
creole = self.env.ref(
'child_compassion.lang_compassion_haitien_creole')
if original_lang == french:
vals['original_language_id'] = creole.id
if original_lang.translatable and original_lang not in sponsorship\
.child_id.project_id.field_office_id.spoken_language_ids:
correspondence = super(Correspondence, self.with_context(
no_comm_kit=True)).create(vals)
correspondence.send_local_translate()
else:
correspondence = super(Correspondence, self).create(vals)
# Swap pages for L3 layouts as we scan in wrong order
if correspondence.template_id.layout == 'CH-A-3S01-1' and \
correspondence.source != 'compassion':
input_pdf = PdfFileReader(BytesIO(base64.b64decode(
correspondence.letter_image)))
output_pdf = PdfFileWriter()
nb_pages = input_pdf.numPages
if nb_pages >= 2:
output_pdf.addPage(input_pdf.getPage(1))
output_pdf.addPage(input_pdf.getPage(0))
if nb_pages > 2:
for i in range(2, nb_pages):
output_pdf.addPage(input_pdf.getPage(i))
letter_data = BytesIO()
output_pdf.write(letter_data)
letter_data.seek(0)
correspondence.write({
'letter_image': base64.b64encode(letter_data.read())
})
return correspondence
def create(self, vals):
""" Create a message for sending the CommKit after be translated on
the local translate plaform.
"""
if vals.get('direction') == "Beneficiary To Supporter":
correspondence = super(Correspondence, self).create(vals)
else:
sponsorship = self.env['recurring.contract'].browse(
vals['sponsorship_id'])
original_lang = self.env['res.lang.compassion'].browse(
vals.get('original_language_id'))
# TODO Remove this fix when HAITI case is resolved
# For now, we switch French to Creole for avoiding translation
if 'HA' in sponsorship.child_id.local_id:
french = self.env.ref(
'child_compassion.lang_compassion_french')
creole = self.env.ref(
'child_compassion.lang_compassion_haitien_creole')
if original_lang == french:
vals['original_language_id'] = creole.id
if original_lang.translatable and original_lang not in sponsorship\
.child_id.project_id.field_office_id.spoken_language_ids:
correspondence = super(
Correspondence,
self.with_context(no_comm_kit=True)).create(vals)
correspondence.send_local_translate()
else:
correspondence = super(Correspondence, self).create(vals)
# Swap pages for L3 layouts as we scan in wrong order
if correspondence.template_id.layout == 'CH-A-3S01-1' and \
correspondence.source != 'compassion':
input_pdf = PdfFileReader(
BytesIO(base64.b64decode(correspondence.letter_image)))
output_pdf = PdfFileWriter()
nb_pages = input_pdf.numPages
if nb_pages >= 2:
output_pdf.addPage(input_pdf.getPage(1))
output_pdf.addPage(input_pdf.getPage(0))
if nb_pages > 2:
for i in range(2, nb_pages):
output_pdf.addPage(input_pdf.getPage(i))
letter_data = BytesIO()
output_pdf.write(letter_data)
letter_data.seek(0)
correspondence.write(
{'letter_image': base64.b64encode(letter_data.read())})
return correspondence
def parse(self, file_full, statdata): pdf = PdfFileReader(file(file_full, 'rb')) pages = pdf.getNumPages() text = '' self._extra['pages'] = pages for pagenr in range(pages): page = pdf.getPage(pagenr-1) text += ' ' + page.extractText() return text
def get_pdf(self, text, use_design=False):
"""
Given the text, produces an A4 blank PDF with the text put in the
position given by the tranlsation box.
:param text: Text to put inside a translation box
:param use_design: Set to true to use a design in the background
:return: Rendered PDF
:rtype: pypdf.PdfFileReader if use_design is False or PdfFileWriter
"""
self.ensure_one()
packet = StringIO.StringIO()
can = Canvas(packet, bottomup=0)
text_wrap = self._wrap_text(text, can._fontname, can._fontsize)
top = self.top*inch
left = self.left*inch
for line in text_wrap[:self.nb_lines+1]:
can.drawString(left, top, line)
top += can._leading
can.save()
# Move to the beginning of the StringIO buffer
packet.seek(0)
remaining = ''
if len(text_wrap) > self.nb_lines:
remaining = ' '.join(text_wrap[self.nb_lines+1:])
out_pdf = PdfFileReader(packet)
if use_design:
design_pdf_path = self.env['ir.config_parameter'].get_param(
'sbc_compassion.composition_design')
if design_pdf_path:
design_pdf = PdfFileReader(file(design_pdf_path, 'rb'))
page = design_pdf.getPage(0)
page.mergePage(out_pdf.getPage(0))
out_pdf = PdfFileWriter()
out_pdf.addPage(page)
return out_pdf, remaining
def preview(self):
""" Generate a picture for preview.
"""
pdf = self._get_pdf(self.sponsorship_ids[0], preview=True)
if self.s2b_template_id.layout == 'CH-A-3S01-1':
# Read page 2
in_pdf = PdfFileReader(BytesIO(pdf))
output_pdf = PdfFileWriter()
out_data = BytesIO()
output_pdf.addPage(in_pdf.getPage(1))
output_pdf.write(out_data)
out_data.seek(0)
pdf = out_data.read()
with Image(blob=pdf) as pdf_image:
preview = base64.b64encode(pdf_image.make_blob(format='jpeg'))
return self.write({'state': 'preview', 'preview_image': preview})
def preview(self):
""" Generate a picture for preview.
"""
pdf = self._get_pdf(self.sponsorship_ids[0], preview=True)
if self.s2b_template_id.layout == 'CH-A-3S01-1':
# Read page 2
in_pdf = PdfFileReader(BytesIO(pdf))
output_pdf = PdfFileWriter()
out_data = BytesIO()
output_pdf.addPage(in_pdf.getPage(1))
output_pdf.write(out_data)
out_data.seek(0)
pdf = out_data.read()
with Image(blob=pdf) as pdf_image:
preview = base64.b64encode(pdf_image.make_blob(format='jpeg'))
return self.write({'state': 'preview', 'preview_image': preview})
def add_annotation_to_page(pdf_page, annotation, fontsize=24, margin=20): # Adds an annotation at bottom-left of the page width = pdf_page.mediaBox.getWidth() height = pdf_page.mediaBox.getHeight() # Create background with annotation a lower-left io = StringIO.StringIO() can = canvas.Canvas(io) can.setPageSize([width, height + fontsize + margin]) can.setFontSize(fontsize) can.drawString(margin, margin, annotation) can.save() io.seek(0) #move to the beginning of the StringIO buffer page_background = PdfFileReader(io).getPage(0) page_background.mergeTranslatedPage(pdf_page, ty=margin+fontsize, tx=0) return page_background
def pair_pages(self):
"""
construct an empty pdf file object and append as many blank pages to
the end to pair the pages.
"""
paired_pages = PdfFileWriter()
for page in PdfFileReader(file(self.job.pdf_file, "rb")).pages:
paired_pages.addPage(page)
# while paired_pages.getNumPages() % 4 != 0:
# paired_pages.addBlankPage()
return paired_pages
def mergePdf(self):
# self.threadPdfWritingStatus.emit(
# '<font size=4><b>Method "%s": </b></font><b>Setting Title for</b> %s<b>. Please Wait...</b><br />' % (
# self.groupType, self.url))
self.threadPdfWritingStatus.emit(
'<b>Setting Title for</b> %s<b>. Please Wait...</b><br />' % self.url)
packet = StringIO()
# create a new PDF with Reportlab
pdfCanvas = canvas.Canvas(packet, pagesize=A4)
pdfCanvas.setFont('Helvetica', 8)
if len(self.title) is 0:
self.title = str(self.url).split('/')[-1]
self.title = self.regex.getSearchedData('(?i)([a-zA-Z0-9-_ ]*?)\.[a-zA-Z0-9_]*$', self.title)
self.title = self.regex.replaceData('(?i)_', ' ', self.title)
title = unicode(self.title[:57] + '...') if (len(self.title) > 60) else unicode(self.title)
url = self.url[:57] + '...' if (len(self.title) > 60) else self.url
pdfCanvas.drawString(5, 830, title + ' ' + str(url).lower())
d = datetime.datetime.now()
strDate = str(d.strftime("%Y-%m-%d %H-%M-%S %p"))
pdfCanvas.drawString(420, 5, 'Created Date Time: ' + strDate)
pdfCanvas.save()
packet.seek(0)
newPdf = PdfFileReader(packet)
if not os.path.exists(self.tempPdfFile):
return self.printWebHtmlToPdf(self.url, self.filePath, self.fileName)
writer = PdfFileWriter()
tmpPdfFile = file(self.tempPdfFile, 'rb')
reader = PdfFileReader(tmpPdfFile)
for i in range(0, (reader.getNumPages())):
page = reader.getPage(i)
page.mergePage(newPdf.getPage(0))
# page = newPdf.getPage(0)
# page.mergePage(reader.getPage(i))
writer.addPage(page)
print 'Filename: ' + self.fileName
outputStream = file(self.filePath + self.fileName, "wb")
writer.write(outputStream)
outputStream.close()
tmpPdfFile.close()
os.remove(str(self.tempPdfFile))
def printMeta(filename):
f = PdfFileReader(open(filename, "rb"))
info = f.getDocumentInfo()
print("[*] PDF Metadata for:" + filename)
for item in info:
print("[+]", item, ":", info[item])
from pyPdf.pdf import PdfFileWriter, PdfFileReader
from
if __name__ == '__main__':
output = PdfFileWriter()
input1 = PdfFileReader('D:\Anaconda\workspace\\vtk_bucket\\1.pdf')
print('ok')
def readTheFile(fName):
return PdfFileReader(file(fName, "rb"))
def extract_text_from_pdf_stream(stream):
reader = PdfFileReader(stream)
return '\n'.join(
reader.getPage(i).extractText()
for i in range(reader.getNumPages())
)
for col in range(ncols):
for row in range(nrows - 1, -1, -1):
newpage = copy_page(page)
bbox = (col * xspace + x0, row * yspace + y0,
col * xspace + x0 + width, row * yspace + y0 + height)
newpage.cropBox = newpage.artBox = newpage.trimBox = newpage.mediaBox = RectangleObject(
bbox)
outpdf.addPage(newpage)
bboxes.append(bbox)
return bboxes
if __name__ == '__main__':
import sys
try:
inpdf = PdfFileReader(open(sys.argv[1], 'rb'))
ncols = int(sys.argv[2])
nrows = int(sys.argv[3])
except (IndexError, IOError):
print "Usage: %s file.pdf ncols nrows [overlap [crop]]" % sys.argv[0]
raise SystemExit
overlap = map(float, sys.argv[4:6])
if not overlap:
overlap = 0.05
crop = map(float, sys.argv[6:10])
if not crop:
crop = 0
outpdf, _ = dice(inpdf, ncols, nrows, crop, overlap)
write_pdf(outpdf, 'pdfdice.pdf')
def extractTextFromPdfStream(stream):
reader = PdfFileReader(stream)
return '\n'.join(
reader.getPage(i).extractText() for i in range(reader.getNumPages()))
