def pdf_merge(pdf1, pdf2):
try:
tmp1 = os.tempnam()
tmp2 = os.tempnam()
tmp3 = os.tempnam()
output = pyPdf.PdfFileWriter()
file(tmp1, "w").write(pdf1)
file(tmp2, "w").write(pdf2)
input1 = pyPdf.PdfFileReader(file(tmp1, "rb"))
input2 = pyPdf.PdfFileReader(file(tmp2, "rb"))
for page in range(input1.getNumPages()):
output.addPage(input1.getPage(page))
for page in range(input2.getNumPages()):
output.addPage(input2.getPage(page))
outputStream = file(tmp3, "wb")
output.write(outputStream)
outputStream.close()
#cmd="/usr/bin/pdftk %s %s cat output %s"%(tmp1,tmp2,tmp3)
#os.system(cmd)
pdf3 = file(tmp3).read()
os.unlink(tmp1)
os.unlink(tmp2)
os.unlink(tmp3)
return pdf3
except:
raise Exception("Failed to merge PDF files")
def test_sealed_document(self):
with self.new_document_from_file() as d:
file_contents = d.original_file.get_bytes()
with contextlib.closing(cStringIO.StringIO(file_contents)) as s:
self.assertEqual(1, pyPdf.PdfFileReader(s).getNumPages())
self.assertIsNone(d.sealed_document)
d = self.api.ready(d)
self.assertIsNone(d.sealed_document)
author = d.author
d = self.api._sign(d, author)
self.assertIsNone(d.sealed_document)
# wait for sealing to be completed, and refresh
time.sleep(10)
d = self.api.get_document(d.id)
self.assertIsNotNone(d.sealed_document)
file_contents = d.sealed_document.get_bytes()
with contextlib.closing(cStringIO.StringIO(file_contents)) as s:
self.assertEqual(2, pyPdf.PdfFileReader(s).getNumPages())
d._set_read_only()
self.assertTrue(d.sealed_document._read_only)
d._set_invalid()
with self.assertRaises(InvalidScriveObject, None):
d.sealed_document.get_bytes()
def generate_tests(settings):
"""create parameterized tests"""
test_cases = unittest.TestSuite()
try:
cases = import_module("inspection." + settings['cases'])
except ImportError:
cases = import_module(settings['cases'])
except ImportError:
raise RuntimeError("module {} not found".format(settings['cases']))
pdf_a_im = pyPdf.PdfFileReader(file(settings['pdf_a'], "rb"))
total_a_pages = pdf_a_im.getNumPages()
pdf_b_im = pyPdf.PdfFileReader(file(settings['pdf_b'], "rb"))
total_b_pages = pdf_b_im.getNumPages()
settings['include'] = list(
set(settings['include']) - set(settings['exclude']))
for case_name in settings['include']:
TestClass = cases.__getattribute__(case_name)
setattr(TestClass, '_settings', settings)
SuperClass = inspect.getmro(TestClass)[1]
method_list = inspect.getmembers(TestClass, predicate=inspect.ismethod)
super_method_list = inspect.getmembers(
SuperClass, predicate=inspect.ismethod)
test_method_list = list(set(method_list) - set(super_method_list))
test_name_list = [method[0] for method in test_method_list if method[
0] != 'tearDownClass' and method[0] != 'setUpClass']
for test_name in test_name_list:
for pi in range(1, total_a_pages + 1):
for pj in range(1, total_b_pages + 1):
test_cases.addTest(TestClass(test_name, pi, pj))
return test_cases
def write(self):
"""Assembles the final PDF and writes to disk."""
pdf_writer = pyPdf.PdfFileWriter()
if self.front_matter is not None:
front_matter = pyPdf.PdfFileReader(file(self.front_matter, "rb"))
for page in range(front_matter.getNumPages()):
pdf_writer.addPage(front_matter.getPage(page))
working_file = tempfile.NamedTemporaryFile(suffix=".pdf", delete=False)
doc = SimpleDocTemplate(working_file)
doc.pagesize = portrait(letter)
story = []
styles = getSampleStyleSheet()
for section in self.sections:
heading_text = section.heading
story.append(Paragraph(heading_text, styles['Heading1']))
for content in section.contents:
if 'figure' in content:
figure = content['figure']
if os.path.exists(figure):
im = utils.ImageReader(figure)
img_width, img_height = im.getSize()
aspect = img_height / float(img_width)
story.append(
Image(figure,
width=img_width,
height=(img_width * aspect)))
if content.get('caption', None) is not None:
caption_text = '<font size=10>{0}</font>'.format(
content['caption'].strip())
story.append(Paragraph(caption_text, styles['Italic']))
story.append(Spacer(1, 10))
if 'table' in content:
_t = self.build_table(content['table'])
story.append(_t)
if content.get('caption', None) is not None:
caption_text = '<font size=10>{0}</font>'.format(
content['caption'].strip())
story.append(Paragraph(caption_text, styles['Italic']))
story.append(Spacer(1, 10))
if 'text' in content:
for para in content['text']:
story.append(Paragraph(para, styles['Normal']))
story.append(Spacer(1, 12))
doc.build(story)
body_matter = pyPdf.PdfFileReader(working_file)
for page in range(body_matter.getNumPages()):
pdf_writer.addPage(body_matter.getPage(page))
try:
os.remove(working_file.name)
except OSError: # Windows reports file in use, other OS errors, etc.
pass
if self.end_matter is not None:
end_matter = pyPdf.PdfFileReader(file(self.end_matter, "rb"))
for page in range(end_matter.getNumPages()):
pdf_writer.addPage(end_matter.getPage(page))
output_stream = file(self.output_filename, "wb")
pdf_writer.write(output_stream)
def process(self, inputFile1):
input1 = pyPdf.PdfFileReader(inputFile1)
output = pyPdf.PdfFileWriter()
for (num, page) in enumerate(input1.pages):
if num in self.operations:
for mergeFile, mergeNumber in self.operations[num]:
merger = pyPdf.PdfFileReader(mergeFile)
mergerPage = merger.getPage(mergeNumber)
mergerPage.mergePage(page)
page = mergerPage
output.addPage(page)
outputFile = cStringIO.StringIO()
output.write(outputFile)
return outputFile
def getPageExtend(self, page=0):
self.pagesize = [
int(round(float(row) * self._papertype_conversion_factor))
for row in pyPdf.PdfFileReader(file(self.fname, 'rb')).getPage(
page).mediaBox[2:4]
]
self.getPageSize()
def getPDFContent(path):
content = ""
pdf = pyPdf.PdfFileReader(file(path, "rb"))
print pdf.getNumPages()
for i in range(0, pdf.getNumPages()):
content += pdf.getPage(i).extractText() + "\n"
return content
def merge_pdf_on_disk(self, docs):
streams = []
writer = pyPdf.PdfFileWriter()
for doc in docs:
current_buff = tempfile.mkstemp(suffix='.pdf',
prefix='credit_control_slip')[0]
current_buff = os.fdopen(current_buff, 'w+b')
current_buff.seek(0)
streams.append(current_buff)
current_buff.write(doc)
current_buff.seek(0)
reader = pyPdf.PdfFileReader(current_buff)
for page in xrange(reader.getNumPages()):
writer.addPage(reader.getPage(page))
buff = tempfile.mkstemp(suffix='.pdf',
prefix='credit_control_slip_merged')[0]
try:
buff = os.fdopen(buff, 'w+b')
# The writer close the reader file here
buff.seek(0)
writer.write(buff)
buff.seek(0)
return buff.read()
except IOError:
raise
finally:
buff.close()
for stream in streams:
stream.close()
def get_no_pages(self, pdf_file, preserve):
import pyPdf
reader = pyPdf.PdfFileReader(open(pdf_file))
if not preserve:
#if you want to remove the file after accessing:
os.remove(pdf_file)
return reader.getNumPages()
def speack_from_pdf(path, language):
pdf = pyPdf.PdfFileReader(open(path, "rb"))
fp = file(path, 'rb')
num_of_pages = pdf.getNumPages()
for i in range(num_of_pages):
inside = [i]
pagenos = set(inside)
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0
caching = True
text = ""
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
text = text.decode("utf-8", "ignore")
print('page ' + str(i))
speack(text, language)
def _merge_PDFs(self, pdfslides):
"""Merge the given PDFs into one."""
output_filename = "%s.pdf" % self._get_filename().split(".svg")[0]
output_filepath = abspath(join(os.curdir, output_filename))
has_pyPdf = False
try:
import pyPdf
has_pyPdf = True
except ImportError:
pass
if has_pyPdf:
logging.info("Using 'pyPdf' to join PDFs to %s", output_filepath)
output = pyPdf.PdfFileWriter()
inputfiles = []
for slide in pdfslides:
inputstream = file(slide, "rb")
inputfiles.append(inputstream)
reader = pyPdf.PdfFileReader(inputstream)
output.addPage(reader.getPage(0))
outputStream = file(output_filepath, "wb")
output.write(outputStream)
outputStream.close()
for f in inputfiles:
f.close()
else:
logging.warning("PyPDF not installed, cannot merge PDF slides")
def _fill_body_place_and_odg(self):
pdf = file(self.pdf.path)
pp = pyPdf.PdfFileReader(pdf)
txt = pp.getPage(0).extractText()
self.body = txt
self.place = self.__get_place(txt)
self.set_odg_list(self.__get_odg(txt))
def page_extractor_pyPdf(file_name):
"""Extracts the text of a pdf with pyPdf"""
import pyPdf
file_reader = pyPdf.PdfFileReader(open(file_name, 'r'))
first_page = file_reader.getPage(0)
return first_page.extractText()
def merge_pdfs(pdf_path_list, to_file):
pdf_out = pyPdf.PdfFileWriter()
total_page_size = 0
f_in_handler_list = []
for path in pdf_path_list:
# 这里不能用 with open(), 因为with语句会自动关闭文件, 导致pdf_out.write(f_out)失败
f = open(path, "rb")
f_in_handler_list.append(f)
pdf_in = pyPdf.PdfFileReader(f)
page_size = pdf_in.getNumPages()
total_page_size += page_size
# 分别将page添加到输出pdf_out中
for i in range(0, page_size):
pdf_out.addPage(pdf_in.getPage(i))
print "Processed file path: %s, page_size: %d" % (path, page_size)
with open(to_file, "wb") as f_out:
pdf_out.write(f_out)
print "Merged file path: %s, page_size: %d" % (to_file,
pdf_out.getNumPages())
# close pdf_in句柄
for f in f_in_handler_list:
f.close()
def cutpdf(name_input, name_output):
pdf_input = file(name_input, "rb")
pdf_output = file(name_output, "wb")
output = pyPdf.PdfFileWriter()
input1 = pyPdf.PdfFileReader(pdf_input)
pg = input1.getNumPages()
for i in range(0, pg):
page1 = input1.getPage(i)
page2 = copy.copy(page1)
cutline = (page1.mediaBox.getUpperRight_x() / 2,
page1.mediaBox.getUpperRight_y())
page1.mediaBox.upperRight = cutline
output.addPage(page1)
page2.mediaBox.upperLeft = cutline
output.addPage(page2)
output.write(pdf_output)
pdf_output.close
return True
def tokenize(path):
# open PDF
pdf = pyPdf.PdfFileReader(open(str(path), "rb"))
stopword_list = list(stopwords.words("english"))
# read PDF file in a list
pdf_content = []
for page in pdf.pages:
pdf_content.append(page.extractText())
# tokenize all the words in the resume
tokenize = []
for line in pdf_content:
tokenize = filter(None, (line.split(" ")))
# remove punctuations and case-fold
no_punctuations = []
for token in tokenize:
no_punctuations.append(token.rstrip(",:|.-").lower())
# remove stop words
without_stop_words = []
for word in filter(None, no_punctuations):
if word not in stopword_list:
without_stop_words.append(word)
return without_stop_words
def get_url_title(url):
"""Try to load url and return a tuple of its title and any
error text.
Works for html and pdf (but not, e.g., Word docs).
"""
notes = ''
try:
page = requests.get(url)
except Exception as ex:
title = 'Source'
notes = 'Error loading url: "{}".'.format(str(ex))
else:
# Test page.url rather than url parameter since redirection
# can route to something other than the url parameter.
if not page.url.endswith('pdf'):
try:
soup = BeautifulSoup(
page.text, convertEntities=BeautifulSoup.HTML_ENTITIES)
title = soup.find('head').find('title').text
except Exception as ex:
title = 'Source'
notes = 'Error parsing page: "{}".'.format(str(ex))
else:
try:
pdf = pyPdf.PdfFileReader(StringIO(page.content))
title = pdf.documentInfo['/Title']
except Exception as ex:
title = 'Source'
notes = 'Error parsing PDF: "{}".'.format(str(ex))
if not title.strip():
title = 'Source'
return title, notes
def ActualizarCantPaginas(data):
list_dir_zonas = [
'{}\\{}\\{}'.format(path_urbano_croquis_listado, x[0], x[1])
for x in data
]
for dir_zona in list_dir_zonas:
for archivo in os.listdir(dir_zona):
if (archivo.endswith('.pdf')):
l = len(archivo)
cod = archivo[0:l - 4]
nom_pdf = "{}\\{}".format(dir_zona, archivo)
pdf = pyPdf.PdfFileReader(open(nom_pdf, "rb"))
cant_pag = pdf.getNumPages()
list_web = nom_pdf.split("\\")[3:]
nom_web = ""
for i in list_web:
nom_web = nom_web + '/' + i
# print nom_web
nom_web = nom_web.replace("\\", "/")
# print nom_web
conx.ActualizarCantidadPaginas(fase, cod, cant_pag, nom_pdf,
nom_web)
def combine_multiple_canvas(self):
"""Combine multiple PDF files at once when is working with multiple canvas"""
if not self.multiple_canvas or not pyPdf or not self.temp_files:
return
readers = []
def append_pdf(input, output):
for page_num in range(input.numPages):
output.addPage(input.getPage(page_num))
output = pyPdf.PdfFileWriter()
for f_name in self.temp_files:
reader = pyPdf.PdfFileReader(file(f_name, 'rb'))
readers.append(reader)
append_pdf(reader, output)
if isinstance(self.filename, basestring):
fp = file(self.filename, 'wb')
else:
fp = self.filename
output.write(fp)
# Closes and clear objects
fp.close()
for r in readers:
del r
del output
def pdf_pages(file_info, width):
output = ''
if width is None:
width = DEFAULT_PAGE_WIDTH
if not os.path.isfile(file_info['path'] + '.pdf'):
if file_info['extension'] in ('rtf', 'doc', 'odt') and not os.path.isfile(file_info['path'] + '.pdf'):
server.fg_make_pdf_for_word_path(file_info['path'], file_info['extension'])
if 'pages' not in file_info:
try:
reader = pyPdf.PdfFileReader(open(file_info['path'] + '.pdf'))
file_info['pages'] = reader.getNumPages()
except:
file_info['pages'] = 1
max_pages = 1 + int(file_info['pages'])
formatter = '%0' + unicode(len(unicode(max_pages))) + 'd'
for page in range(1, max_pages):
page_file = dict()
test_path = file_info['path'] + 'page-in-progress'
if os.path.isfile(test_path):
while (os.path.isfile(test_path) and time.time() - os.stat(test_path)[stat.ST_MTIME]) < 30:
if not os.path.isfile(test_path):
break
time.sleep(1)
page_file['extension'] = 'png'
page_file['path'] = file_info['path'] + 'page-' + formatter % page
page_file['fullpath'] = page_file['path'] + '.png'
if not os.path.isfile(page_file['fullpath']):
server.fg_make_png_for_pdf_path(file_info['path'] + '.pdf', 'page')
if os.path.isfile(page_file['fullpath']):
output += unicode(image_for_docx(docassemble.base.functions.DALocalFile(page_file['fullpath']), docassemble.base.functions.this_thread.current_question, docassemble.base.functions.this_thread.misc.get('docx_template', None), width=width))
else:
output += "[Error including page image]"
output += ' '
return(output)
def textoPdfCoef(nombrePdf):
pdf = pyPdf.PdfFileReader(open(nombrePdf, "rb"))
for page in pdf.pages:
data = []
a = page.extractText().split("TR=100")[1].split("Datos")[0].split(".")
r = 10
for i, d in enumerate([2, 3, 5, 10, 25, 50, 100]):
#for j,tr in enumerate(["C1","X0","C2"]):
if i < 6 and i >= 1:
C1 = float(a[r * i][1 + len(str(d)):] + "." + a[r * i + 1][:3])
elif i == 0:
C1 = float(a[r * i][1:] + "." + a[r * i + 1][:3])
else:
None
C1 = float(a[r * (i - 1) + 3][1 + len(str(d)):] + "." +
a[r * (i - 1) + 4][:3])
if i < 6:
X0 = float(a[r * i + 1][3:] + "." + a[r * i + 2][:3])
C2 = float(a[r * i + 2][3:] + "." + a[r * i + 3][:3])
else:
None
X0 = float(a[r * (i - 1) + 4][3:] + "." + a[r *
(i - 1) + 5][:3])
C2 = float(a[r * (i - 1) + 5][3:] + "." + a[r *
(i - 1) + 6][:3])
data.append([C1, X0, C2])
return data
def getPDFContent(doc,search_terms):
#print "getPDFContent"
filename = "iomat_%s.pdf" % (doc.date.replace("/","-"))
content = ""
pdf = pyPdf.PdfFileReader(file(filename,'rb'))
str = ""
for i in range (0,pdf.getNumPages()):
page_content = pdf.getPage(i).extractText().lower()
#print type(page_content)
for term in search_terms:
#print u"Procurando o termo %s" % term
if page_content.find(term) != -1:
where = page_content.find(term)
str = str + "O termo %s foi encontrado no diario %s na pagina %d \n" % (term,filename,i+1)
other = ""
if where>60 and (where + 60 < len(page_content)):
other = page_content[where-60:where+60]
str = str + other + "\r\n\r\n"
docLink = "http://www.iomat.mt.gov.br/ler_pdf.php?download=ok\&edi_id=%d\&page=0" % (doc.value)
str = str + docLink + "\r\n\r\n\r\n"
return str
def get_metadata(self, filing):
url = filing['pdf_url']
try:
pdf = urllib2.urlopen(url).read()
except urllib2.HTTPError:
return None
# We can save the PDF here and then upload it to Document Cloud.
pdf = pyPdf.PdfFileReader(StringIO(pdf))
text = pdf.getPage(0).extractText()
print
print text
print
metadata = {}
for line in text.split('\n'):
if line.find('=') > -1:
k, v = line.split('=')
k = k.title()
if v == 'N/A':
v = ''
metadata.update({
k: v,
})
return metadata
def scrape_text(src):
pages = []
pdf = pyPdf.PdfFileReader(open(src, "rb"))
for page in pdf.pages:
text = extract_text(page)
pages.append(text)
return pages
def pdf_opener(filename):
# filename = "test_pf.pdf"
pdf = pyPdf.PdfFileReader(open(filename, "rb"))
return pdf
for page in pdf.pages:
print page.extractText()
def GetPageCount():
global path
global pageCount
fh = file(path, 'rb')
input = pyPdf.PdfFileReader(fh)
pageCount = input.getNumPages()
fh.close()
def AutoSplit(event):
global pageCount
global path
if path:
dlg = wx.MessageDialog(
top, "This will automatically export individual pages.",
"Confirm AutoSplit", wx.OK | wx.CANCEL | wx.ICON_QUESTION)
result = dlg.ShowModal()
dlg.Destroy()
if result == wx.ID_OK:
fh = file(path, 'rb')
input = pyPdf.PdfFileReader(fh)
DestFileName = wx.GetTextFromUser(
"Please provide output file name:", "Export File Name?",
"Pages from " + os.path.basename(path).split('.')[0], top)
for page in range(0, pageCount):
outputPage = pyPdf.PdfFileWriter()
outputPage.addPage(input.getPage(page))
outputFileName = os.path.dirname(
path) + os.sep + DestFileName + " - " + str(page +
1) + ".pdf"
outputStream = file(outputFileName, "wb")
outputPage.write(outputStream)
outputStream.close()
fh.close()
else:
dlg = wx.MessageDialog(top, "No file selected!", "Error...",
wx.OK | wx.ICON_QUESTION)
dlg.ShowModal()
top.SetStatusText("No file selected. Please use \"Select File...\"")
def ExportSelected(event):
if path:
PagesToExport = SelectionPanel.GetSelections()
if len(PagesToExport) < 1:
dlg = wx.MessageDialog(top, "No pages selected!", "Error...",
wx.OK | wx.ICON_QUESTION)
dlg.ShowModal()
dlg.Destroy()
top.SetStatusText(
"No pages selected. Please use the selection panel.")
else:
fh = file(path, 'rb')
DestFileName = wx.GetTextFromUser(
"Please provide output file name:", "Export File Name?",
"Pages from " + os.path.basename(path).split('.')[0], top)
input = pyPdf.PdfFileReader(fh)
outputPage = pyPdf.PdfFileWriter()
for PageToExport in PagesToExport:
outputPage.addPage(input.getPage(PageToExport))
outputFileName = os.path.dirname(
path) + os.sep + DestFileName + ".pdf"
outputStream = file(outputFileName, "wb")
outputPage.write(outputStream)
outputStream.close()
fh.close()
else:
dlg = wx.MessageDialog(top, "No file selected!", "Error...",
wx.OK | wx.ICON_QUESTION)
dlg.ShowModal()
top.SetStatusText("No file selected. Please use \"Select File...\"")
return
def pages(F):
#zwraca ilosc stron pliku o scierzce F
FILEOBJ = file(F, "rb")
PDF = pyPdf.PdfFileReader(FILEOBJ)
n = PDF.getNumPages()
FILEOBJ.close()
return n
def pdfsearch(request):
if request.method == 'POST':
raw = request.POST
url = request.path
#unpack raw json into data variable
for key in raw:
data = simplejson.loads(key)
#unpack data to assign tier, node, and parent variables
i=0
while i in range(len(data)):
if data[i]['name'] == 'tier':
tier = data[i]['value']
i += 1
elif data[i]['name'] == 'node':
node = data[i]['value']
i += 1
elif data[i]['name'] == 'parent':
parent = data[i]['value']
i += 1
else: i += 1
#identify the model from the selected tier
if tier == 'node_1':
model = Node_1
elif tier == 'node_2':
model = Node_2
elif tier == 'node_3':
model = Node_3
elif tier == 'node_4':
model = Node_4
elif tier == 'node_5':
model = Node_5
else: pass
parent = Parent.objects.get(id = parent)
# from the model, create specific node variable that node's PDF path variable
node = model.objects.get(node_name__contains = node[:4])
try :
path = node.pdf_path #pdf path in model should be the page(s) pertinent to that node
except:
msg = 'No PDF content to display'
return HttpResponse(msg, mimetype = 'application/text')
#get the actual content of the PDF
content = 'penis'
p = file(path, "rb")
pdf = pyPdf.PdfFileReader(p)
i=0
while i in range(pdf.getNumPages()):
content += pdf.getPage(i).extractText() + "\n"
i += 1
content = {"pdf" : str(content)}
return HttpResponse(content, content_type = 'application/json')
else: return 'f****d'
