PyPDF module doesn' t make valid pdf file - python

i'm trying to make some program in python to manipulate my pdf beamer presentations. Professor use on click dynamic transition so one page has several click transitions. I want to print those presentations but i have around 5000 pages. So i want to use just the last click transition page, so i will minimize number of pages to around 500. I'm using PyPDF2 module but it not makes valid pdf file. Here's the code:
from pyPdf import PdfFileWriter, PdfFileReader
import os,sys
pdful = raw_input("Uneti ime fajla:")
output = PdfFileWriter()
input1 = PdfFileReader(open(pdful, "rb"))
m = []
f = True
print ("Uneti strane koje zelite da zadrzite.String 0 kraj unosa:\n")
while f:
l = int(raw_input("Uneti broj stranice:"))
if l == 0:
f = not f
else: m.append(l-1)
for i in range(len(m)):
strana = input1.getPage(int(m[i]))
output.addPage(strana)
outputStream = file("Mat8.pdf","wb")
output.write(outputStream)
# string writings are in Serbian, but that's not so important. Program should take input from user: name of file to manipulate, and pages that should copy.

from pyPdf import PdfFileWriter, PdfFileReader pyPdf is discontinued already and is succeeded by PyPDF2. I am not sure about Python 2, but in Python 3 you should import PyPDF2.
No need to import os, sys. However, you can call python3 xyz.py some_arg in bash if you did use sys.argv. This way sys.argv[1] == some_arg
I would prefer using maps instead, as long as you don't need to read input line by line. For example,
print ("Uneti strane koje zelite da zadrzite.String 0 kraj unosa:\n")
m = map (lambda x: int(x) - 1, raw_input("Uneti broj stranice:").split())
Instead of the while loop. Also, iterate over objects instead of indices.
for page_number in m:
strana = input1.getPage(page_number)
output.addPage(strana)
Finally, use with to enclose file operations. Python will automatically handle closing of the file, lest you forget to do so.
with open (pdful, 'wb') as outputStream:
output.write(outputStream)

Related

Printing a PDF with Python from variable, instead a file

I would like to print a PDF file with an external printer. However, since I'm about to open, create or transform multiple files in some loop, I would like to print the thing without the need of saving it as a PDF file in every iteration.
Simplified code looks like this:
import PyPDF2
import os
pdf_in = open('tubba.pdf', 'rb')
pdf_reader = PyPDF2.PdfFileReader(pdf_in)
pdf_writer = PyPDF2.PdfFileWriter()
page = pdf_reader.getPage(0)
page.rotateClockwise(90)
# Some other operations done on the page, such as scaling, cropping etc.
pdf_writer.addPage(page)
pdf_out = open('rotated.pdf', 'wb')
pdf_writer.write(pdf_out)
pdf_print = os.startfile('rotated.pdf', 'print')
pdf_out.close()
pdf_in.close()
Is there any way to print "page", or "pdf_writer"?
Best regards
You can just use variables.
Eg.
path = 'C\yourfile.pdf'
os.startfile(path) #just pass the variable here

How to convert whole pdf to text in python

I have to convert whole pdf to text. i have seen at many places converting pdf to text but particular page.
from PyPDF2 import PdfFileReader
import os
def text_extractor(path):
with open(os.path.join(path,file), 'rb') as f:
pdf = PdfFileReader(f)
###Here i can specify page but i need to convert whole pdf without specifying pages###
page = pdf.getPage(0)
text = page.extractText()
print(text)
if __name__ == '__main__':
path="C:\\Users\\AAAA\\Desktop\\BB"
for file in os.listdir(path):
if not file.endswith(".pdf"):
continue
text_extractor(path)
How to convert whole pdf file to text without using getpage()??
You may want to use textract as this answer recommends to get the full document if all you want is the text.
If you want to use PyPDF2 then you can first get the number of pages then iterate over each page such as:
from PyPDF2 import PdfFileReader
import os
def text_extractor(path):
with open(os.path.join(path,file), 'rb') as f:
pdf = PdfFileReader(f)
###Here i can specify page but i need to convert whole pdf without specifying pages###
text = ""
for page_num in range(pdf.getNumPages()):
page = pdf.getPage(page_num)
text += page.extractText()
print(text)
if __name__ == '__main__':
path="C:\\Users\\AAAA\\Desktop\\BB"
for file in os.listdir(path):
if not file.endswith(".pdf"):
continue
text_extractor(path)
Though you may want to remember which page the text came from in which case you could use a list:
page_text = []
for page_num in range(pdf.getNumPages()): # For each page
page = pdf.getPage(page_num) # Get that page's reference
page_text.append(page.extractText()) # Add that page to our array
for page in page_text:
print(page) # print each page
You could use tika to accomplish this task, but the output needs a little cleaning.
from tika import parser
parse_entire_pdf = parser.from_file('mypdf.pdf', xmlContent=True)
parse_entire_pdf = parse_entire_pdf['content']
print (parse_entire_pdf)
This answer uses PyPDF2 and encode('utf-8') to keep the output per page together.
from PyPDF2 import PdfFileReader
def pdf_text_extractor(path):
with open(path, 'rb') as f:
pdf = PdfFileReader(f)
# Get total pdf page number.
totalPageNumber = pdf.numPages
currentPageNumber = 0
while (currentPageNumber < totalPageNumber):
page = pdf.getPage(currentPageNumber)
text = page.extractText()
# The encoding put each page on a single line.
# type is <class 'bytes'>
print(text.encode('utf-8'))
#################################
# This outputs the text to a list,
# but it doesn't keep paragraphs
# together
#################################
# output = text.encode('utf-8')
# split = str(output, 'utf-8').split('\n')
# print (split)
#################################
# Process next page.
currentPageNumber += 1
path = 'mypdf.pdf'
pdf_text_extractor(path)
Try pdfreader. You can extract either plain text or decoded text containing "pdf markdown":
from pdfreader import SimplePDFViewer, PageDoesNotExist
fd = open(you_pdf_file_name, "rb")
viewer = SimplePDFViewer(fd)
plain_text = ""
pdf_markdown = ""
try:
while True:
viewer.render()
pdf_markdown += viewer.canvas.text_content
plain_text += "".join(viewer.canvas.strings)
viewer.next()
except PageDoesNotExist:
pass
PDF is a page-oriented format & therefore you'll need to deal with the concept of pages.
What makes it perhaps even more difficult, you're not guaranteed that the text excerpts you're able to extract are extracted in the same order as they are presented on the page: PDF allows one to say "put this text within a 4x3 box situated 1" from the top, with a 1" left margin.", and then I can put the next set of text somewhere else on the same page.
Your extractText() function simply gets the extracted text blocks in document order, not presentation order.
Tables are notoriously difficult to extract in a common, meaningful way... You see them as tables, PDF sees them as text blocks placed on the page with little or no relationship.
Still, getPage() and extractText() are good starting points & if you have simply formatted pages, they may work fine.
I found out a very simple way to do this.
You have to follow this steps:
Install PyPDF2 :To do this step if you use Anaconda, search for Anaconda Prompt and digit the following command, you need administrator permission to do this.
pip install PyPDF2
If you're not using Anaconda you have to install pip and put its path
to your cmd or terminal.
Python Code: This following code shows how to convert a pdf file very easily:
import PyPDF2
with open("pdf file path here",'rb') as file_obj:
pdf_reader = PyPDF2.PdfFileReader(file_obj)
raw = pdf_reader.getPage(0).extractText()
print(raw)
I just used pdftotext module to get this done easily.
import pdftotext
# Load your PDF
with open("test.pdf", "rb") as f:
pdf = pdftotext.PDF(f)
# creating a text file after iterating through all pages in the pdf
file = open("test.txt", "w")
for page in pdf:
file.write(page)
file.close()
Link: https://github.com/manojitballav/pdf-text

How do I write a python script that can read doc/docx files and convert them to txt?

Basically I have a folder with plenty of .doc/.docx files. I need them in .txt format. The script should iterate over all the files in a directory, convert them to .txt files and store them in another folder.
How can I do it?
Does there exist a module that can do this?
I figured this would make an interesting quick programming project. This has only been tested on a simple .docx file containing "Hello, world!", but the train of logic should give you a place to work from to parse more complex documents.
from shutil import copyfile, rmtree
import sys
import os
import zipfile
from lxml import etree
# command format: python3 docx_to_txt.py Hello.docx
# let's get the file name
zip_dir = sys.argv[1]
# cut off the .docx, make it a .zip
zip_dir_zip_ext = os.path.splitext(zip_dir)[0] + '.zip'
# make a copy of the .docx and put it in .zip
copyfile(zip_dir, zip_dir_zip_ext)
# unzip the .zip
zip_ref = zipfile.ZipFile(zip_dir_zip_ext, 'r')
zip_ref.extractall('./temp')
# get the xml out of /word/document.xml
data = etree.parse('./temp/word/document.xml')
# we'll want to go over all 't' elements in the xml node tree.
# note that MS office uses namespaces and that the w must be defined in the namespaces dictionary args
# each :t element is the "text" of the file. that's what we're looking for
# result is a list filled with the text of each t node in the xml document model
result = [node.text.strip() for node in data.xpath("//w:t", namespaces={'w':'http://schemas.openxmlformats.org/wordprocessingml/2006/main'})]
# dump result into a new .txt file
with open(os.path.splitext(zip_dir)[0]+'.txt', 'w') as txt:
# join the elements of result together since txt.write can't take lists
joined_result = '\n'.join(result)
# write it into the new file
txt.write(joined_result)
# close the zip_ref file
zip_ref.close()
# get rid of our mess of working directories
rmtree('./temp')
os.remove(zip_dir_zip_ext)
I'm sure there's a more elegant or pythonic way to accomplish this. You'll need to have the file you want to convert in the same directory as the python file. Command format is python3 docx_to_txt.py file_name.docx
conda install -c conda-forge python-docx
from docx import Document
doc = Document(file)
for p in doc.paragrafs:
print(p.text)
pass
Thought I would share my approach, basically boils down to two commands that convert either .doc or .docx to a string, both options require a certain package:
import docx
import os
import glob
import subprocess
import sys
# .docx (pip3 install python-docx)
doctext = "\n".join(i.text.encode("utf-8").decode("utf-8") for i in docx.Document(infile).paragraphs)
# .doc (apt-get install antiword)
doctext = subprocess.check_output(["antiword", infile]).decode("utf-8")
I then wrap these solutions up in a function, that can either return the result as a python string, or write to a file (with the option of appending or replacing).
import docx
import os
import glob
import subprocess
import sys
def doc2txt(infile, outfile, return_string=False, append=False):
if os.path.exists(infile):
if infile.endswith(".docx"):
try:
doctext = "\n".join(i.text.encode("utf-8").decode("utf-8") for i in docx.Document(infile).paragraphs)
except Exception as e:
print("Exception in converting .docx to str: ", e)
return None
elif infile.endswith(".doc"):
try:
doctext = subprocess.check_output(["antiword", infile]).decode("utf-8")
except Exception as e:
print("Exception in converting .docx to str: ", e)
return None
else:
print("{0} is not .doc or .docx".format(infile))
return None
if return_string == True:
return doctext
else:
writemode = "a" if append==True else "w"
with open(outfile, writemode) as f:
f.write(doctext)
f.close()
else:
print("{0} does not exist".format(infile))
return None
I then would call this function via something like:
files = glob.glob("/path/to/filedir/**/*.doc*", recursive=True)
outfile = "/path/to/out.txt"
for file in files:
doc2txt(file, outfile, return_string=False, append=True)
It's not often I need to perform this operation, but up until now the script has worked for all my needs, if you find this function has a bug let me know in a comment.

Generate flattened PDF with Python

When I print a PDF from any of my source PDFs, the file size drops and removes the text boxes presents in form. In short, it flattens the file.
This is behavior I want to achieve.
The following code to create a PDF using another PDF as a source (the one I want to flatten), it writes the text boxes form as well.
Can I get a PDF without the text boxes, flatten it? Just like Adobe does when I print a PDF as a PDF.
My other code looks something like this minus some things:
import os
import StringIO
from pyPdf import PdfFileWriter, PdfFileReader
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
directory = os.path.join(os.getcwd(), "source") # dir we are interested in
fif = [f for f in os.listdir(directory) if f[-3:] == 'pdf'] # get the PDFs
for i in fif:
packet = StringIO.StringIO()
can = canvas.Canvas(packet, pagesize=letter)
can.rotate(-90)
can.save()
packet.seek(0)
new_pdf = PdfFileReader(packet)
fname = os.path.join('source', i)
existing_pdf = PdfFileReader(file(fname, "rb"))
output = PdfFileWriter()
nump = existing_pdf.getNumPages()
page = existing_pdf.getPage(0)
for l in range(nump):
output.addPage(existing_pdf.getPage(l))
page.mergePage(new_pdf.getPage(0))
outputStream = file("out-"+i, "wb")
output.write(outputStream)
outputStream.close()
print fName + " written as", i
Summing up: I have a pdf, I add a text box to it, covering up info and adding new info, and then I print a pdf from that pdf. The text box becomes not editable or moveable any longer. I wanted to automate that process but everything I tried still allowed that text box to be editable.
If installing an OS package is an option, then you could use pdftk with its python wrapper pypdftk like this:
import pypdftk
pypdftk.fill_form('filled.pdf', out_file='flattened.pdf', flatten=True)
You would also need to install the pdftk package, which on Ubuntu could be done like this:
sudo apt-get install pdftk
The pypdftk library can by downloaded from PyPI:
pip install pypdftk
Update: pdftk was briefly removed from Ubuntu in version 18.04, but it seems it is back since 20.04.
A simple but more of a round about way it to covert the pdf to images than to put those image into a pdf.
You'll need pdf2image and PIL
Like So
from pdf2image import convert_from_path
from PIL import Image
images = convert_from_path('temp.pdf')
im1 = images[0]
images.pop(0)
pdf1_filename = "flattened.pdf"
im1.save(pdf1_filename, "PDF" ,resolution=100.0, save_all=True, append_images=images)
Edit:
I created a library to do this called fillpdf
pip install fillpdf
from fillpdf import fillpdfs
fillpdfs.flatten_pdf('input.pdf', 'newflat.pdf')
Per the Adobe Docs, you can change the Bit Position of the Editable Form Fields to 1 to make the field ReadOnly. I provided a full solution here, but it uses Django:
https://stackoverflow.com/a/55301804/8382028
Adobe Docs (page 552):
https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/pdf_reference_archives/PDFReference.pdf
Use PyPDF2 to fill the fields, then loop through the annotations to change the bit position:
from io import BytesIO
from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import BooleanObject, NameObject, NumberObject
# open the pdf
input_stream = open("YourPDF.pdf", "rb")
reader = PdfFileReader(input_stream, strict=False)
if "/AcroForm" in reader.trailer["/Root"]:
reader.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)}
)
writer = PdfFileWriter()
writer.set_need_appearances_writer()
if "/AcroForm" in writer._root_object:
# Acro form is form field, set needs appearances to fix printing issues
writer._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)}
)
data_dict = dict() # this is a dict of your form values
writer.addPage(reader.getPage(0))
page = writer.getPage(0)
# update form fields
writer.updatePageFormFieldValues(page, data_dict)
for j in range(0, len(page["/Annots"])):
writer_annot = page["/Annots"][j].getObject()
for field in data_dict:
if writer_annot.get("/T") == field:
# make ReadOnly:
writer_annot.update({NameObject("/Ff"): NumberObject(1)})
output_stream = BytesIO()
writer.write(output_stream)
# output_stream is your flattened PDF
A solution that goes for Windows as well, converts many pdf pages and flatens the chackbox values as well. For some reason #ViaTech code did not work in my pc (Windows7 python 3.8)
Followed #ViaTech indications and used extensively #hchillon code from this post
from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import BooleanObject, NameObject, IndirectObject, TextStringObject, NumberObject
def set_need_appearances_writer(writer):
try:
catalog = writer._root_object
# get the AcroForm tree and add "/NeedAppearances attribute
if "/AcroForm" not in catalog:
writer._root_object.update({
NameObject("/AcroForm"): IndirectObject(len(writer._objects), 0, writer)})
need_appearances = NameObject("/NeedAppearances")
writer._root_object["/AcroForm"][need_appearances] = BooleanObject(True)
return writer
except Exception as e:
print('set_need_appearances_writer() catch : ', repr(e))
return writer
class PdfFileFiller(object):
def __init__(self, infile):
self.pdf = PdfFileReader(open(infile, "rb"), strict=False)
if "/AcroForm" in self.pdf.trailer["/Root"]:
self.pdf.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
# newvals and newchecks have keys have to be filled. '' is not accepted
def update_form_values(self, outfile, newvals=None, newchecks=None):
self.pdf2 = MyPdfFileWriter()
trailer = self.pdf.trailer['/Root'].get('/AcroForm', None)
if trailer:
self.pdf2._root_object.update({
NameObject('/AcroForm'): trailer})
set_need_appearances_writer(self.pdf2)
if "/AcroForm" in self.pdf2._root_object:
self.pdf2._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
for i in range(self.pdf.getNumPages()):
self.pdf2.addPage(self.pdf.getPage(i))
self.pdf2.updatePageFormFieldValues(self.pdf2.getPage(i), newvals)
for j in range(0, len(self.pdf.getPage(i)['/Annots'])):
writer_annot = self.pdf.getPage(i)['/Annots'][j].getObject()
for field in newvals:
writer_annot.update({NameObject("/Ff"): NumberObject(1)})
self.pdf2.updatePageFormCheckboxValues(self.pdf2.getPage(i), newchecks)
with open(outfile, 'wb') as out:
self.pdf2.write(out)
class MyPdfFileWriter(PdfFileWriter):
def __init__(self):
super().__init__()
def updatePageFormCheckboxValues(self, page, fields):
for j in range(0, len(page['/Annots'])):
writer_annot = page['/Annots'][j].getObject()
for field in fields:
writer_annot.update({NameObject("/Ff"): NumberObject(1)})
origin = ## Put input pdf path here
destination = ## Put output pdf path here, even if the file does not exist yet
newchecks = {} # A dict with all checkbox values that need to be changed
newvals = {'':''} # A dict with all entry values that need to be changed
# newvals dict has to be equal to {'':''} in case that no changes are needed
c = PdfFileFiller(origin)
c.update_form_values(outfile=destination, newvals=newvals, newchecks=newchecks)
print('PDF has been created\n')
I had trouble flattening a form that I had entered content into using pdfrw (How to Populate Fillable PDF's with Python) and found that I had to add an additional step using generate_fdf (pdftk flatten loses fillable field data).
os.system('pdftk '+outtemp+' generate_fdf output '+outfdf)
os.system('pdftk '+outtemp+' fill_form '+outfdf+' output '+outpdf)
I came to this solution because I was able to flatten a file just fine using ghostscript's pdf2ps followed by ps2pdf on my Mac, but the quality had low resolution when I ran it on an Amazon Linux instance. I couldn't figure out why that was the case and so moved to the pdftk solution.

merging pdf files with pypdf

I am writing a script that parses an internet site (maya.tase.co.il) for links, downloads pdf file and merges them. It works mostly, but merging gives me different kinds of errors depending on the file. I cant seem to figure out why. I cut out the relevant code and built a test only for two specific files that are causing a problem. The script uses pypdf, but I am willing to try anything that works. Some files are encrypted, some are not.
def is_incry(pdf):
from pyPdf import PdfFileWriter, PdfFileReader
input=PdfFileReader(pdf)
try:
input.getNumPages()
return input
except:
input.decrypt("")
return input
def merg_pdf(to_keep,to_lose):
import os
from pyPdf import PdfFileWriter, PdfFileReader
if os.path.exists(to_keep):
in1=file(to_keep, "rb")
in2=file(to_lose, "rb")
input1 = is_incry(in1)
input2 = is_incry(in2)
output = PdfFileWriter()
loop1=input1.getNumPages()
for i in range(0,loop1):
output.addPage(input1.getPage(i))#
loop2=input2.getNumPages()
for i in range(0,loop2):
output.addPage(input2.getPage(i))#
outputStream = file("document-output.pdf", "wb")
output.write(outputStream)
outputStream.close()
pdflen=loop1+loop2
in1.close()
in2.close()
os.remove(to_lose)
os.remove(to_keep)
os.rename("document-output.pdf",to_keep)
else:
os.rename(to_lose,to_keep)
in1=file(to_keep, "rb")
input1 = PdfFileReader(in1)
try:
pdflen=input1.getNumPages()
except:
input1.decrypt("")
pdflen=input1.getNumPages()
in1.close()
#input1.close()
return pdflen
def test():
import urllib
urllib.urlretrieve ('http://mayafiles.tase.co.il/RPdf/487001-488000/P487028-01.pdf', 'temp1.pdf')
urllib.urlretrieve ('http://mayafiles.tase.co.il/RPdf/488001-489000/P488170-00.pdf', 'temp2.pdf')
merg_pdf('temp1.pdf','temp2.pdf')
test()
I thank anyone that even took the time to read this.
Al.
I once wrote a complex PDF generation/merging stuff which I have now open-sourced.
You can have a look at it: https://github.com/becomingGuru/nikecup/blob/master/reg/models.py#L71
def merge_pdf(self):
from pyPdf import PdfFileReader,PdfFileWriter
pdf_file = file_names['main_pdf']%settings.MEDIA_ROOT
pdf_obj = PdfFileReader(open(pdf_file))
values_page = PdfFileReader(open(self.make_pdf())).getPage(0)
mergepage = pdf_obj.pages[0]
mergepage.mergePage(values_page)
signed_pdf = PdfFileWriter()
for page in pdf_obj.pages:
signed_pdf.addPage(page)
signed_pdf_name = file_names['dl_done']%(settings.MEDIA_ROOT,self.phash)
signed_pdf_file = open(signed_pdf_name,mode='wb')
signed_pdf.write(signed_pdf_file)
signed_pdf_file.close()
return signed_pdf_name
It then works like a charm. Hope it helps.
I tried the documents with pyPdf - it looks like both the pdfs in this document are encrypted, and a blank password ("") is not valid.
Looking at the security settings in adobe, you're allowed to print and copy - however, when you run pyPdf's input.decrypt(""), the files are still encrypted (as in, input.getNumPages() after this still returns 0).
I was able to open this in OSX's preview, and save the pdfs without encryption, and then the assembly works fine. pyPdf deals in pages though, so I don't think you can do this through pyPdf. Either find the correct password, or perhaps use another application, such as using a batch job to OpenOffice, or another pdf plugin would work.

Categories