#!/usr/bin/env python
# coding: utf-8

# <a href="https://colab.research.google.com/github/klajosw/python/blob/master/kl_py_pdf_read_write_01.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

# <p align="left"> 
#     <img src="https://raw.githubusercontent.com/klajosw/python/master/kl_mie_python_logo_250.jpg" 
#          align="left" width="251" height="251">
#     
# </p>
# 
# 
# <p> </p>
# 
# # PDF használata pythonnal.
# 
# ## PyPDF2, PyPDF4 csomag
# 
# ## tika  csomag
# 
# ## pdfplumber csomag
# 
# 
# 
# https://klajosw.blogspot.com/
# 
# https://github.com/klajosw/
# 
# ---

# 
# 
# # Telepítés
# 
# ## Anaconda
# 
# conda install PyPDF2
# conda install tika
# conda install pdfplumber
# 
# ## Python
# 
# python3 -m pip install PyPDF2
# python3 -m pip show PyPDF2
# 
# python3 -m pip install tika
# python3 -m pip install pdfplumber
# 
# ### Állományból telepítés
# 
# python3 -m pip install c:\Users\User\Downloads\PyPDF4-1.27.0.tar.gz 
# 
# ----
# 

# In[ ]:


# modul importálása
import PyPDF2 
    
# file objektum létrehozása (b: binális megnyítással) 
pdfFileObj = open(r'c:\Users\User\Documents\kl\sj_pdf\hozzajarulo_nyilatkozat_vedooltashoz.pdf', 'rb') 
    
# pdf kiolvasó objektum léterhozása 
pdfReader = PyPDF2.PdfFileReader(pdfFileObj) 
    
# lapszám kiírása 
print('A pdf file oldal száma :', pdfReader.numPages) 
    
# egy oldal megcímzése 
pageObj = pdfReader.getPage(0) 

print('---------------pdf tartalma ---------------')
    
# megcímzett oldal kiolvasása és kiírása 
print(pageObj.extractText()) 

print('---------------pdf információk ---------------')


information = pdfReader.getDocumentInfo()
number_of_pages = pdfReader.getNumPages()
print('pdf létrehozás ideje:', information['/CreationDate'])

txt = f"""
    Information about pdf
    Author: {information.author}
    Creator: {information.creator}
    Producer: {information.producer}
    Subject: {information.subject}
    Title: {information.title} 
    Number of pages: {number_of_pages}
    """

print(txt)
    
# pdf olvasás lezárása
pdfFileObj.close() 


# In[ ]:


# modul importálása
from tika import parser  
  
# pdf file megnyítása
parsed_pdf = parser.from_file(r'c:\Users\User\Documents\kl\sj_pdf\hozzajarulo_nyilatkozat_vedooltashoz.pdf')
#parsed_pdf = parser.from_file(r'c:\Users\User\Documents\kl\sj_pdf\02_04_21_Firefox_finomsagok.pdf')


#print(parsed_pdf.keys())  ## dict_keys(['metadata', 'content', 'status'])  
# pdf tartalom kinyerése szövegként
data = parsed_pdf['content'] 

print('---------------pdf tartalma ---------------')
  
# tartalom kiírása 
print(data)
  
print('---------------pdf információk ---------------')

print('pdf létrehozás ideje: ', parsed_pdf['metadata']['Creation-Date']) 
print('pdf oldalszám: ', parsed_pdf['metadata']['xmpTPg:NPages']) 
print('pdf gen. prg.: ', parsed_pdf['metadata']['xmp:CreatorTool']) 

# print(parsed_pdf['metadata'])


# In[ ]:





# In[ ]:


# extract_doc_info.py

from PyPDF2 import PdfFileReader

def extract_information(pdf_path):
    with open(pdf_path, 'rb') as f:
        pdf = PdfFileReader(f)
        information = pdf.getDocumentInfo()
        number_of_pages = pdf.getNumPages()

    txt = f"""
    Information about {pdf_path}: 

    Author: {information.author}
    Creator: {information.creator}
    Producer: {information.producer}
    Subject: {information.subject}
    Title: {information.title}
    Number of pages: {number_of_pages}
    """

    print(txt)
    return information

if __name__ == '__main__':
    path = r'c:\Users\User\Downloads\06_04_20_USB4.pdf'
    extract_information(path)


# In[ ]:


# pdf tartalom forgatás

from PyPDF4 import PdfFileReader, PdfFileWriter

def rotate_pages(pdf_path):
    pdf_writer = PdfFileWriter()
    pdf_reader = PdfFileReader(pdf_path)
    # elforgatás 90 fokkal jobbra
    page_1 = pdf_reader.getPage(0).rotateClockwise(90)
    pdf_writer.addPage(page_1)
    # elforgatás 90 fokkal balra
    page_2 = pdf_reader.getPage(1).rotateCounterClockwise(90)
    pdf_writer.addPage(page_2)
    # alap helyzetbe
    pdf_writer.addPage(pdf_reader.getPage(2))

    with open(r'c:\Users\User\Downloads\rotate_pages.pdf', 'wb') as fh:
        pdf_writer.write(fh)

if __name__ == '__main__':
    path = r'c:\Users\User\Downloads\06_04_20_USB4.pdf'
    rotate_pages(path)


# In[ ]:


# pdf_összefüzés

from PyPDF2 import PdfFileReader, PdfFileWriter

def merge_pdfs(paths, output):
    pdf_writer = PdfFileWriter()

    for path in paths:
        pdf_reader = PdfFileReader(path)
        for page in range(pdf_reader.getNumPages()):
            # Add each page to the writer object
            pdf_writer.addPage(pdf_reader.getPage(page))

    # Write out the merged PDF
    with open(output, 'wb') as out:
        pdf_writer.write(out)

if __name__ == '__main__':
    paths = [r'c:\Users\User\Downloads\06_04_20_USB4.pdf', r'c:\Users\User\Downloads\01_03_20_IPTV_Streaming.pdf']
    merge_pdfs(paths, output=r'c:\Users\User\Downloads\merged.pdf')


# In[ ]:


# pdf kivágás / oldalakra szét darabolás

from PyPDF2 import PdfFileReader, PdfFileWriter

def split(path, name_of_split):
    pdf = PdfFileReader(path)
    for page in range(pdf.getNumPages()):
        pdf_writer = PdfFileWriter()
        pdf_writer.addPage(pdf.getPage(page))

        output = f'{name_of_split}{page}.pdf'
        with open(output, 'wb') as output_pdf:
            pdf_writer.write(output_pdf)

if __name__ == '__main__':
    path = r'c:\Users\User\Downloads\06_04_20_USB4.pdf'
    split(path, r'c:\Users\User\Downloads\jupyter_page.pdf')


# In[ ]:


# pdf jelszavas védelem
from PyPDF4 import PdfFileWriter, PdfFileReader

def add_encryption(input_pdf, output_pdf, password):
    pdf_writer = PdfFileWriter()
    pdf_reader = PdfFileReader(input_pdf)

    for page in range(pdf_reader.getNumPages()):
        pdf_writer.addPage(pdf_reader.getPage(page))

    pdf_writer.encrypt(user_pwd=password, owner_pwd=None, use_128bit=True)

    with open(output_pdf, 'wb') as fh:
        pdf_writer.write(fh)
        
## Jelszavas megnyítás
# pdf_reader.decrypt(password="Miérdekel?")
# pdf_reader.getPage(0)


if __name__ == '__main__':
    add_encryption(input_pdf=r'c:\Users\User\Downloads\06_04_20_USB4.pdf',
                   output_pdf=r'c:\Users\User\Downloads\06_04_20_USB4_encrypt.pdf',
                   password='Miérdekel?')


# In[ ]:


#python verzió lekérése (jupyter-ben)
import sys
from pathlib import Path

get_ipython().system('{sys.executable} --version')
# Python 3.7.7

print('\n', Path.home())


# In[ ]:


import PyPDF2
pdfFileObj = open(r'c:\Users\User\Downloads\06_04_20_USB4.pdf', 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
print('oldalszám', pdfReader.numPages)
pageObj = pdfReader.getPage(0)
pageObj.extractText()
pdfReader.getPage(1-1).extractText()  ## második oldaltol az utolsóig beolvasás


# In[ ]:


import PyPDF2, os

# Get all the PDF filenames. / keresd ki összes PDF fájlnevet.
pdfFiles = []
for filename in os.listdir('.'):
    if filename.endswith('.pdf'):
        pdfFiles.append(filename)
pdfFiles.sort(key=str.lower)

# Loop through all the PDF files. / járjuk végig az összes PDF fájlt.
for filename in pdfFiles:
    pdfFileObj = open(filename, 'rb')
    pdfReader = PyPDF2.PdfFileReader(pdfFileObj)

# Loop through all the pages (except the first) and add them. / járjuk végig az összes oldalt (az első kivételével), és adja hozzá őket.
    for pageNum in range(1, pdfReader.numPages):
        pageObj = pdfReader.getPage(pageNum)
        pdfWriter.addPage(pageObj)


# Save the resulting PDF to a file. / Mentsd el a kapott PDF fájlt.
pdfOutput = open('all_sources.pdf', 'wb')
pdfWriter.write(pdfOutput)
pdfOutput.close()


# In[ ]:


import os
from os.path import isfile, join
import PyPDF2
"""If running locally, set these variables to your local directories.
"""
pdf_dir = r"c:/Users/User/Documents/kl/sj_pdf"
txt_dir = r"c:/Users/User/Documents/kl/sj_pdf"
    
"""Note: Uses a generator expression.
Rerun the cell if you restart the loop below.
"""
corpus = (f for f in os.listdir(pdf_dir) if not f.startswith('.') and isfile(join(pdf_dir, f)) and f.endswith('.pdf'))

"""The documentation for PyPDF2 is minimal. 
For this pattern, I followed the syntax at 
https://automatetheboringstuff.com/chapter13/ and
https://github.com/msaxton/iliff_review/blob/master/code/atla_pdfConvert.py
"""

for filename in corpus:
    print(filename)
    # Open the PDF and load as PyPDF2 Reader object.
    pdf = open(join(pdf_dir, filename), mode='rb')
    pdfReader = PyPDF2.PdfFileReader(pdf,strict=False)
    
    # Loop through the pages, extract the text, and write each page to individual file.
    for page in range(0, pdfReader.numPages):
        pageObj = pdfReader.getPage(page)
        text = pageObj.extractText()   #.encode('ascii', 'ignore')
        
        # Compile the page name. Add one because Python counts from 0.
        page_name = "{}-page{}.txt".format(filename[:-4], page+1)

        # Write to each page to file
        with open(join(txt_dir, page_name), mode="w", encoding='utf-8') as o:
            o.write(text)
            
"""
    try:
        pdf_writer = PyPDF4.PdfFileWriter()
        pdf_writer.addPage(pdf.getPage(page))
        output = name_of_split + '_f'+str(page)+'.pdf'
        with open(output, 'wb') as output_pdf:
            pdf_writer.write(output_pdf)
    except Exception as e:
        print('Exception:', output,e,output_pdf)

"""


# In[ ]:


## Angol karakterek csoportosítása
whitespace = ' \t\n\r\v\f'
ascii_lowercase = 'abcdefghijklmnopqrstuvwxyz'
ascii_uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
ascii_letters = ascii_lowercase + ascii_uppercase
digits = '0123456789'
hexdigits = digits + 'abcdef' + 'ABCDEF'
octdigits = '01234567'
punctuation = r"""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
printable = digits + ascii_letters + punctuation + whitespace


# In[ ]: