2019년 2월 26일 화요일

[Python] PDF File Handle with pypdf2


1. PDF File Handle with pypdf2
1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
from PyPDF2 import PdfFileWriter, PdfFileReader
  
def get_info(path):
    with open(path, 'rb') as f:
        pdf = PdfFileReader(f)
        info = pdf.getDocumentInfo()
        number_of_pages = pdf.getNumPages()
 
    print(info)
    print('pages: ' + str(number_of_pages))
 
    author = info.author
    creator = info.creator
    producer = info.producer
    subject = info.subject
    title = info.title
    
def text_extractor(path):
    with open(path, 'rb') as f:
        pdf = PdfFileReader(f)
 
        # get the first page
        page = pdf.getPage(1)
        print(page)
        print('Page type: {}'.format(str(type(page))))
 
        text = page.extractText()
        print('text: ' + text)
 
def pdf_splitter(path):
    import os
    import glob    
    fname = os.path.splitext(os.path.basename(path))[0]

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

        output_filename = '{}_page_{}.pdf'.format(fname, page+1)

        with open(output_filename, 'wb') as out:
            pdf_writer.write(out)

        print('Created: {}'.format(output_filename))

def merger(output_path, input_paths):
    pdf_writer = PdfFileWriter()

    for path in input_paths:
        pdf_reader = PdfFileReader(path)
        for page in range(pdf_reader.getNumPages()):
            pdf_writer.addPage(pdf_reader.getPage(page))

    with open(output_path, 'wb') as fh:
        pdf_writer.write(fh)
        
    '''
    import glob
    if __name__ == '__main__':
    paths = glob.glob('w9_*.pdf')
    paths.sort()
    merger('pdf_merger.pdf', paths)
    '''
    
def merger1(output_path, input_paths):
    pdf_merger = PdfFileMerger()
    file_handles = []

    for path in input_paths:
        pdf_merger.append(path)

    with open(output_path, 'wb') as fileobj:
        pdf_merger.write(fileobj)
    
    '''
    if __name__ == '__main__':
        paths = glob.glob('fw9_*.pdf')
        paths.sort()
        merger1('pdf_merger2.pdf', paths)
    '''

def rotator(path):
    pdf_writer = PdfFileWriter()
    pdf_reader = PdfFileReader(path)
 
    page1 = pdf_reader.getPage(0).rotateClockwise(90)
    pdf_writer.addPage(page1)
    page2 = pdf_reader.getPage(1).rotateCounterClockwise(90)
    pdf_writer.addPage(page2)
    pdf_writer.addPage(pdf_reader.getPage(2))
 
    with open('pdf_rotator.pdf', 'wb') as fh:
        pdf_writer.write(fh)

def watermark(input_pdf, output_pdf, watermark_pdf):
    watermark = PdfFileReader(watermark_pdf)
    watermark_page = watermark.getPage(0)

    pdf = PdfFileReader(input_pdf)
    pdf_writer = PdfFileWriter()

    for page in range(pdf.getNumPages()):
        pdf_page = pdf.getPage(page)
        pdf_page.mergePage(watermark_page)
        pdf_writer.addPage(pdf_page)

    with open(output_pdf, 'wb') as fh:
        pdf_writer.write(fh)
    
    '''
    if __name__ == '__main__':
        watermark(input_pdf='w9.pdf', 
                  output_pdf='watermarked_w9.pdf',
                  watermark_pdf='watermark.pdf')
    '''
    
def encrypt(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)

    '''
    if __name__ == '__main__':
        encrypt(input_pdf='reportlab-sample.pdf',
                output_pdf='encrypted.pdf',
                password='blowfish')
    '''
    
if __name__ == '__main__':
    path = r'k:\Torrent\Download\PostView.nhn.pdf'
    get_info(path)
    text_extractor(path)
    pdf_splitter(path)

on
라벨:

댓글 없음:

댓글 쓰기

피드 구독하기: 댓글 (Atom)