PDF of Python automation

################################## #处理PDF和Word文档 ###################################

‘‘‘

PDF and Word documents are binary files, in addition to text,

They also save a lot of fonts, colors, and layout information

‘‘‘

‘‘‘

Extracting text from a PDF

‘‘‘

################################## #从PDF提取文本 ###################################

Import PyPDF2

Pdffileobj=open (R ' C:\Users\Administrator\Desktop\test.pdf ', ' RB ')

Pdfreader=pypdf2.pdffilereader (Pdffileobj)

Pdfreader.numpages

Pageobj=pdfreader.getpage (0)

Pageobj.extracttext ()

################################## #解压PDF #########################################

Import PyPDF2

Pdfreader=pypdf2.pdffilereader (Open (R ' C:\Users\Administrator\Desktop\test.pdf ', ' RB '))

pdfreader.isencrypted # # #是否加密

Pdfreader.getpage (0)

Pdfreader.decrypt (' Rosebud ') # # # #提供解密口令

Pageobj=pdfreader.getpage (0)

################################## #创建PDF #########################################

‘‘‘

PyPDF2 cannot write arbitrary text to PDF:

PyPDF2 ability to write PDFs, only copy pages from other PDFs, rotate pages, overlay pages, and encrypt files

‘‘‘

‘‘‘

General Way:

1. Open one or more used PDFs (source pdf) to get the Pdffilereader object

2. Create a new Pdffilewriter object

3. Copy the page from the Pdffilereader object to the Pdffilewriter object

4. Writing output PDF with Pdffilewriter object

‘‘‘

#################################################### #拷贝页面 ###################################################### #####

def merge (Pdf_one, pdf_two, filename= ' my.pdf ', output_dir=r ' C:\Users\Administrator\Desktop '):

Input_one = File (Pdf_one, ' RB ')

Input_two = File (Pdf_two, ' RB ')

Pdf_input_one = Pypdf2.pdffilereader (Input_one)

Pdf_input_two = Pypdf2.pdffilereader (input_two)

Numone = Pdf_input_one.getnumpages ()

Numtwo = Pdf_input_two.getnumpages ()

Print Numone, Numtwo

Pdf_output = Pypdf2.pdffilewriter ()

For Pagenum in range (Numone):

print ' Hereo '

Pageobj=pdf_input_one.getpage (Pagenum)

Pdf_output.addpage (Pageobj)

For Pagenum in range (Numtwo):

print ' Heret '

Pageobj=pdf_input_two.getpage (Pagenum)

Pdf_output.addpage (Pageobj)

Pdf_name = Output_dir+filename

Print Pdf_name

Output_stream = File (pdf_name, ' WB ')

Pdf_output.write (Output_stream)

Output_stream.close ()

Input_one.close ()

Input_two.close ()

print ' done! '

Merge (R ' C:\Users\Administrator\Desktop\Pairs_Trading_Quantitative Methods and Analysis.pdf ', R ' C:\Users\ Administrator\desktop\demontjoye.sm.pdf ')

#################################################### #旋转页面 ###################################################### #####

‘‘‘

Using the Rotateclockwise () and Rotatecounterclockwise () methods

The pages of a PDF document can also be rotated by 90-degree integer multiples, which are passed to these methods

Integers 90, 180, or 270

‘‘‘

def merge (Pdf_one, pdf_two, filename= ' my.pdf ', output_dir=r ' C:\Users\Administrator\Desktop '):

Input_one = File (Pdf_one, ' RB ')

Input_two = File (Pdf_two, ' RB ')

Pdf_input_one = Pypdf2.pdffilereader (Input_one)

Pdf_input_two = Pypdf2.pdffilereader (input_two)

Numone = Pdf_input_one.getnumpages ()

Numtwo = Pdf_input_two.getnumpages ()

Print Numone, Numtwo

Pdf_output = Pypdf2.pdffilewriter ()

For Pagenum in range (Numone):

print ' Hereo '

Pageobj=pdf_input_one.getpage (Pagenum)

Pageobj=pageobj.rotateclockwise (90)

Pdf_output.addpage (Pageobj)

For Pagenum in range (Numtwo):

print ' Heret '

Pageobj=pdf_input_two.getpage (Pagenum)

Pageobj=pageobj.rotateclockwise (90)

Pdf_output.addpage (Pageobj)

Pdf_name = Output_dir+filename

Print Pdf_name

Output_stream = File (pdf_name, ' WB ')

Pdf_output.write (Output_stream)

Output_stream.close ()

Input_one.close ()

Input_two.close ()

print ' done! '

Merge (R ' C:\Users\Administrator\Desktop\Pairs_Trading_Quantitative Methods and Analysis.pdf ', R ' C:\Users\ Administrator\desktop\demontjoye.sm.pdf ')

#################################################### #叠加页面 ###################################################### #####

Import PyPDF2

Minutesfile=open (R ' C:\Users\Administrator\Desktop\Pairs_Trading_Quantitative Methods and Analysis.pdf ', ' RB ')

Pdfreader=pypdf2.pdffilereader (Minutesfile)

Minutesfirstpage=pdfreader.getpage (0)

Pdfwatermarkreader=pypdf2.pdffilereader (Open (R ' C:\Users\Administrator\Desktop\deMontjoye.SM.pdf ', ' RB '))

Minutesfirstpage.mergepage (pdfwatermarkreader.getpage (0))

Pdfwriter=pypdf2.pdffilewriter ()

Pdfwriter.addpage (Minutesfirstpage)

For Pagenum in range (1,pdfreader.numpages):

Pageobj=pdfreader.getpage (Pagenum)

Pdfwriter.addpage (Pageobj)

Resultpdffile=open (R ' C:\Users\Administrator\Desktop\merge.pdf ', ' WB ')

Pdfwriter.write (Resultpdffile)

Minutesfile.close ()

Resultpdffile.close ()

#################################################### #加密PDF ##################################################### ######

Import PyPDF2

Pdffile=file (R ' C:\Users\Administrator\Desktop\deMontjoye.SM.pdf ', ' RB ')

Pdfreader=pypdf2.pdffilereader (Pdffile)

Pdfwriter=pypdf2.pdffilewriter ()

For Pagenum in range (pdfreader.numpages):

Pdfwriter.addpage (Pdfreader.getpage (pagenum))

Pdfwriter.encrypt (' Swordfish ')

Resultpdf=file (R ' C:\Users\Administrator\Desktop\t.pdf ', ' WB ')

Pdfwriter.write (Resultpdf)

Resultpdf.close ()

PDF of Python automation