An pdf merge tool to auto remove annotations and merge papers

mergeFile.py

# -*- coding:utf-8 -*-
Despriptor=r'''
    An pdf merge tool to auto remove annotations and merge papers

    work-flow: 
    1. Export biblatex with attachment files throgh Zotero(https://www.zotero.org)
    2. cd to the export root folder, and excute the command `mergeFile.py -t yourtitle`
    
    requirements: 
    0.python version: tested with 3.7.3, win64
    1.python packages
        bibtexparser, PyPDF2
    2.latex package: tested with texlive
    

    Author: Lai Jun(mfary\#139.com)
'''

import bibtexparser
import glob


if __name__ == "__main__":
    import argparse
    from argparse import RawTextHelpFormatter
    import random
    import hashlib
    import shutil
    import os
    from PyPDF2 import PdfFileWriter, PdfFileReader
    import subprocess as sub
    parser = argparse.ArgumentParser(description=Despriptor,formatter_class=RawTextHelpFormatter)
    parser.add_argument('-t',dest='title', help='the title')
    args = parser.parse_args() 
    if args.title is None:    
        mytitle  =  'Paper Collections for:'
    else:
        mytitle  =  args.title
    bibfiles = glob.glob("./*.bib")
    for bibfile in bibfiles:
        file1 = open(bibfile,'r',encoding='utf-8')
        bibdata = bibtexparser.load(file1)
        file1.close()
        tmpfilename = './'+hashlib.sha224(str(random.random()).encode('utf-8')).hexdigest()
        tmpfilenameTex =tmpfilename +'.tex'
        tmpfilenamePDF =tmpfilename +'.pdf'
        tmpfile     = open(tmpfilenameTex,'w',encoding='utf8')
        preamble    = r'''
\documentclass{article}
\usepackage[final]{pdfpages}
\usepackage{fancyhdr}
\fancyhf{}
\usepackage[a4paper,bindingoffset=0.2in,%
            left=1in,right=1in,top=1in,bottom=1in,%
            footskip=.25in]{geometry}   
\fancypagestyle{plain}{%
\fancyhf{} % clear all header and footer fields
\fancyfoot[RO,RE]{{\vspace*{0.5\baselineskip}\thepage}} %RO=right odd, RE=right even
\renewcommand{\headrulewidth}{0pt}
\renewcommand{\footrulewidth}{0pt}}

\begin{document}
'''
        endString   =r'''
\end{document}'''

        listofcontents = ''
        tmpfileLists   = []
        authors        = []
        titlesandpages = []
        for oneEntry in bibdata.entries:
            if u'file' in oneEntry:
                if oneEntry[u'file'].find(';') !=-1:
                    pdffiles   =  oneEntry[u'file'].split(';')
                    print('I just reserve the first pdf file')
                    entry = pdffiles[0]
                    for pdffile in pdffiles:
                        if pdffile.find('application/pdf') !=-1:
                            entry =  pdffile
                            break
                else:
                    entry = oneEntry[u'file']

                pdfFileNameMeta = entry.split(':')
                authors.append(oneEntry[u'author'])
                tmptitle = oneEntry[u'title']
            else:
                pdfFileNameMeta  = None

            if pdfFileNameMeta is not None and  pdfFileNameMeta[2] == u'application/pdf':
                pdfFileName = u'./'+pdfFileNameMeta[1]
                tmpPdfFileName = './'+hashlib.sha224(str(random.random()).encode('utf-8')).hexdigest()+'.pdf'
                tmpfileLists.append(tmpPdfFileName)
                shutil.copy2(pdfFileName,tmpPdfFileName)
                infile = PdfFileReader(tmpPdfFileName, 'rb')
                output = PdfFileWriter()
                for i in range(infile.getNumPages()):
                    p = infile.getPage(i)
                    output.addPage(p)
                
                tmppages  =  infile.getNumPages()
            
                tmpPdfFileName = './'+hashlib.sha224(str(random.random()).encode('utf-8')).hexdigest()+'.pdf'
                tmpfileLists.append(tmpPdfFileName)
                f = open(tmpPdfFileName,'wb')
                output.write(f)
                f.close()
            else:
                tmppages = 0
                if pdfFileNameMeta is not None:
                    try:
                        print(pdfFileNameMeta[2])
                    except:
                        pass
            if pdfFileNameMeta is not None:
                titlesandpages.append({'title':tmptitle,'pages':tmppages})
                # listofcontents = listofcontents + u"""\includepdf[pages=-,pagecommand={\thispagestyle{plain}}]"""+ u'{'+pdfFileName+ u'}'+u"\n"
                listofcontents = listofcontents + r"""\includepdf[pages=-,pagecommand={\thispagestyle{plain}}]"""
                listofcontents = listofcontents + u'{'+tmpPdfFileName+ u'}'
                listofcontents = listofcontents + u"\n"
        
        fileContent = preamble+listofcontents+endString
        tmpfile.write(fileContent)
        tmpfile.close()
        
        p = sub.Popen(['xelatex', tmpfilenameTex,'-interaction=nonstopmode','-halt-on-error'],stdout=sub.PIPE,stderr=sub.PIPE)
        output, errors = p.communicate()
        for tmpfile in tmpfileLists:
            os.remove(tmpfile)
        
        # create cover 
        coverContent = r'''
\documentclass[12pt,twoside,a4paper]{report}
\usepackage[utf8]{inputenc}
\usepackage{amsmath}
\usepackage{array}
\newcolumntype{P}[1]{>{\raggedright\arraybackslash}p{#1}}
\usepackage{longtable}
\usepackage{geometry}
\usepackage{marginnote}
\usepackage{color}
\newcommand*{\titleTH}{\begingroup% T&H Typography
\raggedleft
\vspace*{\baselineskip}
%{\bfseries The Big Book of}\\[\baselineskip]
{\textcolor{red}{\Huge \textbf{yourtitle}}}\\\vspace*{3\baselineskip}
\raggedright
{yourtableofcontent} \\[0.167\textheight]


{yourAuthors}\par
\raggedleft
\vfill{\Large \today }\par
\vspace*{3\baselineskip}\endgroup}
\begin{document}
\thispagestyle{empty}
\titleTH
\end{document}
        '''
        tableofContent  = u''
        startpage = 1
        
        for titlesandpage in titlesandpages:
            tmpStr = u''
            tmpStr = titlesandpage['title']
            pages   = titlesandpage['pages']
            if pages ==0:
                pass
            else:
                tmpStr = tmpStr + u":" + str(startpage) +u'--' +str(startpage+pages-1)
                startpage = startpage+pages
        #    tmpStr = tmpStr+u'\\\\'
            if len(tableofContent) == 0:   
                tableofContent = tableofContent+tmpStr
            else:
                tableofContent = tableofContent+u'\\\\'+tmpStr
        coverContent  = coverContent.replace('yourtitle',mytitle)
        coverContent  = coverContent.replace('yourtableofcontent',tableofContent)

        authorlists =u''
        for author in authors:
            authorlists = authorlists + author +'; '
            if len(authorlists) > 1024:
                break
        coverContent  = coverContent.replace('yourAuthors',authorlists)
        tmpfilenameofCover = './'+hashlib.sha224(str(random.random()).encode('utf8')).hexdigest()
        tmpfilenameofCoverTex = tmpfilenameofCover +'.tex'
        tmpfilenameofCoverPdf = tmpfilenameofCover +'.pdf'
        tmpfile     = open(tmpfilenameofCoverTex,'w')
        try:
            tmpfile.write(coverContent)
        except:
            tmpfile.write(coverContent.encode('utf8'))
        tmpfile.close()
        p = sub.Popen(['xelatex', tmpfilenameofCoverTex,'-interaction=nonstopmode','-halt-on-error'],stdout=sub.PIPE,stderr=sub.PIPE)
        output, errors = p.communicate()

        #merge to the final pdf
        print('merge cover and pdfs')

        writer = PdfFileWriter()
        pdflist = [tmpfilenameofCoverPdf,tmpfilenamePDF]

        for pdf in pdflist:
            pdff = open(pdf,'rb')
            pdfFile = PdfFileReader(pdff)
            for pageNum in range(pdfFile.getNumPages()):
                currentPage = pdfFile.getPage(pageNum)
                writer.addPage(currentPage)

        outputStream = open("mergedFile.pdf","wb")
        writer.write(outputStream)
        outputStream.close()

        # p = sub.Popen(['pdfmerge',tmpfilenameofCoverPdf,tmpfilenamePDF,'-o mergedFile.pdf'],stdout=sub.PIPE,stderr=sub.PIPE)
        # output, errors = p.communicate()
        # print(errors)

        # del files
        texfilenamesprefix = [tmpfilenameofCover,tmpfilename]
        filetypes=[u'aux',u'log',u'pdf',u'tex']
        for fileprefix in texfilenamesprefix:
            for filetype in filetypes:
                filenames = fileprefix+u'.'+filetype
                try:
                    os.remove(filenames)
                except:
                    pass