Python PyPDF2 模块，PdfFileMerger() 实例源码

def render_to_response(self, context, **kwargs):
        context['pdf'] = True
        pdf_response = HttpResponse(content_type='application/pdf')
        response = super().render_to_response(context, **kwargs)
        response.render()
        try:
            html = HTML(string=response.content)
            fileobj = io.BytesIO()
            html.write_pdf(fileobj)
            merger = PdfFileMerger()
            merger.append(fileobj)
            if self.object.science_case_file:
                merger.append(self.object.science_case_file.file)
            if self.object.experimental_design_file:
                merger.append(self.object.experimental_design_file.file)
            merger.write(pdf_response)
        except Exception as exc:
            error = 'There was an error generating your pdf. {}'
            messages.error(self.request, error.format(str(exc)))
            return HttpResponseRedirect(reverse('sciapplications:index'))
        return pdf_response

def create(self, cr, uid, ids, data, context=None):
        pool = registry(cr.dbname)
        merger = PdfFileMerger()
        outfiles = []
        for p in pool.get(self.model).read(cr,uid,ids):
            outfiles.append(self.newfilename())
            sla = self.render(cr,uid,p,data.get('template') or self.template)
            if self.report_type == 'scribus_sla':
                os.unlink(outfiles[-1])
                return (sla.read(),'sla')
            command = "xvfb-run -a scribus-ng -ns -g %s -py %s -pa -o %s" % (sla.name,os.path.join(get_module_path('report_scribus'), 'scribus.py'),outfiles[-1])
            _logger.info(command)
            res = os.system(command)
            sla.close()
            if not os.path.exists(outfiles[-1]) or os.stat(outfiles[-1]).st_size == 0:
                raise MissingError('There are something wrong with the template or scribus installation')
            merger.append(PdfFileReader(file(outfiles[-1], 'rb')))
        outfile = tempfile.NamedTemporaryFile(mode='w+b',suffix='.pdf')
        merger.write(outfile.name)
        for filename in outfiles:
            os.unlink(filename)
        outfile.seek(0)
        pdf = outfile.read()
        outfile.close()
        return (pdf,'pdf')

def main():
    all_pdfs = get_all_pdf_files(os.path.expanduser('~lmx/'))
    if not all_pdfs:
        raise SystemExit('No pdf file found!')

    merger = PyPDF2.PdfFileMerger()

    with open(all_pdfs[0], 'rb') as first_obj:
        merger.append(first_obj)

    for pdf in all_pdfs[1:]:
        with open(pdf, 'rb') as obj:
            reader = PyPDF2.PdfFileReader(obj)
            merger.append(fileobj=obj, pages=(1, reader.getNumPages()))

    with open('merge-pdfs.pdf', 'wb') as f:
        merger.write(f)

def merge_pdf(request, technology_id):

    # generate_quality_pdf(request, 1)
    technology = Technology.objects.get(id=technology_id)
    operation_groups = technology.operation_groups.all()

    data = technology_pdf_data(technology_id)
    merger = PdfFileMerger()
    file_name = 'technology.pdf'
    with open(file_name, 'w') as mypdf:
        mypdf.write(data)
    merger.append(PdfFileReader(file(file_name, 'rb')))
    os.remove(file_name)

    for operation_group in operation_groups:
        file_name = 'operation_group_%d.pdf' %(operation_group.id)
        with open(file_name, 'w') as mypdf:
            data2= technology_subpicture_pdf_data(operation_group.id)
            mypdf.write(data2)
        merger.append(PdfFileReader(file(file_name, 'rb')))
        os.remove(file_name)

    output_name = "%s.pdf" %(technology.code)
    merger.write(str(output_name))

    response = HttpResponse(mimetype='application/pdf')
    with open(output_name, 'rb') as mypdf:
        response.write(mypdf.read())

    os.remove(output_name)

    response['Content-Disposition'] = 'attachment; filename=%s' %(output_name)
    return response

def overlay_hocr_pages(self, dpi, hocr_filenames, orig_pdf_filename):

        logging.debug("Going to overlay following files onto %s" % orig_pdf_filename)
        # Sort the hocr_filenames into natural keys!
        hocr_filenames.sort(key=lambda x: self.natural_keys(x[0] ))
        logging.debug(hocr_filenames)

        pdf_dir, pdf_basename = os.path.split(orig_pdf_filename)
        basename = os.path.splitext(pdf_basename)[0]
        pdf_filename = os.path.join(pdf_dir, "%s_ocr.pdf" % (basename))

        text_pdf_filenames = []
        for img_filename, hocr_filename in hocr_filenames:
            text_pdf_filename = self.overlay_hocr_page(dpi, hocr_filename, img_filename)
            logging.info("Created temp OCR'ed pdf containing only the text as %s" % (text_pdf_filename))
            text_pdf_filenames.append(text_pdf_filename)

        # Now, concatenate this text_pdfs into one single file.
        # This is a hack to save memory/running time when we have to do the actual merge with a writer

        all_text_filename = os.path.join(pdf_dir, "%s_text.pdf" % (basename))
        merger = PdfFileMerger()
        for text_pdf_filename in text_pdf_filenames:
            merger.append(PdfFileReader(file(text_pdf_filename, 'rb')))
        merger.write(all_text_filename)
        merger.close()
    del merger


        writer = PdfFileWriter()
        orig = open(orig_pdf_filename, 'rb')
        text_file = open(all_text_filename, 'rb')

        for orig_pg, text_pg in zip(self.iter_pdf_page(orig), self.iter_pdf_page(text_file)):
            orig_pg = self._get_merged_single_page(orig_pg, text_pg)
            writer.addPage(orig_pg)

        with open(pdf_filename, 'wb') as f:
            # Flush out this page merge so we can close the text_file
            writer.write(f)

        orig.close()
        text_file.close()

        # Windows sometimes locks the temp text file for no reason, so we need to retry a few times to delete
        for fn in text_pdf_filenames:
            #os.remove(fn)
            Retry(partial(os.remove, fn), tries=10, pause=3).call_with_retry() 

        os.remove(all_text_filename)
        logging.info("Created OCR'ed pdf as %s" % (pdf_filename))

        return pdf_filename