def pdf_split(filename, output_directory):
# open pdf file
pdf_file = open(filename, "rb")
pdf = PdfFileReader(pdf_file)
# list of pdf page filenames
filenames = []
# iterate through all pages
for i in range(0, pdf.getNumPages()):
# split pages and save files
outputFileName = os.path.join(output_directory, os.path.basename(filename)[:-4] + '-%d.pdf' % (i + 1))
output = PdfFileWriter()
output.addPage(pdf.getPage(i))
outputStream = open(outputFileName, "wb")
output.write(outputStream)
outputStream.close()
filenames.append(outputFileName)
return filenames
"convert \"%s\" -alpha off -resize 500x500 -quality 70 \"%s\\scr.jpg\"" % (
pdf_filename,
output_folder
)
)
print "screenshots generated"
# open pdf file
pdf_file = open(pdf_filename, "rb")
pdf = PdfFileReader(pdf_file)
# iterate through all pages
for i in range(0, pdf.getNumPages()):
# split pages and save files
outputFileName = pdf_filename.replace('.pdf', '-%d.pdf' % i)
output = PdfFileWriter()
output.addPage(pdf.getPage(i))
outputStream = open(outputFileName, "wb")
output.write(outputStream)
outputStream.close()
# convert to text and save into a file
convert_pdf(outputFileName)
translate_txt(outputFileName.replace('.pdf', '.txt'), 'libs/chars_ayna.xml')
# remove pdf page file
# os.remove(outputFileName)
print "page %d is processed" % (i + 1)
# close pdf file