Several pdf files to text

[Pedroski55]

HI again, just had some free time, so I tidied up my pdf to text program.

You just need to change the paths, I don't use Windows, so I am not too sure about the correct format.

Then you can paste this in your Idle shell and enter myApp()

Works well for me! The girlfriend might need it again someday, have to keep her happy

def myApp():
    import os    
    import pdf2image
    from PIL import Image
    import pytesseract

    # set your paths

    source = '/home/pedro/babystuff/pdf2text/'
    destination_jpg = '/home/pedro/babystuff/pdf2jpg/'
    save_text_path = '/home/pedro/babystuff/ocr_textfiles/'

    # get the pdf files

    files = os.listdir(source)
    mypdfs = []

    # maybe there are some other files in there, so only get .pdf files
    for f in files:
        if f.endswith('.pdf'):
            mypdfs.append(f)

    # get rid of the jpg files after reading them

    def junkjpgs(path):
        print('Clearing out the folders we use, in case there is anything in there ... ')
        pics = os.listdir(path)
        if len(pics) == 0:
            print('Nothing in ' + path + '\n\n')
            return
        for file in pics:
            os.remove(path + file)
        print('ALL files removed from: ' + path + '\n\n')

    # in case there are any old jpg files in the jpg folder
    junkjpgs(destination_jpg)

    # crack the PDF open

    def splitPDF(aPDF, source, destination):
        print('Splitting the PDF to individual jpgs ... ')
        outputName = aPDF.split('.')
        savename = outputName[0]    
        # images is a list
        images = pdf2image.convert_from_path(source + aPDF)
        i=1
        for image in images:
            image.save(destination + savename + str(i) + '.jpg', 'JPEG')
            i+=1           
        print('PDF split to .jpgs and all saved in: ' + destination + '\n\n')
        savetextname = savename + '.txt'
        return savetextname

    def convert2text(name):
        # get the jpgs
        jpgFiles = os.listdir(destination_jpg)
        jpgFiles.sort()
        this_text = open(save_text_path + name, 'a')
        # this works fine
        for i in range(len(jpgFiles)):
            chiText1 = pytesseract.image_to_string(Image.open(destination_jpg + jpgFiles[i]), lang='chi_sim')
            print('Page ' + str(i + 1) + ' done')
            this_text.write(chiText1)
            print('Next loop coming up')
        this_text.close()
        print('removing the jpgs ... ')
        junkjpgs(destination_jpg)
        print('finished this PDF ... ')
        

    for f in mypdfs:
        text_name = splitPDF(f, source, destination_jpg)
        convert2text(text_name)