#!/usr/bin/python
import os
import base64
import warnings
import pandas as pd
import pypdfium2 as pdfium
from pypdf import PdfReader
from PIL import Image

def into_jpg(file, file_loc):
    try:
        
        write_loc = '/home/pi/code/images/train'
        new_file_name = str(base64.b64encode(str.encode(file.split('.')[0]))[:15], 'utf-8')
        new_file_loc = os.path.join(write_loc, new_file_name + '.jpg')
        new_count = 1
        
        pdfs = pdfium.PdfDocument(file_loc)
        n_pages = len(pdfs)
        
        for page_num in range(len(pdfs)):
            page = pdfs.get_page(page_num)
            pil_image = page.render(
                    scale = 1,
                    rotation = 0,
                    crop = (0, 0, 0, 0)
                    #optimise_mode = pdfium.OptimiseMode.NONE
                ).to_pil()
            
            pil_image.save(os.path.join(write_loc, f'{new_file_name}_{page_num+1}.jpg'))
            new_file_loc = os.path.join(write_loc, new_file_name + '_' + str(page_num) + '.jpg')
              
    except Exception as exp:
        print(exp)
        
    
    return

file_dir = '/home/pi/code/ma_1'
file_loc = None
count = 1
for file in os.listdir(file_dir):
    if os.path.isdir(os.path.join(file_dir, file)):
        for file_ in os.listdir(os.path.join(file_dir, file)):
            file_loc = os.path.join(os.path.join(file_dir, file), file_)
            IsProcess = True
            while IsProcess: 
                if os.path.isfile(file_loc):
                    try:
                        PdfReader(file_loc)
                        print('File Location_{0}:'.format(count), file_loc)
                        into_jpg(file_, file_loc)
                        
                        IsProcess = False
                    except Exception as exp:
                        print(exp)
                        
    count = count + 1
           

import pdf2image

# can use glob to get a list of pdfs and loop through the list
pdf = "2_cv外贸助理.pdf"
# for saving various pdfs
path2pdf = '/home/pedro/babystuff/'
# for saving split pdfs as jpg
path2jpg = '/home/pedro/babystuff/pdf2jpg/'

def splitPDF(aPDF, source, destination):
    print(f'Splitting {source + aPDF} 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

(Sep-04-2023, 08:42 AM)Pedroski55 Wrote: I often split PDFs to jpgs for OMR. This works well for me.

import pdf2image

# can use glob to get a list of pdfs and loop through the list
pdf = "2_cv外贸助理.pdf"
# for saving various pdfs
path2pdf = '/home/pedro/babystuff/'
# for saving split pdfs as jpg
path2jpg = '/home/pedro/babystuff/pdf2jpg/'

def splitPDF(aPDF, source, destination):
    print(f'Splitting {source + aPDF} 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

(Sep-05-2023, 06:19 AM)koklimabc Wrote: hm. Tq.