turn pdf pages to jpg (not png, since jpg is smaller than png, website friendly)

pdf2jpg.py

# extract pdf to jpg
from pdf2image import convert_from_path
from tqdm import tqdm
import os
import uuid


input_path = 'corridor.pdf'
uid = uuid.uuid4().hex[:4]
output_path = uid + '-' + input_path.split('.')[0]
if not os.path.exists(output_path):
    os.makedirs(output_path)
    

pages = convert_from_path(input_path, 500)
for idx, p in tqdm(enumerate(pages)):
    new_f = output_path + '/' + output_path + '-' + str(idx) + '.jpg'
    p.save(new_f, quality=85)


os.rename(input_path, uid+'-'+input_path)