نحوه استخراج متن از PDF از طریق Python API from operator import itemgetter from itertools import groupby import fitz doc = fitz.open( 'mydocument.pdf' ) pages = [ doc[ i ] for i in range( doc.pageCount ) ] for page in pages: text_words = page.getTextWords() # The words should be ordered by y1 and x0 sorted_words = SortedCollection( key = itemgetter( 3, 0 …