You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
33 lines
1.3 KiB
33 lines
1.3 KiB
4 months ago
|
# this is for doing some math operations
|
||
|
|
import math
|
||
|
|
# this is for handling the PDF operations
|
||
|
|
import fitz
|
||
|
|
# importing PhotoImage from tkinter
|
||
|
|
from tkinter import PhotoImage
|
||
|
|
|
||
|
|
class PDFMiner:
|
||
|
|
def __init__(self, filepath):
|
||
|
|
# creating the file path
|
||
|
|
self.filepath = filepath
|
||
|
|
# opening the pdf document
|
||
|
|
self.pdf = fitz.open(self.filepath)
|
||
|
|
# loading the first page of the pdf document
|
||
|
|
self.first_page = self.pdf.load_page(0)
|
||
|
|
# getting the height and width of the first page
|
||
|
|
self.width, self.height = self.first_page.rect.width, self.first_page.rect.height
|
||
|
|
# initializing the zoom values of the page
|
||
|
|
zoomdict = {800:0.8, 700:0.6, 600:1.0, 500:1.0}
|
||
|
|
# getting the width value
|
||
|
|
width = int(math.floor(self.width / 100.0) * 100)
|
||
|
|
# zooming the page
|
||
|
|
self.zoom = zoomdict[width]
|
||
|
|
|
||
|
|
# this will get the metadata from the document like
|
||
|
|
# author, name of document, number of pages
|
||
|
|
def get_metadata(self):
|
||
|
|
# getting metadata from the open PDF document
|
||
|
|
metadata = self.pdf.metadata
|
||
|
|
# getting number of pages from the open PDF document
|
||
|
|
numPages = self.pdf.page_count
|
||
|
|
# returning the metadata and the numPages
|
||
|
|
return metadata, numPages
|