elnazsn1988

# pdfx usage: http://pdfx.cs.man.ac.uk/usage
# requests docs: http://docs.python-requests.org/en/latest/user/quickstart/#post-a-multipart-encoded-file
import requests # get it from http://python-requests.org or do 'pip install requests'

url = "http://pdfx.cs.man.ac.uk"

def pypdfx(filename):
  '''
	Filename is a name of a pdf file WITHOUT the extension
	The function will print messages, including the status code,

elnazsn1988

def fonts(doc, granularity=False):
    """Extracts fonts and their usage in PDF documents.

    :param doc: PDF document to iterate through
    :type doc: <class 'fitz.fitz.Document'>
    :param granularity: also use 'font', 'flags' and 'color' to discriminate text
    :type granularity: bool

    :rtype: [(font_size, count), (font_size, count}], dict
    :return: most used fonts sorted by count, font style information

elnazsn1988

import os
import cv2
from itertools import chain
import base64
import pandas as pd
import requests
import json

def ocr_using_google_api(image_path, request_url):
    '''

elnazsn1988

import os
import cv2
from itertools import chain
import base64
import pandas as pd
import requests
import json

def ocr_using_google_api(image_path, request_url):
    '''

elnazsn1988

from btgym import BTgymEnv
import IPython.display as Display
import PIL.Image as Image
from gym import spaces


import gym
import numpy as np
import random

elnazsn1988

#!/usr/bin/env python
'''Crop an image to just the portions containing text.

Usage:

    ./crop_morphology.py path/to/image.jpg

This will place the cropped image in path/to/image.crop.png.

For details on the methodology, see