Simple URL grabber for instagram written in python3

insGrab.py

#!/usr/bin/env python3

"""
by - Epsi R Nurwijadi
modified by - Randall Tux
"""

import requests
import json
import time

from lxml import html
from pprint import pprint


import requests

user = input('Input username : ')
url = "https://www.instagram.com/" + user + "/"

print(url)
print("")

r_main = requests.get(url)
page_main = html.fromstring(r_main.text)

elements_main = page_main.xpath('//script[contains(., "_sharedData")]/text()')
element_data = elements_main[0]

element_data = element_data.replace("window._sharedData = ", "")
element_data = "[" + element_data + "]"
element_data = element_data.replace("};]", "}]")

json_data = json.loads(element_data)
json_data = json_data[0]["entry_data"]["ProfilePage"][0]["user"]["media"]
json_nodes = json_data["nodes"]

# count = len(json_nodes)
# pprint(json_nodes)

images = []
videos = []
sidecars = []

urls_image = []
urls_video = []
urls_sidecar = []


for json_node in json_nodes:
    typename = json_node["__typename"]
    code = json_node["code"]
    
    if typename == "GraphImage":
        images.append(code)
    elif typename == "GraphVideo":
        videos.append(code)
    elif typename == "GraphSidecar":
        sidecars.append(code)

print(time.strftime('%X'))
for image in images:
    url_image = "https://www.instagram.com/p/"+image+"/"
    print(url_image)

    r_post = requests.get(url_image)
    page_post = html.fromstring(r_post.text)

    elements_post = page_post.xpath('//script[contains(., "_sharedData")]/text()')
    element_data = elements_post[0]

    element_data = element_data.replace("window._sharedData = ", "")
    element_data = "[" + element_data + "]"
    element_data = element_data.replace("};]", "}]")

    json_data = json.loads(element_data)
    json_data = json_data[0]["entry_data"]["PostPage"][0]["media"]["display_src"]

    urls_image.append(json_data)

print(time.strftime('%X'))
for video in videos:
    url_video = "https://www.instagram.com/p/"+video+"/"
    print(url_video)

    r_post = requests.get(url_video)
    page_post = html.fromstring(r_post.text)

    elements_post = page_post.xpath('//script[contains(., "_sharedData")]/text()')
    element_data = elements_post[0]

    element_data = element_data.replace("window._sharedData = ", "")
    element_data = "[" + element_data + "]"
    element_data = element_data.replace("};]", "}]")

    json_data = json.loads(element_data)
    json_data = json_data[0]["entry_data"]["PostPage"][0]["media"]["video_url"]
    
    urls_video.append(json_data)
    
print(time.strftime('%X'))
for sidecar in sidecars:
    url_sidecar = "https://www.instagram.com/p/"+sidecar+"/"
    print(url_sidecar)

    r_post = requests.get(url_sidecar)
    page_post = html.fromstring(r_post.text)

    elements_post = page_post.xpath('//script[contains(., "_sharedData")]/text()')
    element_data = elements_post[0]

    element_data = element_data.replace("window._sharedData = ", "")
    element_data = "[" + element_data + "]"
    element_data = element_data.replace("};]", "}]")

    json_data = json.loads(element_data)
    json_data = json_data[0]["entry_data"]["PostPage"][0]["media"]
    edges = json_data["edge_sidecar_to_children"]["edges"]
    
    for edge in edges:
        json_data = edge["node"]["display_url"]
    
        urls_sidecar.append(json_data)


print("")
print("Images")
    
for url_image in urls_image:
    print(url_image)

print("")
print("Videos")

for url_video in urls_video:
    print(url_video)

print("")
print("SideCar")
    
for url_sidecar in urls_sidecar:
    print(url_sidecar)