insta_followers_data.py

import requests
import json
import time
import csv
import pandas as pd

# step 1: get all followers html content manually from insta page. in one line keep only one username (without quotes and comma.)


def get_usernames():
    with open('followers_usernames.txt') as f:
        return [line.strip() for line in f]


# step 2: get followers data
with open('followers_raw_data.txt', 'a') as f:
    for i, username in enumerate(get_usernames()):
        print(f'{i} - getting data for {username}')
        url = f"https://www.instagram.com/{username}/?__a=1"
        try:
            response = requests.request("GET", url, headers={}, data={})
        except Exception as e:
            print(e)
            time.sleep(60 * 60)
        try:
            data = response.json()
            json.dump(data, f)
            f.write('\n')
        except Exception as e:
            print(e)
        time.sleep(1)


# step 3: remove unwanted data
re = list()
with open('followers_raw_data.txt', 'r') as f:
    for each in f:
        data = json.loads(each)
        ss = each['graphql']['user']
        [ss.pop(x) for x in ['edge_felix_video_timeline', 'edge_owner_to_timeline_media',
                             'edge_saved_media', 'edge_media_collections', 'edge_related_profiles']]
        ss.update({"edge_followed_by": each['graphql']['user']['edge_followed_by']['count'], 'edge_follow': each['graphql']['user']
                   ['edge_follow']['count'], 'edge_mutual_followed_by': each['graphql']['user']['edge_mutual_followed_by']['count']})
        re.append(ss)

# step 4: save the data to csv file
with open('followers_data.csv', 'w') as f:
    csv_writer = csv.writer(f)
    d = False
    for emp in re:
        if not d:
            header = emp.keys()
            csv_writer.writerow(header)
            d = True
        csv_writer.writerow(emp.values())