Merge pull request HarshCasper#221 from aastha985/insta_follower_following_scraper

Add Script to scrape Instagram User's Followers and Following and store them in a csv file.

Author: HarshCasper

Instagram_Followers_Following_Scraper/README.md

@@ -0,0 +1,22 @@
+# Instagram User's Followers and Following Scraper
+This script scraps an Instagram user's following and followers and stores them in a csv file.
+
+### Dependencies
+1. Python3
+1. selenium
+1. pandas
+1. chrome driver
+
+### Running the script
+1. Change the path to the path of chrome driver in your system.
+1.  `py main.py`
+1. Enter your instagram username ( Viewing a user's followers and following requires us to login to instagram)
+1. Enter your instagram password
+1. Enter the user's instagram username to scrap their followers and following
+1. The user's followers and following will be stored in a csv file <username>.csv
+
+### Demo
+[Watch the demo video](https://drive.google.com/file/d/165eaVN8FsYdt5E2Ztkfrhfvl3DEvAT10/view?usp=sharing)
+
+### Disclaimer
+This script is developed for educational purposes only. Any misuse of this script is not allowed. You are responsible for your own actions.

Instagram_Followers_Following_Scraper/main.py

@@ -0,0 +1,120 @@
+from selenium import webdriver
+from time import sleep
+from selenium.webdriver.common.keys import Keys
+from selenium.common.exceptions import NoSuchElementException
+import pandas as pd
+
+
+def get_users(user_type, insta_id):
+    '''Takes the user_type( a string named followers or following) 
+    and a username as argument and returns an array of the user's 
+    followers or following repectively'''
+
+    # select followers/following button
+    button = browser.find_element_by_css_selector(
+        "a[href='/"+insta_id+"/"+user_type+"/']")
+    # count of followers/following
+    no = (int)(button.text.strip().split()[0])
+    # click on followers/following button to open dialog
+    button.click()
+    # for selecting the dialog
+    users = browser.find_element_by_class_name(
+        "PZuss")
+    # for getting list of users
+    users = users.find_elements_by_css_selector(
+        "li")
+    view = browser.find_element_by_class_name("isgrP")
+    actionChain = webdriver.ActionChains(browser)
+    # for handeling scroll event on dialog
+    actionChain.context_click(on_element=view)
+    # no of followers/following in the list
+    n = len(users)
+    # while number of followers in the list is less than total number of followers of the user
+    while(n < no):
+        # for scrolling down
+        actionChain.key_down(Keys.SPACE).key_up(
+            Keys.SPACE).perform()
+        # selecting users
+        users = browser.find_element_by_class_name("PZuss")
+        # updating the number of users in the list
+        users = users.find_elements_by_css_selector("li")
+        n = len(users)
+    # extracting text
+    for j in range(len(users)):
+        users[j] = users[j].text
+    browser.get("https://www.instagram.com/"+insta_id)
+    return users
+
+
+def convert_to_csv(followers, following, insta_id):
+    '''Takes arrays of followers and following and a username 
+    as arguments and creates <username>.csv file to store the data'''
+
+    final_arr = []
+    for i in range(0, max(len(followers), len(following))):
+        follower_account = ""
+        follower_name = ""
+        following_account = ""
+        following_name = ""
+        if(i < len(followers)):
+            follower_account = followers[i].split("\n")[0]
+            follower_name = followers[i].split("\n")[1]
+        if(i < len(following)):
+            following_account = following[i].split("\n")[1]
+            following_name = following[i].split("\n")[0]
+        user = {
+            "Follower Account": follower_account,
+            "Follower Name": follower_name,
+            "Following Account": following_account,
+            "Following Name": following_name,
+        }
+        final_arr.append(user)
+    # convert to data frame
+    df = pd.DataFrame(final_arr)
+    # convert to csv
+    df.to_csv(insta_id+".csv", index=None)
+
+
+if __name__ == "__main__":
+
+    username = input("Enter your Instagram username: ")
+    password = input("Enter your Instagram password: ")
+    insta_id = input("Enter user's Instagram username for scraping: ")
+
+    # path to chromedriver
+    PATH = "C:\Program Files (x86)\chromedriver.exe"
+    browser = webdriver.Chrome(PATH)
+    browser.implicitly_wait(5)
+    browser.get("https://www.instagram.com/")
+
+    username_input = browser.find_element_by_css_selector(
+        "input[name='username']")
+    password_input = browser.find_element_by_css_selector(
+        "input[name='password']")
+
+    # enters username and password
+    username_input.send_keys(username)
+    password_input.send_keys(password)
+
+    # click on submit button
+    login_button = browser.find_element_by_xpath("//button[@type='submit']")
+    login_button.click()
+
+    # save password dialog
+    not_now_button = browser.find_element_by_xpath(
+        "//button[text()='Not Now']")
+    not_now_button.click()
+    sleep(2)
+
+    # get user's instagram page
+    browser.get("https://www.instagram.com/"+insta_id)
+    sleep(2)
+
+    try:
+        arr = ["followers", "following"]
+        followers = get_users("followers", insta_id)
+        following = get_users("following", insta_id)
+        convert_to_csv(followers, following, insta_id)
+    except NoSuchElementException:
+        print("Invalid Account/ Private Account")
+        pass