Anonymous Anonymous - 2 years ago
1590 0

Scrapes data from the top 9 posts on Instagram



# This script is written for personal research and is not endorsed by Instagram.
# Use at your own risk!
# -*- coding: utf-8 -*-
import csv
import requests
from urllib.request import Request, urlopen
import json
import re
import random
import time
import os
from fake_useragent import UserAgent
from random import randint
from time import sleep

ua = UserAgent(cache=False)
ts = time.gmtime()
timestamp = time.strftime("%d-%m-%Y %H-%M", ts)

def read_keywords(t_file):
        with open(t_file) as f:
            keyword_list =
        return keyword_list

def read_proxies(p_file):
        with open(p_file) as f:
            proxy_list =
        return proxy_list

data_filename = f'Hashtag Scrape {timestamp}.csv'
KEYWORD_FILE = './hashtags.txt'
DATA_FILE = './' + data_filename
PROXY_FILE = './proxies.txt'
keywords = read_keywords(KEYWORD_FILE)
proxies = read_proxies(PROXY_FILE)

#Ask for randomisation input fields
low = input("Please enter minimal delay time (in seconds): ")
low_random = int(low)
high = input("Please enter maximal delay time (in seconds): ")
high_random = int(high)

for keyword in keywords:
    import urllib, json, requests
    if len(proxies)!=0:
        proxy_ip = random.choice(proxies)
        proxy_support = urllib.request.ProxyHandler({'https':proxy_ip})
        opener = urllib.request.build_opener(proxy_support)
    prepare_url = urllib.request.Request(
            'User-Agent': ua.random
    url = urllib.request.urlopen(prepare_url)

    post_info = {}
    response = json.load(url) #response is the JSON dump of the url.

    #defining some script helpers
    top_post_count = len(response['graphql']['hashtag']['edge_hashtag_to_top_posts']['edges'])
    likes_value = comments_value =[]

    #Getting the general tag data
    hashtag_name = response['graphql']['hashtag']['name']
    post_count = response['graphql']['hashtag']['edge_hashtag_to_media']['count']
    hashtag_url = f'{keyword}'
    post_ready_tag = f'#{keyword}'
    top_posts = response['graphql']['hashtag']['edge_hashtag_to_top_posts']['edges']
    #calculate the active days ago 
    most_recent_post = response['graphql']['hashtag']['edge_hashtag_to_media']['edges'][0]['node']['taken_at_timestamp']
    import datetime
    from dateutil import relativedelta
    post_datetime = datetime.datetime.fromtimestamp(most_recent_post).strftime('%Y-%m-%d %H:%M:%S')
    post_cleandate = datetime.datetime.fromtimestamp(most_recent_post).strftime('%Y-%m-%d')
    from datetime import datetime, date
    most_recent_clean = datetime.strptime(post_cleandate, '%Y-%m-%d')
    today = datetime.strptime(str(,'%Y-%m-%d')
    posted_days_ago = relativedelta.relativedelta(today, most_recent_clean).days

    for i in range(top_post_count):
        #Getting data from top posts
        top_post_likes = response['graphql']['hashtag']['edge_hashtag_to_top_posts']['edges'][i]['node']['edge_liked_by']
        post_like = response['graphql']['hashtag']['edge_hashtag_to_top_posts']['edges'][i]['node']['edge_liked_by']['count']
        post_comment = response['graphql']['hashtag']['edge_hashtag_to_top_posts']['edges'][i]['node']['edge_media_to_comment']['count']
    print(f'Writing {keyword} to output file')
    with open(data_filename, 'a', newline='',  encoding='utf-8') as data_out:
            fieldnames = ('Hashtag','Category','Niche','Loc. Country','Hashtags FB.%','Followers FB.%','Engagers FB.%',\
            'Active Days Ago','Post Count','Ranking Difficulty','AVG. Likes',\
            'MAX. Likes','MIN. Likes','AVG. Comments','Hashtag URL','Post Ready Tag')
            csv_writer = csv.DictWriter(data_out, fieldnames=fieldnames)
                'Hashtag': hashtag_name,
                'Category' :'',
                'Niche': '',
                'Loc. Country':'',
                'Hashtags FB.%':'',
                'Followers FB.%':'',
                'Engagers FB.%':'',
                'Ranking Difficulty' : min(likes_value) + (0.5 * (round(sum(likes_value)/len(likes_value),2)) - min(likes_value)),
                'Active Days Ago': posted_days_ago,
                'Post Count': post_count,
                'AVG. Likes': round(sum(likes_value)/len(likes_value),2),
                'MAX. Likes': max(likes_value),
                'MIN. Likes': min(likes_value),
                'AVG. Comments': round(sum(comments_value)/len(comments_value),2),
                'Hashtag URL': hashtag_url,
                'Post Ready Tag': post_ready_tag

        #Randomly pause script based on input values
#cleaning up the file: 
destination = data_filename[:-4] + '_unique.csv'
target = open(destination, 'w',encoding='utf-8')
# Let the user know you are starting, in case you are de-dupping a huge file 
print("\nRemoving duplicates from %r" % data_filename)

# Initialize variables and counters
unique_lines = set()
source_lines = 0
duplicate_lines = 0
with open(data_filename, 'r',encoding='utf-8') as data:
# Loop through data, write uniques to output file, skip duplicates.
    for line in data:
        source_lines += 1
        # Strip out the junk for an easy set check, also saves memory
        line_to_check = line.strip('\r\n')	
        if line_to_check in unique_lines: # Skip if line is already in set
            duplicate_lines += 1
        else: # Write if new and append stripped line to list of seen lines

os.rename(destination, data_filename)
print("SUCCESS: Removed %d duplicate line(s) from file with %d line(s)." % \
 (duplicate_lines, source_lines))
print("Wrote output to %r\n" % data_filename)
print("\n" + 'ALL DONE !!!! ')
Recommended from our users: Dynamic Network Monitoring from WhatsUp Gold from IPSwitch. Free Download