ازگر کا استعمال کرتے ہوئے انسٹاگرام ڈیٹا کو کھرچنے کا طریقہ

pip install requests python-box

import requests

# Define headers to mimic a real browser request
headers = {
    "x-ig-app-id": "936619743392459",  # Instagram app ID to authenticate the request
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36",
    "Accept-Language": "en-US,en;q=0.9,ru;q=0.8",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept": "*/*",
}

# Replace this with the username you want to scrape
username = 'testtest'

# Send an API request to get profile data
response = requests.get(f'https://i.instagram.com/api/v1/users/web_profile_info/?username={username}', headers=headers)
response_json = response.json()  # Parse the response into a JSON object

proxies = {
    'http': 'http://<proxy_username>:<proxy_password>@<proxy_ip>:<proxy_port>',
    'https': 'https://<proxy_username>:<proxy_password>@<proxy_ip>:<proxy_port>',
}

response = requests.get(f'https://i.instagram.com/api/v1/users/web_profile_info/?username={username}', headers=headers, proxies=proxies)

from box import Box

response_json = Box(response.json())

# Extract user profile data
user_data = {
    'full name': response_json.data.user.full_name,
    'id': response_json.data.user.id,
    'biography': response_json.data.user.biography,
    'business account': response_json.data.user.is_business_account,
    'professional account': response_json.data.user.is_professional_account,
    'category name': response_json.data.user.category_name,
    'is verified': response_json.data.user.is_verified,
    'profile pic url': response_json.data.user.profile_pic_url_hd,
    'followers': response_json.data.user.edge_followed_by.count,
    'following': response_json.data.user.edge_follow.count,
}

# Extract video data
profile_video_data = []
for element in response_json.data.user.edge_felix_video_timeline.edges:
    video_data = {
        'id': element.node.id,
        'short code': element.node.shortcode,
        'video url': element.node.video_url,
        'view count': element.node.video_view_count,
        'comment count': element.node.edge_media_to_comment.count,
        'like count': element.node.edge_liked_by.count,
        'duration': element.node.video_duration,
    }
    profile_video_data.append(video_data)

# Extract timeline media data (photos and videos)
profile_timeline_media_data = []
for element in response_json.data.user.edge_owner_to_timeline_media.edges:
    media_data = {
        'id': element.node.id,
        'short code': element.node.shortcode,
        'media url': element.node.display_url,
        'comment count': element.node.edge_media_to_comment.count,
        'like count': element.node.edge_liked_by.count,
    }
    profile_timeline_media_data.append(media_data)

import json

# Save user data to a JSON file
with open(f'{username}_profile_data.json', 'w') as file:
    json.dump(user_data, file, indent=4)

# Save video data to a JSON file
with open(f'{username}_video_data.json', 'w') as file:
    json.dump(profile_video_data, file, indent=4)

# Save timeline media data to a JSON file
with open(f'{username}_timeline_media_data.json', 'w') as file:
    json.dump(profile_timeline_media_data, file, indent=4)

import requests
from box import Box
import json

# Headers to mimic a real browser request to Instagram's backend API
headers = {
    "x-ig-app-id": "936619743392459", 
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36",
    "Accept-Language": "en-US,en;q=0.9,ru;q=0.8",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept": "*/*",
}

# Set a proxy to avoid rate-limiting and detection (optional)
proxies = {
    'http': 'http://<proxy_username>:<proxy_password>@<proxy_ip>:<proxy_port>',
    'https': 'https://<proxy_username>:<proxy_password>@<proxy_ip>:<proxy_port>',
}

# The Instagram username to scrape
username = 'testtest'

# Send a request to Instagram's backend API to get profile data
response = requests.get(f'https://i.instagram.com/api/v1/users/web_profile_info/?username={username}', 
                        headers=headers, proxies=proxies)
response_json = Box(response.json())  # Convert the response to Box object for easy navigation

# Extract user profile data
user_data = {
    'full name': response_json.data.user.full_name,
    'id': response_json.data.user.id,
    'biography': response_json.data.user.biography,
    'business account': response_json.data.user.is_business_account,
    'professional account': response_json.data.user.is_professional_account,
    'category name': response_json.data.user.category_name,
    'is verified': response_json.data.user.is_verified,
    'profile pic url': response_json.data.user.profile_pic_url_hd,
    'followers': response_json.data.user.edge_followed_by.count,
    'following': response_json.data.user.edge_follow.count,
}

# Extract video data from the user's video timeline
profile_video_data = []
for element in response_json.data.user.edge_felix_video_timeline.edges:
    video_data = {
        'id': element.node.id,
        'short code': element.node.shortcode,
        'video url': element.node.video_url,
        'view count': element.node.video_view_count,
        'comment count': element.node.edge_media_to_comment.count,
        'like count': element.node.edge_liked_by.count,
        'duration': element.node.video_duration,
    }
    profile_video_data.append(video_data)

# Extract timeline media data (photos and videos)
profile_timeline_media_data = []
for element in response_json.data.user.edge_owner_to_timeline_media.edges:
    media_data = {
        'id': element.node.id,
        'short code': element.node.shortcode,
        'media url': element.node.display_url,
        'comment count': element.node.edge_media_to_comment.count,
        'like count': element.node.edge_liked_by.count,
    }
    profile_timeline_media_data.append(media_data)

# Save user profile data to a JSON file
with open(f'{username}_profile_data.json', 'w') as file:
    json.dump(user_data, file, indent=4)
print(f'saved json: {username}_profile_data.json')

# Save video data to a JSON file
with open(f'{username}_video_data.json', 'w') as file:
    json.dump(profile_video_data, file, indent=4)
print(f'saved json: {username}_video_data.json')

# Save timeline media data to a JSON file
with open(f'{username}_timeline_media_data.json', 'w') as file:
    json.dump(profile_timeline_media_data, file, indent=4)
print(f'saved json: {username}_timeline_media_data.json')